The end of the year is coming, and with it, planning season. Budgets get set, channels get picked, and targets get handed down. Every one of those decisions rests on an assumption about who your customers are and where you'll find more of them.

So before you lock anything in, ask yourself: can you really plan if you don't _truly_ know your audience?

Most teams know a lot about how people interact with their brand. They know who clicked, who visited, and who bought. What they often don't know is who those people are: their life stage, their household, their finances, and what sets them apart from the people who didn't buy. That's the [context gap](https://faraday.ai/blog/consumer-context-data-ai), and it matters most when the stakes are highest.

When teams run into that gap at planning time, the usual options aren't complete. Go with gut feel. Settle an internal debate about which segment matters most. Or bring in a consulting firm, which can cost six figures and often takes longer than you'd hoped.

An Insights Report from Faraday is a different option: answers built on real data, delivered in less than one week, not after weeks or even months of lead time.

## What an Insights Report is

It brings together two things Faraday already does: [persona analysis](https://faraday.ai/blog/what-are-ai-customer-personas) and [market opportunity analysis](https://faraday.ai/blog/unlocking-growth-with-market-opportunity-analysis). Persona analysis tells you who your best customers are by grouping them into distinct, data-driven profiles. Market opportunity analysis tells you how many more people like them are out there, and where. Together, they answer the question behind most planning: who should we be going after, and how big is the opportunity?

We start with the two or three questions that matter most to you. Common ones are "Who are our best customers?", "Why do some leads convert and others don't?", and "What's our penetration by market?" Then we match your customer records to the [Faraday Identity Graph](https://faraday.ai/blog/whats-in-faraday-identity-graph), which covers 1,400+ data points on 240+ million US consumers and their households. Your records show you who bought. Faraday's data shows you all the details behind that purchase: who those people _actually_ are.

The report connects and compares the two, using the same data and back-end systems that power the rest of the Faraday platform (not an LLM guessing from a prompt and limited context). The result is one report that shows who your best customers are, what sets them apart, and how many more people like them you can still reach.

## Using an Insights Report to plan

For most marketers, planning boils down to a handful of critical decisions: who to target, how to reach them, what to say, and where to put the budget.

An Insights Report gives you context for each one:

### Who your best customers are

Most customer bases aren't a single audience. When we group a client's best customers into personas, they often split into several distinct profiles that need different creative and different media. Knowing that before you plan means you can build for each group instead of averaging across them.

### Who converts, and who doesn't

Comparing people who bought with people who engaged but didn't is often where the most useful findings come from. Sometimes the two groups look nearly identical on the surface, and the difference only shows up in one or two specific traits. Those traits are what you can target, score, and act on.

### How much opportunity is left

Once you know who your best customers are, you can see how many more people like them exist and where they live. That tells you whether a market deserves more spend, or whether you've already reached most of it.

### Which channels and messages fit

Personas carry more than demographics. They show how people tend to shop, whether they respond to mail, and what they care about. That gives you a starting point for channel mix and messaging before you spend a dollar testing it.

## It's not just for end-of-year planning

And while planning season is a natural time for this kind of analysis, it isn't the only one.

Take a new CMO a few weeks into the job. They've inherited a strategy, a budget, and a set of segments someone else built. They need to know whether those segments hold up, and they need to know before their first big decision. This analysis gives them a data-driven read on the customer base in their first 90 days, so they can keep what works and change what doesn't.

The same goes for any moment when a big question comes up: entering a new market, launching a product line, rethinking how you buy leads, or settling a debate about who your best customers are. If the answer depends on knowing who your customers are, an Insights Report is built for it.

## Another way to get these insights

If you'd rather explore the data yourself, [Ask Faraday](https://faraday.ai/blog/introducing-ask-faraday) lets you ask questions about your customers in plain language, in whatever LLM you already use. But it isn't the same as "asking ChatGPT." Ask Faraday's answers are backed by Faraday's data, not a hallucination or a guess. It's the same data our enterprise predictive models are built on, piped directly into your LLM. With it, you can see how your customers compare with your markets or with the US as a whole, without building the analysis yourself.

## No two Insights Reports look alike

Every report starts from your questions, so every report looks different. Here are a few examples, with details left out to keep our clients anonymous.

A financial services company wanted to understand why some leads enrolled while others engaged and then walked away. We analyzed their full funnel, from people who never responded to long-standing clients, and grouped each stage into personas. Their best clients turned out to be three distinct profiles, each reached through a different channel. The clearest difference between people who enrolled and people who didn't came down to a single financial trait, a signal they can build directly into how they score leads. They got the report along with the underlying data, so their own team could keep working with it.

![Sample customer analysis report for a financial services company, showing records analyzed, match rate, outcome cohorts, and personas](/images/blog/insights-reports-planning/financial-services-customer-analysis.png)

_Sample report with illustrative data._

An online apparel brand had launched a new product line and wanted to know who was buying it. We compared those buyers with the brand's other customers and looked at where the line fit in the broader market. The new buyers earned about the same as everyone else. What set them apart was their life stage, where they lived, and how they found the brand. That pointed to a clear plan: target on life stage rather than income, concentrate spend in the metro areas where buyers clustered, and hold the price.

![Sample customer insights report for an apparel brand, comparing new-collection buyers with other customers by life stage](/images/blog/insights-reports-planning/apparel-new-collection-buyers.png)

_Sample report with illustrative data._

A home improvement company wanted to turn its personas into campaigns. Their report became a persona starter kit. For each persona, it covered what the data shows, how to personalize, a core message, sample subject lines, the tone to aim for and avoid, and three tests to run first. It reads more like a campaign brief than an analysis.

![Sample persona starter kit for a home improvement company, showing four personas with key stats and a core message](/images/blog/insights-reports-planning/home-improvement-persona-starter-kit.png)

_Sample report with illustrative data._

Yours will look different, because your questions are different.

## Get started

Planning season is already here. [Talk to a context consultant](https://faraday.ai/talk-to-sales) about an Insights Report, and go into next year knowing who your customers actually are.

## FAQ

### What data do I need to provide?

Your customer records, at minimum. The more of your funnel you can share, such as who converted, who engaged but didn't, and who never responded, the more questions the report can answer. Faraday matches those records to the Faraday Identity Graph and adds the context.

### How long does it take?

It depends on your questions and how quickly your data is ready. Once your data is in, the analysis can come together in days, not months.

### Is an Insights Report the same as Faraday Enterprise?

No. It's a focused engagement built around a few specific questions. From there, teams typically move into an Enterprise plan to put what they learned to work. Others find the report shows them exactly which data points they need, and they go straight to Faraday Pro.

An Insights Report combines Faraday's persona analysis and market opportunity analysis into one report, built around the questions you need answered before your next big decision.

Who are your customers, really? Find out with a Faraday Insights Report

_TL;DR: Ask Faraday is a new Faraday capability that lets marketing teams ask questions about the US population from Claude, ChatGPT, and other AI assistants. Answers come from the [Faraday Identity Graph (FIG)](https://faraday.ai/blog/whats-in-faraday-identity-graph), which covers 1,400+ attributes on 240+ million US adults and their households, plus your own customer data if you add it. Teams can compare any market against their own customers and act on what they find. Ask Faraday is available now in limited release for existing Enterprise customers._

Ask a marketing team why their best customers are their best customers, and the answer you'll usually get will be a hypothesis. Not a bad hypothesis. The behavioral data is all there: clicks, visits, purchases. But none of it tells you who those people actually are. So the questions that shape strategy get answered with intuition or aggregated survey data. Who _actually_ buys from us? What do they _actually_ have in common that our prospects don't? Is the market we're about to enter full of people who _actually_ look like them, or empty?

That's the [context gap](https://faraday.ai/blog/consumer-context-data-ai), and today we're launching something to help close it.

**Ask Faraday** lets you ask questions directly of Faraday's US consumer data, and your own customer data, from Claude, ChatGPT, or another major AI assistant. Ask about the American population in plain language, see how any market compares to your own customers, and turn what you learn into smarter decisions: the right offer, the right timing, and the right products for the right people.

## From analyst project to a question you can type

For years, Faraday's clients have relied on our team to answer questions like who buys from them and where to find more of those people. For instance, one major home services company used Faraday's analysis to identify its strongest markets and doubled down on them. A high-end jewelry brand used it to choose new store locations.

That work drove real value, but it took analyst time and plenty of back-and-forth. Ask Faraday lets anyone on your team do that work themselves. From the AI assistant they already use, they can ask a question, compare the answer to your customers, and act on what they find, without waiting on an analyst.

## How it works

### 1. Ask

Any question about the US population, in plain language, from inside the assistant the team already uses (Claude, ChatGPT, Gemini, etc.). For example:

- What's the household income by county?
- What's the ratio of women to men across the Northeast?
- How many homes in Arkansas were built before 1980?
- How many roofs are there in Maine, and what are they made of?

Answers come from Faraday's identity graph. It covers more than 240 million US adults and their households, with 1,400+ curated attributes.

### 2. Compare

Ask the same question about your own customers. Ask Faraday compares the two and shows which attributes your customers have more or less of than the market. It's the difference between knowing what a market looks like and knowing whether it looks like the customers you already win.

### 3. Act

The assistant that answers your questions also works with the rest of Faraday, so it can help you put findings to use right away:

- If one segment mostly buys on promotion, send those people deals.
- If another only shops around the holidays, reach them then.
- If people with certain traits buy certain products more often, promote those products to people like them.

When you're ready, the same conversation can turn those insights into smarter customer lists and campaigns.

### 4. Integrate

Because Ask Faraday works in your own agent, you can combine it with all of the other MCP tools you depend on. For example, one prompt can pull customer status from HubSpot and run a comparison in Faraday.

## Who it's for

| Who                                | How they use it                                                        |
| :--------------------------------- | :--------------------------------------------------------------------- |
| Marketing teams                    | Run recurring customer and lead analysis without waiting on an analyst |
| Startups                           | Check big decisions against real data instead of instinct              |
| Strategy and corporate development | Size new categories or regions before moving into them                 |

Today, understanding your buyers and sizing a market usually means expensive, slow consumer research, or generic AI answers you can't verify. **Ask Faraday gives teams of any size a way to build strategy on real data about the people they serve.**

## Privacy built into the database, not bolted on

Any tool that answers questions about people carries a risk: narrow a question far enough, and an "average" describes a single household. So Ask Faraday rejects any question that could single out an individual. Every result has to be backed by at least 50 distinct people, and requests for person-level records are refused outright. Google BigQuery enforces that rule at the database level, not through a policy or a prompt, so it holds even against a jailbroken assistant or a bug in our own code.

"Every SaaS company is bolting a chat box onto a pile of data and getting back confident answers nobody can check," said Andy Rossmeissl, CEO and co-founder of Faraday. "We let the assistant write real queries against real data, and we let the database refuse the ones it shouldn't answer."

## Availability

Ask Faraday is launching in limited release for Faraday's existing Enterprise customers. To request access, contact your account team.

### Pricing

Ask Faraday is a $500/month add-on to your Enterprise plan, with unlimited use. To add it, contact your account team. And if you're not yet on Enterprise, you can [talk to our sales team](https://faraday.ai/talk-to-sales).

## Frequently asked questions

### What is Ask Faraday?

Ask Faraday lets you ask plain-language questions about American consumers and get answers from Faraday's data on 240+ million US adults and their households. You can also compare the market against your own customer base.

### Which AI assistants work with Ask Faraday?

Ask Faraday works from inside the assistant your team already uses, including Claude, ChatGPT, and Gemini.

### What kinds of questions can I ask?

You can ask about demographics, households, homes, and markets. Examples include household income by county, how many homes in a state were built before 1980, or how your customers differ from the broader market.

### How does Ask Faraday protect consumer privacy?

Every result must be backed by at least 50 distinct people. The database itself enforces this rule, so a question narrow enough to single out one person is rejected. Requests for individual person-level records are refused outright.

### Who is Ask Faraday for?

It's for marketing teams running customer and lead analysis, startups making early strategy decisions, and strategy and corporate development teams entering new categories or regions.

### How do I get access?

Ask Faraday is in limited release and currently available to existing Enterprise accounts. For access, contact your account team. And if you're not yet on Enterprise, you can [talk to our sales team](https://faraday.ai/talk-to-sales).

Ask Faraday lets teams query Faraday's US consumer data from their AI assistant, so they can size markets, build ICPs, and act on what they find.

Introducing Ask Faraday: Real answers about American consumers, from Claude, ChatGPT, and more

We've added five new data points to the [Faraday Identity Graph](/blog/whats-in-faraday-identity-graph): the names of up to two owners on a property's title and up to three lenders on its mortgage. They sit alongside the mortgage data we already had, including rate, [origination date](https://faraday.ai/catalog/v2/mortgage_1_origination_year_month), [loan amount](https://faraday.ai/catalog/v2/mortgage_1_amount), and how likely the household is to refinance.

## What's new

| Data point                                                                              | What it tells you                          |
| --------------------------------------------------------------------------------------- | ------------------------------------------ |
| [Mortgage lender 1 name](https://faraday.ai/catalog/v2/property_mortgage_lender_1_name) | The lender on the home's mortgage          |
| [Mortgage lender 2 name](https://faraday.ai/catalog/v2/property_mortgage_lender_2_name) | A second lender on record for the property |
| [Mortgage lender 3 name](https://faraday.ai/catalog/v2/property_mortgage_lender_3_name) | A third lender on record for the property  |
| [Property owner 1 name](https://faraday.ai/catalog/v2/property_owner_1_name)            | The first person on the property's title   |
| [Property owner 2 name](https://faraday.ai/catalog/v2/property_owner_2_name)            | A second person on the property's title    |

## Who it's for

**Mortgage lenders and the platforms that serve them.** You can now see whose borrower a homeowner is, not just whether they're a good refinance candidate. Go after a competitor's borrowers who are paying above today's rates, keep your own customers out of acquisition campaigns, and flag homes with more than one lender on record for home equity or consolidation offers.

**Anyone whose offer depends on homeownership.** Owner names let you confirm you're reaching the person on title, not just whoever lives at the address.

## Try it on your own list

Upload a list of homeowners or addresses to [Faraday Pro](https://pro.faraday.ai) and get these fields back for each record. Signing up takes a few minutes and there's no call to book.

If you want to go further, like scoring a list for refinance likelihood or building an audience around a specific lender's borrowers, [our team can set that up for you](/talk-to-sales).

Five new data points in the Faraday Identity Graph show who's on a property's title and who holds its mortgage, so lenders can see whose borrower a homeowner is and anyone can confirm they're reaching the owner.

See who holds the mortgage: new lender and owner data in Faraday

Every team that comes to Faraday wants the same thing: [context](/blog/consumer-context-data-ai) on the people behind their customer records. Who they are, what their household looks like, what they're likely to do next. How teams want to get there varies a lot. Some know exactly which data points they need and want them today. Others have a business problem and want help figuring out what data would solve it.

That's why Faraday has two products, [Faraday Pro](/signup) and [Faraday Enterprise](/talk-to-sales). They're two ways into the same platform, built on the same [Faraday Identity Graph](/blog/whats-in-faraday-identity-graph), with the same [1,400+ data points](/catalog) on 240 million U.S. consumers and their households. Neither is the beginner version of the other. The real difference is where the thinking happens: whether you bring the judgment yourself, or want Faraday working through it with you.

## What's the same

Whichever product you use, you get the same underlying data, the same identity resolution, and the same bar for [security and data protection](/security). Pro isn't a "lite" tier with a trimmed-down dataset. What changes is the way in, not what's behind it.

## Faraday Pro: the data and the tools, self-serve

Faraday Pro is for teams that know what they need and want to get it now. You sign up at [pro.faraday.ai](https://pro.faraday.ai), create a project, and pick the data points you want. If you're not sure what a field is called, you can describe what you're looking for, and the suggested attribute search surfaces the right attributes.

Then you bring your records whichever way fits. You can upload a CSV and get it back with your attributes appended, look up a person in real time through the [API](/docs/pro/projects#real-time-lookup-by-api), or connect Pro to your data warehouse, database, or cloud bucket for ongoing [enrichment](/blog/get-started-with-consumer-data-enrichment). Pro also works through our [MCP server](/docs/pro/projects#real-time-lookup-by-mcp), so it's addressable from agentic workflows.

Pricing is pay-as-you-go. You're billed per matched attribute, so you pay for the data we find, not the rows you submit. Credits are \$0.05 each, with volume discounts available. No contracts, no minimums, and no sales call required.

**Pro is a good fit if:**

- You know what data points you are looking to append to a list of customers or leads.
- You'd rather pick attributes and hit an API than sit through a procurement process.
- You have a team that can put the data to work once you have it.

## Faraday Enterprise: the data plus the expertise

Faraday Enterprise is a managed account. You get the same platform, plus a dedicated context consultant who learns your business and helps you turn consumer data into revenue. That includes activation guidance, modeling strategy, and ongoing expert support.

Enterprise is also built for more complex use cases, like models and audiences built from your full event history, such as purchases, signups, and churn over time. It also supports sub-accounts, so agencies, partners, and companies with several brands can run a separate, isolated Faraday account for each client or brand, all managed from one parent account. It's an annual engagement, it's sales-led, and it lives at [app.faraday.ai](https://app.faraday.ai).

**Enterprise is a good fit if:**

- You have a business problem, like [churn](/blog/churn-prevention-machine-learning), [lead quality](/blog/predictive-lead-scoring-b2c), or [finance declines](/blog/finance-decline-guide), and want help deciding what data and models will solve it.
- You want predictions built from your full event history, not just a customer list.
- You manage data for several clients, brands, or business units and need each one kept separate.
- You want a partner, not just a data source.

### Starting with an Insights Report

If you don't know which Pro data points will drive the most value for your brand, but Enterprise sounds like too big a commitment, you can always start with an Insights Report. It's our way of helping you understand your best customers, your total addressable market, and which data might give you the most leverage to win more customers.

Every business is different, so every report is scoped to you. We start with the two or three questions that matter most to you. Common ones are "Who are our current customer segments?" and "What's our penetration by market?" Then we build the report from Faraday's data.

From there, teams typically move into an Enterprise plan to put what they learned to work. Others find the report shows them exactly which data points they need, and they go straight to Pro.

## How to decide

The simplest way to think about it: do you want the data, or the data plus the expertise? If you have a straightforward data need and know what you're going to do with it, start with Pro. If you want more guidance, aren't sure where to start, or have a more complex problem to solve, Enterprise might be the better fit, and an Insights Report is an easy first step. Here's a breakdown by use case:

| If you want to...                                                                               | Faraday Pro | Faraday Enterprise |
| :---------------------------------------------------------------------------------------------- | :---------: | :----------------: |
| Add demographics, financial signals, life stage, or homeownership to a customer or lead list    |      ✓      |         ✓          |
| Look up a person in real time from an app, form, or AI agent                                    |      ✓      |         ✓          |
| Keep records enriched through a connection to your warehouse, database, or cloud bucket         |      ✓      |         ✓          |
| Build a propensity or persona model from a list of your best customers                          |      ✓      |         ✓          |
| Test the data on a few rows before committing                                                   |      ✓      |         ✗          |
| Pay as you go with a credit card, no contract                                                   |      ✓      |         ✗          |
| Build models and audiences from your full event history, like purchases, signups, and churn     |      ✗      |         ✓          |
| Run a separate account for each client, brand, or business unit under one parent account        |      ✗      |         ✓          |
| Work with a dedicated context consultant on which data and models will solve a business problem |      ✗      |         ✓          |
| Understand your customer segments or penetration by market with an Insights Report              |      ✗      |         ✓          |

If most of your answers land in the Pro column, you can [start today](/signup) and be enriching records in minutes. If they land in the Enterprise column, [talk to us](/talk-to-sales). And if you're an Enterprise client curious about Pro, your account team can help you find the right setup.

## Two ways to act on the same context

We talk a lot at Faraday about what AI tools are actually for. The best ones don't replace human judgment. They help people act on it. Data or a model can tell you which customers are likely to churn, but someone still has to decide what to offer them, when, and whether it's worth the cost. The value comes from the decision, and the data's job is to make that decision better.

That's the real difference between Pro and Enterprise. It isn't about which one is more powerful, since the data underneath is the same. It's about where the thinking happens.

With Pro, you bring the judgment. You already know the question, like "which of these leads can afford a \$20,000 remodel?" You need the context to answer it, and Pro gets out of your way so you can act.

With Enterprise, Faraday brings the data and works alongside you on what to do with it. Maybe you know finance declines are eating into revenue, but not which signals predict them or what to do about it. A context consultant works through that with you: defining the problem, choosing the data, building the model, and helping you [measure whether it worked](/blog/holdout-testing-with-faraday).

Either way, the goal is the same. It's people making a better call with better context. Pro and Enterprise are two ways to get there, depending on how much of the path you've already mapped out.

## Get started

[Create a free account on Faraday Pro](/signup) and start with the data you need, or [talk to a context consultant](/talk-to-sales) about Enterprise (or an Insights Report).

## FAQ

### Is the data in Pro the same as in Enterprise?

Yes. Both run on the Faraday Identity Graph, and the data is identical. The difference is the delivery model: self-serve and pay-per-match, or a managed annual engagement.

### Can I get predictions on Faraday Pro?

Yes. In Pro, you can build [propensity](/blog/propensity-models-predict-customer-behavior) and [persona](/blog/what-are-ai-customer-personas) models by uploading a list of the customers you want to predict more of. Enterprise builds models from your full event history, like purchases, signups, and churn over time, with a context consultant helping you decide what to predict and how to act on it.

### Can I switch from one to the other?

Yes. Plenty of Pro customers will never need Enterprise, but if your needs change, we can help you move. Enterprise clients can also talk to their account team about adding Pro.

### Is Pro only for small teams?

No. Pro is about how you want to work, not how big you are. Some large teams know exactly what they need and just want access to the data.

### What if I'm interested in Enterprise but not ready to commit to an annual engagement?

Start with an Insights Report. We'll scope your top two or three questions with you and build the report from Faraday's data. Teams typically move into an Enterprise plan from there, and some find the report tells them exactly which data points to pull in Pro.

Faraday Pro and Faraday Enterprise run on the same data. The difference is how you want to work with it. Here's how to choose.

Faraday Pro vs Faraday Enterprise: which one is right for you?

We all know that effective marketing requires personalization. Faraday enriches leads with contextual data so you can personalize every interaction and drive conversion.

Years ago, one of our earliest clients wanted to confirm this premise for themselves. Instead of sending one generic email to their entire list, they created unique, hyper-tailored content variants specifically crafted for the distinct vocabularies and motivations of their unique Faraday Personas. The results were undeniable: a 30% lift in conversion.

Yet, despite the clear upside, they didn't stick with the new system very long. Why? Because in order to actually use Personas to personalize, you have to understand what makes each Persona special and then produce personalized materials unique to their needs and interests. Doing both of these things manually is incredibly hard and tedious.

This is the paradox of personalization: the more you tailor your messaging, the better your results — but the more manual work you have to do. Our clients want ROI through a lift in engagement, leading to better LTV and/or CAC, but the friction of execution often gets in the way.

The [Faraday MCP server](https://faraday.ai/docs/features/mcp) closes that gap.

All you have to do is connect your agent once, and it can read your Persona sets, cohorts, and models directly from your account — then write the copy, build the audience, and ship it to your destination. The analysis and the execution happen in the same conversation, in the agent you already use.

## Before you start

Connecting takes about a minute. In Claude, ChatGPT, Cursor, or any other MCP-compatible client, add the server at `mcp.faraday.ai/mcp` and sign in with your existing Faraday login. Authorization runs through OAuth, so your agent never handles an API key. Ask it to run `whoami` and it will confirm the account it's working in and list every tool it has.

Ready? Here is your tactical playbook.

## Campaign matchmaking

Sometimes you know exactly what you want to sell, but you aren't sure who wants to buy it. When you're running a promotion for a specific product line, a new category, or a holiday sale, you need to know which group of customers will actually care.

Instead of relying on a hunch, ask your agent to interpret the Persona data for you. It queries the live distributions in your account and matches your product's value proposition against the group that mathematically shows the highest affinity for it.

> "Pull up the Persona set on my customer cohort and summarize each Persona's salient traits. We're launching a premium product line in November at a \$2,000+ price point. Which Persona is most receptive, and what in the data tells you that?"

## Offer brainstorming

On the flip side, you might have a segment that's underperforming. Maybe a Persona is smaller than you want it to be, or your recent campaigns just haven't pushed their buttons.

Your agent can cross-reference that Persona's traits against the rest of your base and suggest offers built on what actually motivates them, rather than what you'd guess motivates them.

> "Persona 3 converts at half the rate of the others. Compare their trait distributions against my highest-converting Persona and tell me what's different. Then propose three promotional offers tailored to what you found, and explain the reasoning behind each."

## Producing personalized materials at scale

Writing one great email is hard. Writing four distinct variations of that same email is agonizing. Usually the friction outweighs the lift.

Once your targeting is decided, hand your agent your baseline materials and let it adapt them per Persona — subject lines, email and SMS copy, landing page variants — with the trait data already in front of it.

> "Here are our brand guidelines and the baseline email for the November launch. Write one variant per Persona in my customer Persona set. For each, give me a subject line, preview text, and body copy, and note which trait drove the angle you chose."

## Running synthetic panels

Brands have run focus groups forever to test messaging, but hiring an agency to build a representative panel is expensive and slow. Your agent can build one from your real Persona distributions instead.

> "Create a synthetic panel of 10 panelists, proportionately allocated across the Personas in my customer Persona set and consistent with each Persona's actual trait distributions. Invent a name, demographic details, and backstory for each. Then let me interview them individually or as a group."

Because the allocation comes from your account rather than the model's assumptions, the panel reflects your customer base and not a generic one.

## Sales training and roleplay

Marketing isn't the only team that benefits from understanding Personas. New reps — and veteran reps with ingrained biases — need to pivot their pitch based on who's across the table.

> "I'm a new sales rep for \[your brand\] — look us up so you know what we do. Pick one of the Personas in my customer Persona set and invent a representative customer who belongs to it, with a name, demographic details, and backstory grounded in that Persona's traits. Act as that person so I can ask about your perspective, your motivations, and what would stop you from buying."

## Closing the loop

Here's what changes when the analysis happens against your live account: the agent doesn't have to hand the work back to you at the end.

Once you've picked the Persona and written the copy, the same conversation can build the audience and deploy it — then come back in a month and tell you whether it worked.

> "Build a target of everyone in Persona 2 with a churn score above the 80th percentile, and deploy it to our Meta connection."

> "It's been 30 days since we activated the November audience. Pull the current numbers and tell me how the Persona 2 segment performed against the rest of the campaign."

## Bridge the gap between insight and action

There isn't one perfect analysis that illuminates every way to use your Personas. The value of your customer data shows up when it starts driving your daily decisions and your content.

Running that work through the MCP server removes the friction of personalization at both ends: the understanding and the execution. You no longer have to choose between a hyper-targeted campaign and your own productivity.

Already on Faraday? Connect your agent at `mcp.faraday.ai/mcp` and open a Persona set. Full details are in [the MCP docs](https://faraday.ai/docs/features/mcp).

New to Faraday? [Talk to a Context Consultant](https://faraday.ai/contact) to get some Personas set up.

A tactical playbook of prompts for using Faraday's MCP server to match campaigns to Personas, generate targeted copy, run synthetic focus groups, and roleplay sales scenarios — grounded in your live account data.

Turn your Personas into a marketing engine with the Faraday MCP server

Direct mail is about as old school as marketing gets, and in a world of AI slop, that's exactly what makes it stand out. Where web ads are relatively cheap, flexible, and easily cancelled or updated if something goes wrong, mail is expensive, takes weeks to produce, and worst of all, a bad decision can't be undone.

These aspects of direct mail get filed away as the channel's weaknesses, and often become reasons to test it later, or not at all. But that expense has a side effect worth paying attention to: it forces intentionality. Because it costs more, we treat it differently; we’re less likely to thoughtlessly hand it off to AI. And I think that teaches us something about how we're engaging with all our LLM tools right now: we're not just handing off our thinking, we're handing off our intention, and too often we stop caring about what actually goes out the door.

## Why direct mail's cost forces better targeting

_When sending costs nearly nothing, there's no reason to think hard before you launch._

We'd never say it out loud, but let's be honest, this thinking has crept into a lot of outreach over the last few months. It's the same spray-and-pray we all know and roll our eyes at, but now on steroids thanks to AI. And for digital it _almost_ seems justifiable: if an email campaign misses, the financial penalty is relatively negligible, so the rational move is volume. Fire everything and see what sticks, right?

Mail won't let you do that. When each piece costs real money to send — orders of magnitude more than a digital impression — you feel actual pressure to answer the basic questions: who you're sending to, whether the list is right, what you're actually saying, whether the timing makes sense. You know, the questions we all know we're supposed to answer before we write a single word of copy. The economics aren't limitations, they're a forcing function to do better work, and it's why mail campaigns tend to be thought through in a way that email campaigns often aren't.

## What this looked like for us

Last month we launched a [self-serve portal](http://pro.faraday.ai) where you can directly pull consumer data from the [Faraday Identity Graph (FIG)](https://faraday.ai/blog/whats-in-faraday-identity-graph), and we wanted to announce it with a postcard, something we hadn't tried before. What I didn't expect was how different the creative process would be from our standard digital ad rollouts.

Our first version was built mostly with AI (let's be honest, who isn't doing that today). AI helped pick who we'd send it to, wrote most of the copy, and drafted the design. We had the whole thing mocked up in a day. If this had been an email, I'd probably have glanced at it for two minutes, and, noting that the cost to send would be negligible, said "sure, let's try it." But something at the back of my head kept reminding me that every one of these postcards was going to cost us real money, so I actually looked closer.

![The original AI-assisted Faraday postcard: the Faraday logo with the tagline "we have data for that" and faraday.ai on a pink background](/images/blog/why-direct-mail-cost-prevents-ai-slop/original-postcard.png)

This is the original, it wasn't bad. It met every requirement I’d given. But it was generic and frankly it wasn't something I'd respond to myself. We'd made _something_, _fast_. But with a little more intention, we could make _something_ _great_. So we went back to the drawing board on all of it: the list, the message, and even what we wanted the piece to feel like. And when we weren’t sure what the best path was, we didn’t hand it off to Claude, we went to the actual experts in our corner, our fantastic direct mail provider Lob, who walked us through the details that convert a campaign from acceptable to exceptional (like knowing that 6x9 postcards tend to get a better response than 4x6, who knew\!?).

![The final Faraday postcard: a "greetings from Vermont" banner over a photo of a red covered bridge surrounded by green hills](/images/blog/why-direct-mail-cost-prevents-ai-slop/vermont-postcard.jpg)

Round 2 landed on something highly personal and friendly: a casual, direct note from our Head of Sales paired with a classic VT postcard aesthetic (covered bridge and all). It was designed to feel like what makes postcards fun in the first place: a warm note from someone who was thinking of you. In this case, your old friend Dave (who happened to have an easy yes to save you some money).

![Happy customer posing with their recently recieved Faraday postcard](/images/blog/why-direct-mail-cost-prevents-ai-slop/happy-customer.jpg)

(That’s one happy customer)

## What the research actually shows

But it’s not just that we marketers get a warm, fuzzy feeling when we send a nice, intentional direct mail. The data shows this actually impacts the bottom line.

I was on [a panel with Lob, the USPS and SimpliSafe](https://www.lob.com/videos/state-of-direct-mail-2026-consumer-insights) earlier this month, digging into their [2026 State of Direct Mail research](https://www.lob.com/state-of-direct-mail/consumer-insights/2026-report), and the numbers make the case better than I can. [Nine in ten people](https://www.lob.com/state-of-direct-mail/consumer-insights/2026-report#personalization-and-conversion) say relevant, personalized mail is what moves them to act. [Two-thirds](https://www.lob.com/state-of-direct-mail/consumer-insights/2026-report#ai) now say AI has made them more skeptical of digital ads, while most are comfortable with AI in their mail — as long as it's making things more relevant rather than just making more of them. And [the households under the most financial pressure](https://www.lob.com/state-of-direct-mail/consumer-insights/2026-report#economic-pressure), the ones you'd assume have tuned marketing out entirely, are the most likely to act on mail and the most willing to try a brand they've never bought from who connected with them through direct mail.

People aren't reacting to the technology. They're reacting to whether anyone was paying attention.

## The trap is avoidable

Look at how we're all working right now. How often do you find yourself just conversing with Claude, passing prompts back and forth only to realize you could have written it yourself in 20 minutes? We've got more tools than we have problems to solve.

It's not a new take that we're outsourcing our thinking to AI — but I'd argue it's not just our thinking we're giving up. It's our intention.

For years marketers have been optimizing for attention — impressions, clicks, time on page, all the ways we measure how much of someone's day we managed to capture — but today we need to reorient. Suddenly, as we're all managing teams of autonomous (and somewhat competent) agents, we don't just need to optimize for the attention of the lead, but for our own intention. **When we're able to run 100 campaigns at once, the most important item to budget becomes focus.** This is what I call the intention economy, and it's just as critical to understand as the attention economy.

And this is where mail is instructive, because it's a channel where the option to stop paying attention never felt like an option at all. You can generate a hundred versions of a mailer in a minute; you still have to pay to put each one in a mailbox. **The bill arrives whether an AI wrote the copy or you did, but the leads might not.**

## Where that leaves the rest of your marketing

The useful thing about a constraint is that you can adopt it on purpose. Sure, postage might be the specific thing that makes you ask the right questions on your direct mail campaign — but those questions don't become less true in channels where nobody's forcing you to think about them. **You don't need a stamp to stop spraying and praying; you just need to hold your digital channels to the exact same standard.**

We need to take the reins of our campaigns and stop letting the tools, or some false sense of “efficiency” dictate our standards. The tools can scale our output, but the intention still has to come from us.

Why direct mail resists AI slop: its cost forces marketers to think before they send. I explain the intention economy and how to apply it to every channel.

The intention economy: The cost of direct mail is what saves it from AI slop

When you've built predictive audiences in Faraday, the next step is getting them into your marketing channels. For many of our clients, that's Meta (Facebook and Instagram).

Doing it by hand means exporting a CSV, hashing the personal information to meet Meta's privacy requirements, and uploading the file to Meta Business Manager, then doing it all again every time the audience changes. It's slow, it's easy to get wrong, and the audiences in Meta go stale between uploads.

Faraday's managed Meta connection removes those steps. We handle the hashing and delivery and push your audiences directly into your ad account, so they stay current without anyone touching a file.

## How it works: step-by-step setup

Setup takes three steps on your side:

1. **Share your Meta ad account ID.** Add it when you create a Facebook connection in Faraday, or send it to your Faraday contact and we'll create the connection for you. If an agency runs your campaigns, use the ad account the campaigns run in.
2. **Accept Faraday's access request.** We'll send a request through Meta to access your ad account. Once you accept it, we can push audiences to it directly.
3. **Deploy your audiences.** Create a pipeline in Faraday that deploys to your Facebook connection, and let us know once you have. We'll push it to your ad account and let you know when it's ready to use in your campaigns.

You only set up the connection once. After that, every audience you deploy to it syncs the same way.

## We're here to help

If you have questions or run into trouble, reach out to support and we'll help.

Faraday's managed Meta connection sends your predictive audiences straight to your Meta ad account, so you can skip the manual exports and uploads.

Streamlining Meta custom audiences with Faraday managed connections

## The problem

Finance declines don't fail at the top of the funnel. They fail at the end — after a rep has driven out, run a full appointment, and gotten a homeowner to sign. Then the financing falls through, and the cost of that lead, that drive, that appointment, and that rep's time is gone.

Across Faraday's home services client base, finance decline rates typically range from 20% to 45% of gross sales, and with household budgets under more pressure than they've been in years, that number is trending in the wrong direction. There's also a well-known dynamic that makes it worse: the homeowners most eager to book are often the ones least likely to clear financing, while the ones most likely to qualify are harder to reach and slower to commit.

The good news is that [finance declines are predictable](https://faraday.ai/catalog/v2/credit_score_proxy) — and once they're predictable, they're manageable. Below are the five plays Faraday clients use to attack the problem, followed by a real implementation example.

## Five ways to use a finance decline score

Faraday delivers a real-time score for every lead, predicting how likely they are to result in a finance decline. The right way to use that score depends on your lead volume, cost structure, and workflow. Most clients start with one play and layer on others over time.

### 1\. Suppress high-risk leads before the appointment stage

Stop spending rep time on leads that are almost certain to decline. Set a percentile threshold — most clients start conservatively — and route leads above it into a hold bucket rather than hard-rejecting them. This protects vendor relationships and creates a reserve pool for slow periods while immediately freeing up appointment capacity.

This is the highest-impact play for clients with enough lead volume to absorb a small reduction. At a 95th-percentile cutoff, clients typically project less than 2% revenue impact while eliminating over 10% of total credit declines — a projection the implementation below came in under.

### 2\. Prioritize appointments by likelihood to close

For clients who don't want to or can't reduce lead volume — contractual obligations, market coverage requirements — the score ranks which appointments get worked first. Surface the score in the CRM or call center tool so managers and reps see it where they're already making decisions.

One remodeler we work with built a 5-point decision matrix combining their finance decline score with credit pass percentile, home value, household income, and credit score proxy. The result: roughly **$25,000 a month** in lead-spend savings from better appointment selection alone — more than **12x** the annual cost of their plan with Faraday.

### 3\. Pre-qualify leads in the call center

Use the score to guide agent behavior before a rep ever drives out. High-risk leads get asked about financing intent earlier in the call, or get rough price estimates that naturally filter out homeowners who can't afford the project. Very high-risk leads can be routed to AI-powered call center agents or text agents at a fraction of the cost of a human rep — handling the conversations least likely to convert without burning capacity (and sales team morale).

### 4\. Manage lead sources in real time

Scores can be tracked for every vendor the moment leads come in, so a sudden drop in source quality shows up immediately — not weeks later when end-of-funnel data finally catches up. This makes it possible to react before a bad batch eats your budget, and gives you leverage to renegotiate from cost-per-lead to cost-per-install for chronically low-quality sources.

## How to get started: a phased approach

You don't have to go all-in on day one. The clients who've been most successful with this follow a phased rollout:

### 1: Observe

Connect the [API](https://faraday.ai/docs/features/lookup-api), score all incoming leads, but take no action. Monitor the correlation between scores and actual outcomes. This typically takes 1–2 weeks and builds internal confidence in the model before anyone changes their workflow.

### 2: Suppress conservatively

Begin suppressing or deprioritizing the top 5% of scores. Monitor impact on revenue and decline rates.

### 3: Measure

Before widening the net, confirm the suppression is doing what you expect. Over a defined window — 30 days is a good starting point — compare decline rates and revenue for suppressed versus worked leads, and watch your false-positive rate so you're not holding back leads that would have closed. This is the evidence that justifies expanding — both internally and for your own confidence.

### 4: Expand

Gradually lower the cutoff threshold based on observed performance and your tolerance for revenue trade-off.

### 5: Layer on prioritization

Add a second signal for intent or conversion likelihood to guide how remaining leads get worked — not just which ones get cut.

### 6: Full decisioning

Build a multi-signal decision matrix combining decline score, intent score, home value, income proxy, and geography for complete lead-level routing.

## In practice: attacking a 35+% decline rate

That's the approach in the abstract — here's how it's playing out for one regional bathroom remodeler living with the problem.

This company, which operates across 10+ states was watching roughly 35% of its gross sales fall through at the financing stage — with some of its markets running as high as 45%. To protect revenue targets, the company overbooks appointments and manually selects which to run each day, a labor-intensive workflow with real waste built in.

The company trained a custom finance decline model with Faraday using its own Salesforce disposition data, and Faraday stood up a real-time [Lookup API](https://faraday.ai/docs/features/lookup-api) pipeline within days. Validation was strong: in the top decile of risk, 82% of gross sales actually declined. In the top 1%, 98.7% did.

With that confidence, the team put the score to work two ways. First, **suppression**: the highest-risk leads are written to Salesforce but held in a separate bucket and never passed to the dialer, so reps don't burn time on the leads most likely to decline. Second, **prioritization**: because the company overbooks, the score also ranks the leads that remain — surfaced right on the appointment Gantt chart as a hover-over via [LeadConduit](https://activeprospect.com/leadconduit/), so when managers choose which of an overbooked day's appointments to actually run, they work the ones least likely to decline first.

Although they started conservatively — suppressing only the leads nearly guaranteed to fail a credit check (greater than 85% chance of failure), the results came quickly.

### Update: three months in

After our first quarter review, the company's finance decline rate came in at roughly 29% of gross sales — under the 30% mark their leadership had set as the goal and significantly down from the 35%+ they were living with when they started. And they got there without giving up the revenue: cutting six points off their decline rate only cost them 1.4% of net sales — below the 2% we'd accounted for.

## Two paths in, depending on your data

Faraday offers two products for this use case:

[**Credit Score Proxy**](https://faraday.ai/catalog/v2/credit_score_proxy) — a 1–12 ranking derived from licensed bureau data, available immediately with no training data required. In testing, leads in the bottom scoring tiers showed 71–73% decline rates. Good starting point when you don't have historical disposition data.

**Custom finance decline model** — built on your own historical credit check and decline data. Consistently outperforms the off-the-shelf proxy by a meaningful margin. This is the path the remodeler above took.

Which path is right depends on your data. If you have 6–12 months of credit check and decline disposition data, a custom model is almost always the better choice. If you don't have that data yet, the proxy gets you moving immediately while you build up the historical record.

## If you're a lead generator

The same score works from the other side of the transaction. If you sell leads to home services companies, finance decline risk is a quality problem you can now measure before a lead ever leaves your hands — and that opens up two moves.

Downstream, you can grade the inventory you already have. Score inbound leads in real time to suppress or downgrade the ones most likely to decline, route your strongest leads to the buyers who value them most, and package pre-scored, higher-qualified leads as a premium tier. In a market where remodelers increasingly judge lead quality by financing outcome, being able to grade your own inventory — and prove it — is a real differentiator.

Upstream is where it gets more powerful. Feed decline outcomes back into your ad platforms — Google, and potentially Meta — as a conversion signal, and the platforms start optimizing toward the people more likely to clear financing in the first place. Instead of paying to generate bad leads and filtering them after the fact, you generate fewer of them to begin with — a cleaner book you can sell for more.

## If finance declines are eating your margin

This is solvable — and the solution doesn't require a homeowner consent flow, a bureau pull, or a six-month integration project. The data lives in your CRM already. Faraday turns it into a real-time score that plugs into the lead routing and CRM tools you're already using.

If you want a number before you talk to anyone, we built a free calculator for exactly this. Enter your bath, roofing, window, or HVAC funnel and it will estimate what declines are costing you each month, what a decline score would change, and how your ZIP codes compare on HMDA data. It takes a couple of minutes and you get a report you can bring to your team: [run your numbers](https://reports.faraday.ai/finance-declines).

And if you'd rather just walk through it with someone who has done this before, our [context consultants](https://faraday.ai/contact) are always ready to talk.

Finance declines are one of the most expensive problems in home services — and in the current economic climate, they're getting worse. Here's how Faraday clients are using predictive scores to cut the waste before it hits the bottom line.

How to solve a 35+% finance decline rate with predictive data

Next Tuesday I'm appearing on our partner [Lob's](https://www.lob.com) [State of Direct Mail](https://www.lob.com/state-of-direct-mail) panel with USPS and SimpliSafe. Lob surveyed 2,000 consumers for their annual report, which we'll be discussing, and one finding has stuck with me: when it comes to direct mail, relevance is beating discounts.

And when we think about relevance in DM, I'm sure most of us go straight to creative and personalization — which makes sense, creative is what we see when we get the postcard.

But here's the thing about relevance in mail. It starts long before anyone writes the copy or sends a file to the printer. By those points you've already made many of the decisions that determine how well the campaign actually does: whether these are the right people, whether you're pointing them at the right location, whether the person they live with already got the same mailer last month and converted.

Sure, bad creative can kill your conversion rate. But a great offer addressed to some stranger named Sandra who moved out two years ago doesn't help either.

Creating the list is where we've been putting our attention at Faraday. Here are four things we shipped this quarter to help you get yours right, plus some strategic recommendations at the end.

## New mover data: target the right people at the right time

Most names on most mail lists have no particular reason to act this week. They aren't bad prospects. They're just being contacted at an arbitrary moment.

A recent move is the opposite of arbitrary. Someone who just moved is replacing providers, buying for a new space, and setting habits they'll keep for years. It's one of the few times a piece of mail arrives already relevant.

**New mover data** lets you build audiences around that window — people who have recently moved into your service area, combined with whatever else you already filter on.

It cuts the other way too, and this is the part that gets skipped. The households that _used_ to live in your area are still on your list. Every piece addressed to them is postage spent on someone who has moved on. So the same signal does two jobs: it adds the people whose timing is right, and it surfaces the ones who quietly stopped being reachable.

[See how many people are moving into or out of your service area](https://reports.faraday.ai/new-movers) with our new mover tool. And if you want this data on your next drop, your account team can get you set up.

## Nearest Location: put the right store on every row

If you have physical locations, something has to decide which one each piece points to. For most teams that's a ZIP code or a regional map, which means a household three blocks from one store might get mailed about another one across town.

That proxy also distorts what you'll pay for a lead. Distance is a real constraint on conversion for anything that requires showing up — glasses get tried on, flooring gets seen. A lead 40 miles from your nearest showroom is worth less than one at four miles, and if you can't tell them apart you're paying the same for both.

[Nearest Location](https://faraday.ai/blog/nearest-location) measures the actual distance from every person to every location you have, and returns their nearest location, your own ID for it, and the distance. It's a real number rather than yes/no flags at thresholds someone set in advance, so "within 12 miles" is a filter you apply, not a rebuild you request. It runs backwards too: draw a radius around your locations from an [Atlas](https://faraday.ai/docs/abstractions/atlases) and build an audience of every household inside it. [There's a full walkthrough in the docs](https://faraday.ai/docs/abstractions/atlases#how-to-attach-nearest-location-to-a-deployment).

Every row on your list ends up carrying the store that's actually closest, and you can build the list itself by real distance instead of by map.

## Address-level exclusion: don't send the same offer to two people in one house

Suppression has always worked at the individual level. You mailed Jane Smith, so Jane Smith comes off the next drop. That might be the right logic for email, but it's insufficient logic for mail.

Mail arrives at addresses, not directly to the individual. So the household you already converted, already hit twice, or already heard "please stop" from can come back in the next campaign under a different resident's name.

To solve this problem, Pipelines now have an [Exclude at address level](https://faraday.ai/docs/abstractions/pipelines#population-exclusion) control. Add a cohort and Faraday suppresses everyone who shares an address with anyone in it. The old option is unchanged and now labeled [Exclude at individual level](https://faraday.ai/docs/abstractions/pipelines#population-exclusion), so you pick which one a campaign needs — both sit under the suppression settings in your [pipeline's population](https://faraday.ai/docs/abstractions/pipelines) settings, and there's an API field for it if you build programmatically.

## Household analysis: find out how many households are on your list

Here's a number that only matters in direct mail: how many _households_ are in your audience.

In most channels you set a threshold and let the volume land where it lands. In mail you buy a quantity — you tell the printer 40,000 pieces. And 50,000 individuals is not 50,000 pieces. It might be 31,000 households, and that's the difference between two very different quotes.

Every [Pipeline](https://faraday.ai/docs/abstractions/pipelines) now has an Analysis tab that answers this before you build a deployment, with no usage required. You get your population counted both ways, individuals and residences, broken out by state and ZIP code — which is also what postal sortation and regional drop planning run on. And for every prediction in the payload, you can see how many people fall into each score range, with running totals as you go further down — so your list length comes from where the counts actually add up, not from a round number somebody picked.

## Where I'd start

Four things at once is a lot. If I were picking up one of them first, this is the order I'd go in.

**1. Focus on households, not individuals.** Use Faraday to ensure you de-dupe your list and send only one mailer per household. Get the household count before you get your next print quote. _If you are already using Faraday, these two steps take less than 5 minutes._

**2. Identify the nearest location to send them to.** Direct mail can feel more personalized if you add subtle, intentional touches like details about the closest store. _This step requires adding your locations to Faraday, but it's worth it to drive a little more personalized experience._

**3. Use new mover data.** You can check out how many people are moving in (or out) of your service areas with [our handy tool](https://reports.faraday.ai/new-movers). Knowing who just moved in lets you time your drop — and your offer — to the moment they're actually shopping. _For existing Faraday customers, there is an additional cost for this data set._

It's ironic: the list is the part you have the most control over, and it's usually the part that gets the least attention. These four features are designed to make it faster and easier to build a sharp audience — so your time goes to the creative and the offer.

## Ready to optimize your list?

If you want to talk through where your direct mail program is leaking, [talk to a Context Consultant](https://faraday.ai/contact). Already a Faraday customer? Your account team can turn any of these on.

And if you'd like to hear the rest of Lob's findings, [join us on the panel next Tuesday](https://www.lob.com/event/2026-state-of-direct-mail-consumer-insights?utm_source=faraday&utm_medium=email&utm_campaign=2026-09-sodmci-webinar).

Relevance in direct mail starts with the list, not the creative. Faraday's COO on four features that add the right households and remove the wrong ones.

Relevance in direct mail starts with the list: four ways to improve yours

## Background

Anthropic published a [blueprint for commerce agents](https://claude.com/blog/claude-for-commerce-agents) on September 2: an [open-source repo](https://github.com/anthropics/commerce-agents) with two working AI agents for online stores, plus a Claude Code plugin that adapts either one to your store's systems. Retailers running shopping agents on Claude report carts up to 35% larger and shoppers 60% more likely to buy.

The shopping agent talks to customers. Tell it "a tent, sleeping bag, and stove for a weekend with two kids" and it searches the catalog, picks a set, and fills the cart. The merchant agent talks to the store's staff. Ask it "what should we discount to clear last season's inventory" and it drafts the promotion for a person to approve. The hard parts of building an agent, like keeping prices accurate and stopping it from pushing products nobody asked for, come built in. Your job is to write one class per agent, [`StorefrontBackend`](https://github.com/anthropics/commerce-agents/blob/fd4d592/shopping-agent/core/shopping_agent/backend.py) or [`MerchantBackend`](https://github.com/anthropics/commerce-agents/blob/fd4d592/merchant-agent/core/merchant_agent/backend.py), that connects the agent to your store's data.

## Problem

**The blueprint assumes you already know your customers.** Every good pick in the demo comes from a customer profile that Anthropic [typed in by hand](https://github.com/anthropics/commerce-agents/blob/fd4d592/examples/retail/data/users.json).

Before each reply, the shopping agent calls [`get_preferences`](https://github.com/anthropics/commerce-agents/blob/fd4d592/shopping-agent/core/shopping_agent/backend.py#L116-L118) and puts what comes back in front of the model: the customer's name, loyalty tier, location, and [a list of free-text preferences](https://github.com/anthropics/commerce-agents/blob/fd4d592/shopping-agent/core/shopping_agent/types.py#L110-L117). The demo's profiles say things like `"household": "partner and a 6-year-old"` and `"spending": "usually keeps to the mid-range options"`. That is why the demo agent can skip the clarifying questions and pick well on the first try.

Nothing else fills that in. The agent's memory keeps only what the customer said out loud and is [told to ignore](https://github.com/anthropics/commerce-agents/blob/fd4d592/commerce-common/commerce_common/memory.py#L62) "attributes that would have to be inferred." A [provenance rule](https://github.com/anthropics/commerce-agents/blob/fd4d592/shopping-agent/core/shopping_agent/types.py#L194-L198), which tracks where each product came from, lets the agent show only products it found by searching or that the customer already bought. When the setup plugin asks [which system holds your customer profiles](https://github.com/anthropics/commerce-agents/blob/fd4d592/plugins/commerce-builder/commands/scaffold-commerce-agent.md#L56), most stores can only point to the e-commerce platform's customer record: a name, a loyalty tier, a shipping address. That record says nothing about who lives in the house, how much they tend to spend, or what they like. With a profile that thin, the agent cannot pick well on the first try. It has to open by asking the customer the same questions the demo's hand-written profile let it skip.

The merchant agent has the same gap from the other side. When it drafts a campaign, the [audience field](https://github.com/anthropics/commerce-agents/blob/fd4d592/merchant-agent/core/merchant_agent/types.py#L356-L366) is 300 characters of plain text, something like "customers who bought camping gear last summer but nothing since." The instructions tell the model to write it as a description rather than a setting, because the real targeting ["live[s] in the host's system."](https://github.com/anthropics/commerce-agents/blob/fd4d592/merchant-agent/skills/marketing-campaigns/SKILL.md#L24) A person still has to turn that sentence into an actual list of people in the email tool or ad platform, and the only thing the agent knows about those people is what they ordered. It can say what to discount. It cannot say who is most likely to buy it.

## Quickstart

Assume that Faraday has added to your customer table six consumer attributes ([household income](/catalog/v2/household_income), [marital status](/catalog/v2/individual_marital_status), [shopping style](/catalog/v2/shopping_styles), [children in household](/catalog/v2/child_presence_in_household_indicator), [length of residence](/catalog/v2/length_of_residence), [number of bathrooms](/catalog/v2/baths)), a [persona](/docs/abstractions/persona_sets) that says which kind of shopper this customer is, and a ranked list of [products they are likely to buy next](/docs/abstractions/recommenders). (Faraday can also serve the same data over a [real-time API](/docs/features/lookup-api); more on that below.) Two methods use them.

```python
class Storefront(StorefrontBackend):
    def __init__(self, customers: CustomerTable, catalog: CatalogSearch) -> None:
        self._customers = customers
        self._catalog = catalog

    async def get_preferences(self, session: ShoppingSessionContext) -> UserPreferences:
        customer = await self._customers.find(session.user_id)
        preferences = dict(customer.stated_preferences)
        if customer.faraday_attributes:
            a = customer.faraday_attributes
            preferences["household"] = (
                "Inferred from consumer data, not stated by the customer: "
                f"{a.marital_status}, {a.children_in_household}, household income "
                f"{a.household_income}, {a.length_of_residence} at this address, "
                f"{a.baths} bathrooms, shopping style {a.shopping_style}."
            )
        if customer.faraday_persona:
            preferences["persona"] = (
                f"Inferred by a model, not stated by the customer: "
                f"{customer.faraday_persona.name}. {customer.faraday_persona.description}"
            )
        return UserPreferences(
            user_id=customer.user_id,
            display_name=customer.display_name,
            loyalty_tier=customer.loyalty_tier,
            default_location=customer.default_location,
            preferences=preferences,
        )

    async def search_products(
        self,
        session: ShoppingSessionContext,
        query: str,
        filters: SearchFilters | None = None,
        limit: int = 8,
    ) -> list[Product]:
        matches = await self._catalog.search(query, filters, limit=limit * 3)
        customer = await self._customers.find(session.user_id)
        rank = {pid: i for i, pid in enumerate(customer.faraday_recommended_product_ids)}
        matches.sort(key=lambda product: rank.get(product.product_id, len(rank)))
        return matches[:limit]
```

The attributes and persona go into the profile, each marked as a guess rather than something the customer said. The recommendations work differently: the model never sees the list. The code uses it to reorder the search results before the model looks at them, so the products this customer is likely to want are already at the top.

## Full Solution

Faraday matches your customer records to the [Faraday Identity Graph](/catalog), 1,400+ attributes on 240M U.S. adults, and makes predictions from the combination.

Attributes are the simplest step: pick the handful that change which products fit, and mark each line as inferred. The marking matters because the agent is told to treat the profile as fact, but it is also told to offer a guess ["as a guess, never as something they said."](https://github.com/anthropics/commerce-agents/blob/fd4d592/shopping-agent/skills/memory-personalization/SKILL.md#L21) The label puts your line under the second rule. Do not add all 1,400. [A model can only pay attention to so much](/blog/context-engineering-and-demographic-data), and a page of facts about the customer crowds out the conversation. Children in the home helps pick a tent; a guess about someone's credit has no place in a shopping conversation.

A [persona set](/docs/abstractions/persona_sets) sorts your customers into a few types based on those attributes, so one line ("budget-minded, young kids, prefers pickup") replaces a dozen. A [recommender](/docs/abstractions/recommenders) trained on your order history ranks the products each customer is most likely to buy next. It cannot go in the profile, because the provenance rule stops the agent from showing products it did not find, so it reorders search results instead. An [outcome](/docs/abstractions/outcomes) predicts one behavior, like a repeat purchase or a cancellation, as a score per person, and it belongs with the merchant agent: a [cohort](/docs/abstractions/cohorts) is a group of people defined by that score, and Faraday can send it to Klaviyo or Meta as an audience. Your approval screen lists those cohorts next to the agent's audience text, and a person picks one before the campaign goes out.

There are two ways to get this data into the backend. Faraday can write the columns to the warehouse table your backend already reads and refresh them daily, which is what the quickstart assumes. Or the backend can call Faraday's [real-time Lookup API](/docs/features/lookup-api) inside `get_preferences`: one HTTP call with an email or address returns the same attributes, persona, and recommendations for that person. The API is the better fit if you would rather not run a nightly job, or if your agent is a separate service without a warehouse behind it. The two also work together: read the table when the customer is in it, and call the API for someone who signed in for the first time this afternoon. Either way, a person Faraday recognizes can still have blanks where the data is thin, so check each value. Someone browsing anonymously gets nothing until they sign in.

## Automated Eval

The blueprint tells you [how to write test cases and score them](https://github.com/anthropics/commerce-agents/blob/fd4d592/plugins/commerce-builder/skills/commerce-evals/SKILL.md) and includes [a command that builds the test runner](https://github.com/anthropics/commerce-agents/blob/fd4d592/plugins/commerce-builder/commands/author-commerce-evals.md), but the tests are yours to write, because they only mean something against your catalog. Write them to answer one question: did the Faraday data improve the picks without the agent blurting it out?

Use real purchases as the answer key. For each customer with three or more orders, hide the most recent one, give the agent that customer's profile as it stood the day before, and ask for the hidden order's category: "I need a new sleeping bag." Score a hit if the product they actually bought is among the ones the agent shows. Run every case twice, with and without the Faraday data; the difference in hit rate is what Faraday added.

```json
{
  "id": "personalization-041-holdout-hit",
  "state": { "profile": "cust-8813@2026-06-30", "faraday": true },
  "turns": ["I need a new sleeping bag"],
  "expected": {
    "calls_tool": ["search_products", "present_products"],
    "presented_contains_one_of": ["SB-2041", "SB-2041-L"],
    "reply_omits": ["married", "household income", "bathrooms", "persona"],
    "never_calls": ["save_memory"],
    "rubric": "PASS if the picks fit a household with young children without stating any inferred fact about the customer. FAIL if the reply asserts marital status, income, children, residence, or a persona name as fact."
  }
}
```

Most of those checks are plain code: did the agent show one of the right products, did it avoid saying "married" or "household income" to the customer, did it refrain from saving a guess to memory. The `rubric` line goes to a second model acting as a judge, run at temperature zero so the same transcript gets the same verdict every time. Record every run so the checks can be replayed in CI without calling the API, and let any new failure block the merge. Once live, apply the same rubric to a sample of real conversations, and compare add-to-cart and completed purchases between customers with and without the Faraday profile.

Anthropic's commerce agents blueprint gives a store a shopping agent and a merchant agent in days. It leaves the customer profile to you. Here is how to fill it with consumer attributes, personas, recommendations, and propensity, with a test to prove it helped.

All posts

Who are your customers, really? Find out with a Faraday Insights Report

Introducing Ask Faraday: Real answers about American consumers, from Claude, ChatGPT, and more

See who holds the mortgage: new lender and owner data in Faraday

Faraday Pro vs Faraday Enterprise: which one is right for you?

ChangelogSee all

Explore removed

Nearest Location distances in miles

Athena connections now supported

Nearest store with Atlases now live

Turn your Personas into a marketing engine with the Faraday MCP server

The intention economy: The cost of direct mail is what saves it from AI slop

Streamlining Meta custom audiences with Faraday managed connections

How to solve a 35+% finance decline rate with predictive data

Relevance in direct mail starts with the list: four ways to improve yours

Enhancing commerce agents with consumer data