A high match rate is a vanity metric if you don't distinguish between where someone lives (address-level matching) and who they are (person-level matching). And even a perfect match doesn't guarantee useful enrichment — those are two independent dimensions of precision, and conflating them is one of the most common and costly mistakes teams make.

## The two dimensions of data precision

There are two independent dimensions of precision in any data enrichment process: **match precision** and **enrichment precision**. They are not the same thing, and a strong score on one does not imply a strong score on the other.

- **Match precision** describes how confidently a data provider recognizes the record you sent them. It has two levels: **person-level matching** (the provider has identified a specific individual — e.g., Jane Smith at 123 Main St, Unit 4B) and **address-level matching** (the provider has identified the household or residence, but not the specific person living there).

- **Enrichment precision** describes the quality of the data being appended to that matched record. It also has two levels: **observed data** (the provider has actual, directly measured values for that person or household) and **imputed data** (the provider doesn't have the value directly, so they estimate it).

- **Imputation** is the standard data science technique used when a value is missing. The system may look at everyone else known to live at the same fully qualified address — a spouse, an adult child, a roommate — take the values that are available for them, and average those to produce a best estimate. It's often better than returning nothing, but the resulting data is residence-level, even when the match itself was person-level.

These two dimensions combine into four possible outcomes. The quadrant below shows what each combination is good for:

[![2x2 grid that describes enrichment precision and match precision.](/images/blog/enrichment-precision-diagram.png)](/images/blog/enrichment-precision-diagram.png)

## What matching precision actually means in practice

Both levels of matching are valid, depending on what you're doing. If you're running a direct mail campaign based on property characteristics — say, targeting homeowners with pools — address-level matching is perfectly fine. You care about the house, not the person. But if you're personalizing outreach based on individual behavior or demographics, person-level matching is what you actually need.

Most providers report a single "match rate" number without distinguishing between these levels. A 95% match rate sounds great — until you realize a significant portion of those matches are address-level, not person-level, and your personalization strategy depends on the latter.

## What enrichment precision actually means in practice

Not all attributes are created equal. Some are naturally person-level — things like age, income, or purchase behavior. These describe an individual. Others are naturally residence-level — like bathroom count, square footage, or home value. These describe a property.

Here's a key insight: more precision isn't always better. If you ask for bathroom count for everyone in your customer base, you're going to get residence-level data — and that's exactly what you want, because bathroom count is fundamentally a property of the home, not the person. Asking for it at the person level wouldn't even make sense. The "right" level of precision depends on what the attribute actually describes.

When everything aligns perfectly, you get a person-level match with observed person-level data for a person-level attribute. You know who Jane is, and you have her actual income. That's the best case.

But data is inherently sparse. Even the best providers don't have every attribute for every person. So when a provider has matched Jane at the person level but doesn't have her income specifically, imputation kicks in — and the value you get back is residence-level, even though the match itself was person-level.

This is the distinction most teams miss: a person-level match does not guarantee person-level enrichment.

## Why this matters for your strategy

If you're buying data to fuel AI models, personalization engines, or predictive analytics, the quality of your outputs depends entirely on understanding what went in. And "quality" here isn't just about volume or match rates — it's about the right kind of precision for your use case.

This connects to a broader problem we see across the industry: teams buy more data thinking it will solve their performance issues, when what they actually need is the right data at the right level of precision. A massive dataset with high match rates but mostly imputed enrichment data isn't necessarily more useful than a smaller dataset with genuine person-level attributes.

Here's a practical framework for thinking about it:

When address-level precision is fine:

- Direct mail campaigns targeting properties (not people)
- Geographic or neighborhood-level analysis
- Property-based segmentation (home value tiers, housing type)

When you need person-level precision:

- Individualized outreach or personalization
- Predictive models based on personal demographics or behavior
- Lookalike audience building based on individual customer profiles
- AI agent workflows that need to understand a specific consumer

Questions to ask your data provider:

- What percentage of my matches are person-level vs. address-level?
- For enriched attributes, how much of the data is directly observed vs. imputed?
- For the specific attributes I care about, are they naturally person-level or residence-level?
- How do you handle sparsity for the attributes that matter most to my use case?

## Transparency builds better outcomes

Most data providers don't explain any of this. They give you a match rate, they give you enriched fields, and they let you assume the best. That works fine — until your AI model underperforms and you can't figure out why, or your personalized campaigns feel generic despite having "complete" customer profiles.

At Faraday, we think the answer is transparency. When you understand exactly what level of precision you're getting — for both matching and enrichment — you can make smarter decisions about how to use it. You can weight imputed data differently in your models. You can choose the right attributes for your use case. You can stop over-investing in data volume and start investing in data precision.

Because ultimately, the question isn't "how much data do I have?" It's "do I have the right data, at the right level of precision, for what I'm trying to do?"

Want to understand how Faraday handles matching and enrichment precision for your data? [Grab a time to talk to one of our context consultants](https://faraday.ai/talk-to-sales).

Match rate alone doesn’t tell you whether enriched data is actually useful, teams need to separate match precision, meaning person-level vs. address-level matching, from enrichment precision, meaning observed vs. imputed data. The right level of precision depends on the use case.

Understanding enrichment precision: what your match rate is actually telling you (and what it's not)

Some brands know their customers by the numbers — average order value, purchase frequency, seasonal spikes. But numbers alone don't tell you _why_ someone buys, what job they're hiring your product to do, or what keeps them coming back. That's the gap this story is about closing.

A leading DTC children's apparel brand had years of valuable transactional data. They knew what sold, when it sold, how often customers returned, which customers were driven by discounts, and what marketing channels were profitable. What they didn't have was a clear, company-wide picture of who their customers actually were and what motivated them to transact.

## The challenge

The brand's core problem wasn't a lack of data — it was a lack of _meaning_ in that data. Their customer records were transactional: order histories, product SKUs, shipping addresses. Useful for operations, but not enough to answer the strategic questions the team was asking.

Who are our highest-value customers, really? What life stage are they in? What motivates their purchases — convenience, values, gifting, something else entirely? And how do we make those insights accessible to everyone in the company — from the CMO to the junior copywriter and performance marketer — not just the data team staring at dashboards?

They needed their customers to come alive. Not as static slide decks pinned to a wall, but as something the whole company could engage with.

## How Faraday helped: Enriching data and finding customers

The brand connected their e-commerce order data to the Faraday platform, which enriched every customer record with attributes from the [**Faraday Identity Graph**](https://faraday.ai/features/faraday-identity-graph) — a built-in dataset covering 1,400+ traits across 240M+ US adults.

Overnight, flat transactional records became rich consumer profiles. The brand could now see household composition, lifestyle indicators, shopping preferences, property details, and estimated income brackets layered onto their existing customer base. The brand could see how their customers were clustering across these socio-demographic dimensions through Faraday derived [personas](https://faraday.ai/docs/how-to/predictions/customer-personas).

This enrichment didn't just add data points — it added _dimension_. For the first time, the team could see patterns they'd only guessed at: which customer segments over-indexed on sustainability values, which ones were driven by gifting occasions, and where geographic concentrations of high-value buyers actually lived.

But Faraday didn't stop at insight. Using their **custom audiences** capability, the brand could deploy these enriched segments directly to ad platforms, pushing predictive, behavior-based audiences into channels like Meta and Instagram. This meant the brand wasn't just _understanding_ their customers better — they were _finding more of them_ on the channels where they actually spend time.

## How Heatseeker helped: validating Personas through real market experiments

Enriched data tells you _who_ your customers are. But it doesn't tell you what message will make them act. That's where Heatseeker came in.

Using Heatseeker's market experiment engine, the brand ran structured experiments **on real consumer channels like Instagram** — not in focus groups or surveys, but in the wild, where customers actually make decisions. Specifically, they:

- **Tested [jobs-to-be-done](https://strategyn.com/jobs-to-be-done/) (JTBD) hypotheses in-market** — running experiments on Instagram to determine which JTBD statements resonated most with different customer segments. Was the primary job "find durable, cute clothes that survive active kids"? Or "buy gifts that feel personal and thoughtful"? Real consumers gave real signal — not survey responses, not guesswork.
- **Quantified pain points with real engagement data** — rather than assuming what frustrated their customers, they tested pain point messaging against Faraday-enriched audience segments on consumer channels to see which problems actually drove clicks, engagement, and conversion.
- **Mapped enriched data to behavioral personas** — Faraday's demographic and psychographic enrichment was layered with Heatseeker's behavioral experiment data, creating personas grounded in both _who customers are_ and _what they actually care about_.
- **Brought personas to life with AI-powered avatars** **and synthetic panels**— and here's where it gets groundbreaking. Heatseeker's AI persona technology doesn't just produce a PDF or a slide deck. It creates **persona avatars that talk like real customers** — because they're grounded in real behavioral and quantitative data from market experiments. Anyone in the company can open a conversation with a persona and ask questions: "What would make you switch brands?" "What's the hardest part about shopping for kids' clothes?" "Would free shipping or a loyalty discount matter more to you?" The personas respond with the voice, priorities, and pain points of the real customer segments they represent.

This is a fundamentally different kind of persona. Not a made-up archetype from a workshop. A living, conversational representation of actual customer behavior.

## The results

The brand went from having a spreadsheet of customer segments to having a **living persona system that the entire company could rally around — and actually talk to.**

**For marketing**, personas informed messaging strategy, creative direction, channel selection, and segment identification — grounded in validated JTBD, pain points from real Instagram experiments, and real time assignment of new customers to a persona.

**For merchandising**, knowing which persona segments over-indexed on gifting vs. everyday wear helped shape product assortment and seasonal planning. They could literally ask the persona avatar "what would you want to see in a holiday collection?" and get an answer rooted in real data.

**For the executive team**, persona avatars became a shared language for strategic conversations about growth, retention, expansion, and the evolution of their customer base — accessible to anyone, not locked behind an analytics dashboard.

**For customer empathy across the org**, something shifted. When a product designer, a customer service rep, or a new hire can actually _chat_ with a data-grounded persona, they develop an intuitive understanding of the customer that no deck or report can replicate. Empathy stops being an abstract value and becomes a daily practice.

The personas weren't static documents filed away after a single workshop. Because they're built on continuously enriched Faraday data and validated through Heatseeker's ongoing market experiments, they evolve as the customer base evolves.

## Why this matters

Most companies treat persona creation as a one-time exercise: run a few interviews, build some slide decks, pin them to a wall, and move on. The problem is those personas age out the moment customer behavior shifts — and nobody in the org actually uses them.

This case demonstrates a fundamentally different approach. By combining Faraday's identity-level consumer enrichment, clustering algorithm, and custom audience deployment with Heatseeker's ability to experimentally validate what actually drives customers — and then making those insights conversational — the brand created personas that are:

- **Data-rich** — grounded in 1,400+ real consumer attributes from the Faraday Identity Graph and, not assumptions
- **Behavior-validated** — tested through real market experiments on Instagram and consumer channels, not focus groups
- **Findable** — deployed as custom audiences through Faraday so you can reach these customers where they are
- **Conversational** — Heatseeker's AI persona avatars let anyone in the company chat with their customers, driving empathy and faster decisions
- **Living** — continuously updated as new data flows in and new experiments run

The combination of _knowing who your customers are_ (Faraday), _finding them where they are_ (Faraday custom audiences), _proving what they care about_ (Heatseeker experiments), and _making them someone you can talk to_ (Heatseeker AI personas) is what turns personas from a strategy exercise into a competitive advantage.

---

**Ready to bring your personas to life?** Faraday and Heatseeker work together to turn your customer data into validated, living personas that drive real decisions — and real empathy. [Get started with Faraday](https://faraday.ai/signup) | [Try Heatseeker](https://heatseeker.ai)

By combining Faraday's deep consumer data enrichment with Heatseeker's real-world market experiments, this DTC brand transformed static transactional data into living, AI-powered Personas that growth and empathy.

This DTC children's apparel brand brought their customer Personas to life with Faraday and Heatseeker

[John Hardy](https://johnhardy.com/) has always been more than just a jewelry brand; it’s a boutique experience. But even for a brand with such a legacy, the modern digital landscape presents a challenge: how do you maintain that high-touch, one-to-one feeling when you're communicating with thousands of customers at once?

In a boutique, associates tailor recommendations based on what they know about a client’s preferences, occasions, and past purchases. That depth of understanding drove conversions. But replicating that level of personalization online was the real challenge.

To continue delivering the same high-touch experience that had brought them so much success as they scaled, they needed to move past generic blasts and toward the same thing that had always driven their success: unique, personalized experiences that lead to actual conversions.

## The problem: Personalization at scale requires context

We recently sat down with [Jonas Malpass Caligan](https://www.linkedin.com/in/jonas-malpass-caligan-540b6b35/), John Hardy’s VP of Ecommerce and Digital marketing, and her framing of this problem really captured the friction:

“To me, personalization is really the only way to break through the noise we are seeing in the market. Many of our greatest successes have been thanks to the one-to-one relationship building we’ve been able to create through clientelling, and Faraday allows us to do that at scale for all of our customers.”

This is a challenge we hear from brands all the time. At Faraday, we have a word for it too: it’s a **context gap**. When a sales associate is selling in a boutique, they have a massive advantage: **small talk**. Through simple conversation, they learn that a customer has a daughter with a birthday coming up, or that they prefer silver over gold for everyday wear. That simple conversation provides the context that informs a perfectly timed, highly effective offer.

Automated digital workflows don’t have the benefit of small talk. They are typically limited to **first-party data**—the information a brand can collect directly through transactions and clicks. And while vital, that data only represents a fraction of the customer’s actual life and narrative.

To operate with the same effectiveness as a seasoned sales associate, automated systems need more than transaction history. They need the kind of background context an associate gathers naturally through conversation—the signals that explain not just what someone bought, but why they might buy next. Without that, automation defaults to generic. Faraday closes that context gap by providing privacy-safe third-party consumer data that supplies the missing background, allowing digital workflows to behave less like blunt instruments and more like informed, intentional advisors.

## The implementation: Using data to drive conversion

The John Hardy team decided to put this theory to the test with one of their most important annual initiatives: their **VIP gift card program**. For four years, this program had relied on a manual selection process based on basic purchase history. It worked, but it lacked the nuance the team knew was necessary to maximize its potential without over-spending on discounts.

Working with Faraday, the team replaced manual guesswork with a predictive [adaptive discount](https://faraday.ai/templates/adaptive-discounting/segment)ing strategy powered by Faraday’s data. Instead of looking at past purchases alone, they used AI-driven propensity scores to identify which specific discounts online customers would need to redeem an offer and convert.

This effectively automated the intuition of an in-store associate:

- **Predictive targeting:** They identified the exact customers who needed a nudge to buy, rather than wasting a gift card on someone who would have purchased at full price.
- **Data-driven "soft cues":** They integrated life-event data into their clientelling workflows, giving remote sales teams a natural, data-backed reason to reach out that felt personal, not promotional.

## The outcomes: Better outcomes, lower noise

The results of this data-driven approach were immediate and clear. By provisioning their workflows with better context, the John Hardy team proved that you can drive more growth with less "noise."

| Metric                 | Result |
| :--------------------- | :----- |
| Year-over-Year Demand  | \+17%  |
| Total Redemptions      | \+25%  |
| Audience Size Increase | \+9%   |

To validate the model, the team monitored a **holdout group**—high-propensity customers identified by Faraday who were intentionally _not_ sent a gift card. Even without the incentive, this group converted at a rate of **14%**, confirming that the models were accurately identifying the brand's most naturally engaged customers. But even better, when that same high-propensity audience _did_ receive the gift card, the conversion rate jumped to **34%**. This 20-point lift proved the measurable power of the targeted offer and demonstrated that the team was successfully finding the exact customers who were ready to be moved to a purchase.

## Scaling the boutique experience

For the John Hardy team, the success of the V VIP program was only the beginning. The goal remains the same: to act smarter and faster by bridging the context gap across every channel.

As they look ahead, the team is already planning to weave these predictive insights deeper into their broader strategy—from informing **wholesale expansion** to providing daily **clientelling cues** for their global sales teams. By combining a savvy marketing vision with the right data context, John Hardy is ensuring that "boutique" remains a feeling, no matter how large the brand scales.

John Hardy used Faraday’s predictive data to tailor offers more precisely, increasing conversions and demand while reducing unnecessary discounting.

Personalization at scale: How John Hardy tailored their offers and won with Faraday

[![diagram showing how marketing stacks have changed in 2026](/images/blog/bowties-diamonds/bowties-diamonds1.png)](/images/blog/bowties-diamonds/bowties-diamonds1.png)

Something very interesting has happened with the overall topology of a cutting-edge brand’s martech stack. Over the past year or so the pattern I’m seeing among leading brands (including many of our own clients) is a shift from “bowtie”-style stacks, like you see at the left, to “diamonds” like on the right. Here’s how and why this revolution is underway.

## The 2010s martech stack: Hub-and-spoke data warehouse models

Throughout the 2010s it was fashionable (and useful) to imagine any technology-forward organization’s stack as a “hub and spoke” with the data warehouse in the middle. Every component would pull the data it needed from the warehouse and, in return, supply the warehouse with data that other components might need.

In practice this was never quite so easy. Not every software product a brand needed to actually engage its customers natively talked to the warehouse. Sometimes this was for straightforward reasons—it’s hard to build and maintain countless native connectors to every “source of truth” across every vertical—and other times the end product saw the warehouse as a threat: they wanted to own the workflow _and_ the data.

[![diagram showing hub and spoke style marketing stack](/images/blog/bowties-diamonds/bowties-diamonds4.png)](/images/blog/bowties-diamonds/bowties-diamonds4.png)

## The early 2020s: ETL tools and the bowtie marketing stack

In the end, the market spoke, and robust Extract Transform and Load (ETL) tools like [Fivetran](https://www.fivetran.com/) became the crucial connector to feed data into the warehouse. Complementary Reverse ETL tools like Hightouch served the natural inverse role: delivering data from the warehouse back to the engagement tools marketers actually use.

It’s easy to see how central this ETL/RETL role became in the stack’s topology. So much so, in fact, that the “mental model” would often place it, rather than the warehouse itself, in the middle. That’s how we got the bowties of the early 2020s.

[![diagram showing bowtie style marketing stack](/images/blog/bowties-diamonds/bowties-diamonds2.png)](/images/blog/bowties-diamonds/bowties-diamonds2.png)

## 2026 martech stacks: Middleware and the diamond data model

The centrality of the ETL/RETL position did not escape its occupants’ notice. In many cases it was the _only_ tool with visibility on 100% of all of the organization’s data. The incumbent ETL/RETL vendors started to spread their wings, offering value-added services within this prime location—see Hightouch’s decisioning product and its latest agentic offering as examples. Other vendors like [OfferFit](https://www.braze.com/resources/articles/what-is-offerfit) (now a B[raze](https://www.braze.com/) product) sprung up in this “middleware” zone, leveraging data from the warehouse to orchestrate workflows within the engagement platforms.

Faraday, of course, thrives here as well, adding context to an organization’s data on its way to the engagement tools. Products like [cube](https://cube.dev/) are starting to imagine the middleware zone itself as multi-layered, offering normalized semantics that make its neighbors’ jobs easier.

The “source of truth,” meanwhile, at the bottom of the diagram, has crystallized in my mind to a single point. As Scott Brinker so eloquently [put it](https://newsletter.chiefmartec.com/p/the-saas-moats-are-crumbling-but-the-opportunity-is-bigger), once you “strip away the features, the interfaces, the proprietary data lock-in, the ecosystem lip service,” these systems essentially resolve to the same thing: the organization as represented by _data_.

[![diagram showing modern marketing stack](/images/blog/bowties-diamonds/bowties-diamonds3.png)](/images/blog/bowties-diamonds/bowties-diamonds3.png)

## The future of martech: AI agents and constellation structures

As the agentic paradigm deepens its hold on our industry, this diagram—already a far from perfect reflection of reality—will inevitably shift again. Where it goes is anyone’s guess, but I do believe it will be far less linear. Certainly agents will orchestrate everything, but I imagine their purview will extend beyond unidirectional customer engagement. A “constellation” structure is likely to emerge, with agents gathering data from every interaction and disseminating learnings throughout the stack.

The result may look eerily familiar — a modern recreation of the hub-and-spoke structure from a decade ago. Can’t wait to see where we go from there.

Martech has evolved from warehouse-centric “hub-and-spoke” systems to ETL-driven “bowtie” stacks and now to middleware-powered “diamond” models, with the next shift likely toward AI agent–orchestrated, more fluid “constellation” architectures.

Bowties to diamonds: 2026’s new marketing stack

**Update, May 2026:** This feature has been deprecated. The ability to interact with your Faraday personas and predictions is now available in a more powerful form through our [MCP server](https://faraday.ai/docs/features/mcp), which is currently in beta and gives AI agents real-time access to your Faraday data and predictions directly. We recommend exploring the MCP as the successor to this feature.

---

In 2026, we all know that effective marketing requires personalization.

But this wasn’t always accepted as fact. Years ago, one of our earliest clients—[a major home goods brand](https://www.bollandbranch.com/)—wanted to confirm the premise for itself. So they ran a rigorous experiment to find out just how much value Faraday’s predictive [Personas](/docs/abstractions/persona_sets) could generate. They committed to a strategy that most marketing teams of that era only dreamed of: instead of sending one generic email to their entire list, they created unique content variants for every single campaign. They had their team write a generic control version, as well as three hyper-tailored versions specifically crafted for the distinct vocabularies and motivations of their unique Personas.

The results were undeniable: [A 30% lift in conversion](/stories/boll-and-branch).

By every revenue metric, the experiment was a massive success. Yet, despite the clear upside, they didn’t stick with the new system very long.

Why would a business walk away from a 30% lift? The answer is simple: because the manual labor required to understand what makes each Persona special, and then write, edit, and stage unique versions of every single email, was simply too hard and tedious to sustain. The friction of the process outweighed the lift in revenue.

This is the paradox of personalization: The more you tailor your messaging, the better your results—but the more work you have to do.

## Talk to your Personas

We built a new chat interface to solve that tedium.

Faraday has always been great at helping you understand _who_ your customers are. We have a range of tools—from [AI-generated summaries to salience trait detection](/blog/new-release-trait-salience)—that help you investigate exactly how they differ. But at the end of the day, you still have to figure out how to apply those insights and actually _talk_ to them.

Now, you actually can. Our new chat feature provides a familiar AI interface, but we preload the chatbot with all the in-depth details about your Personas. You don't have to teach the AI who your customers are. It already knows!

However, the agent does _not_ natively know anything about your brand. This is by design—it allows you to give the chat whatever context, guidelines, or quarterly goals you want so you get highly relevant outputs. You just chat!

[![Chat with personas feature in Faraday's dashboard](/images/blog/persona-chat/persona-chat-unfilled.png)](/images/blog/persona-chat/persona-chat-unfilled.png)

## Power up your marketing

This feature allows you to move from passive analysis to active execution immediately. Here is a sneak peek at a few ways you can start using it today:

- **Match Personas to campaigns:** Describe a specific product launch or holiday promotion and ask the chat which Persona in your set is most likely to respond.
- **Brainstorm tailored offers:** Identify an underperforming segment and ask the AI to suggest specific promotions or incentives that align with that Persona’s unique motivations.
- **Generate personalized copy at scale:** Paste your baseline messaging into the chat and instantly receive variants for subject lines, email body copy, and landing pages tailored to each Persona.
- **Build synthetic focus groups:** Save time and budget by asking the AI to generate a panel of virtual customers that proportionately mirrors the distributions of your actual Persona set.
- **Enable Sales roleplay:** Improve outreach by asking the agent to "act" as a specific Persona so your sales team can practice overcoming objections and perfecting their pitch.

_(Note: The chat does not currently retain memory or history between sessions, so you will want to provide your brand context in each new conversation.)_

## How to talk to your Personas

This feature is included at no additional charge for clients on our usage-based pricing (UBP) plans.

You can find the new chat feature directly within your existing Persona sets:

1. Go to a Persona set on the Dashboard.
2. Click the **Chat** tab at the top of the page, or simply add `/chat` to the end of the URL.
3. Start talking to the interface as you would with any other LLM.

[![Chat with personas feature in Faraday's dashboard](/images/blog/persona-chat/persona-chat-filled.png)](/images/blog/persona-chat/persona-chat-filled.png)

## A note on privacy and safety

We know that using AI with customer data requires trust. The chat agent **does not have access to PII (Personally Identifiable Information)**. The model operates on the aggregate patterns and statistical definitions of your Persona groups, not the private data of individuals.

## Ready to start?

The days of choosing between personalization and productivity are over. By talking directly to your Personas, you can finally operationalize the deep insights you already have, turning static data into dynamic content in seconds.

_Keep an eye out for our next post, where we will dive deep into step-by-step playbooks and actual prompts for getting the most value out of these new use cases!_

Faraday’s newest feature lets you talk to your Personas using an AI agent—preloaded with your unique Persona definitions—to instantly generate targeted marketing copy, subject lines, and campaign strategies without manual tedium.

What's new: Talk to Personas

We recently announced the biggest update to the Faraday platform ever: an overhauled version of the [Faraday Identity Graph (FIG)](https://faraday.ai/features/faraday-identity-graph). FIG is the foundational dataset on which all other services at Faraday are built and if you want the big picture, check out our [main announcement](https://faraday.ai/blog/now-live-faraday-identity-graph-version2).

But today, I want to zoom in and talk about one specific, highly anticipated aspect of FIG v2: the data catalog.

## Starting from scratch

Over the last decade, we’ve learned a lot about how to structure data, and we’ve been continuously improving that whole time. But for FIG v2, rather than continue to make incremental updates, we took those years of learnings and rebuilt the dataset from scratch—ensuring every attribute is standardized, strictly categorized, and crystal clear.

Nowhere is that rigor more obvious than in our new data catalog.

## A better data dictionary

This new data catalog goes far beyond a standard data dictionary. It features an entire dedicated page for every single attribute in FIG v2.

[![FIGv2 data catalogue](/images/blog/fig-v2-data-catalog/data-catalog.png)](/images/blog/fig-v2-data-catalog/data-catalog.png)

Historically, a lot of this highly detailed data has only existed internally at Faraday and clients were required to go through their account management team to get these details. Now, for the first time, we are publishing it so that all of our users can get direct value out of it.

[![FIGv2 data catalogue example](/images/blog/fig-v2-data-catalog/data-catalog-example.png)](/images/blog/fig-v2-data-catalog/data-catalog-example.png)

When you land on these new attribute pages, you won't just find basic metadata like names and descriptions. We are showing you the true depth of the data by surfacing the really important technical details and historical context you need to make decisions, including:

- **Data distribution:** Exactly how many people are observed in each category, or how a numerical attribute is distributed across a histogram.
- **Technical properties:** The API name, category, unit, data type, statistical type, allowed values, and deprecation status.
- **Coverage breakdowns:** Exactly how many individuals have a known value versus a value imputed from their address or geography.
- **Data derivation:** Whether a value was directly collected/observed, modeled, or survey-based — so you know exactly how each attribute was produced.
- **Time series and contribution history:** A look at how many observations we've collected over time and the authorities that contributed them.
- **Directionality and interpretation:** Guidance on how to use the data (e.g., how missing values should be interpreted—does a missing value mean "we don't know," or should you assume it's "false"?).

## Built for marketers and data scientists alike

How you use this level of transparency really depends on what you're trying to build.

**If you’re a marketer,** let's say you’re looking for a specific piece of context to personalize an email campaign. In the past, finding that exact attribute usually meant digging through a dense, traditional data dictionary or—more likely—having to reach out to your account manager and wait for an answer. Now, you can skip the middleman, search the catalog yourself, and find exactly what you need to make a campaign feel bespoke.

**If you're a data scientist**, say using Faraday's data for internal modeling, things like data type and directionality matter immensely—they have a massive impact on the resulting accuracy of the models you're building. Instead of hunting for those specs, all of those crucial technical details are now front and center.

## Easier to browse, more to discover

When you start searching through the new data catalog, you might notice the data feels much cleaner. By doing a massive amount of consolidation and normalization behind the scenes, we’ve made FIG v2 much easier to navigate. Better yet, that cleanup created headroom for us to bring in additional vendors and add entirely new attributes.

So go ahead and explore—there is a lot more context about American consumers waiting for you.

**Interested in a specific data point?** If you're looking for a particular attribute or curious about our coverage for a specific demographic, we’re happy to pull those details for you. Just send a note to your account management team directly.

## What comes next

As we noted in our [main announcement](/blog/now-live-faraday-identity-graph-version2), FIG v2 is set to officially release in April. However, we are currently looking for beta testers to get in early. If you're interested in getting your hands on the new data catalog and taking it for a spin, reach out to your account management team to learn more.

And keep an eye out—we'll be dropping more deep dives into FIG v2 in the coming weeks\!

Explore the new Faraday Identity Graph (FIG) v2 data catalog to access detailed attribute pages, visual data distributions, and technical metadata designed for marketers and data scientists.

Deep dive: FIG v2 data catalog

Even when top-line revenue looks healthy, a shrinking active customer base is a major warning sign. In today's direct-to-consumer landscape, where customer acquisition costs are at an all-time high, you cannot afford to have a leaky bucket.

A major DTC children's clothing company recently faced this exact dilemma. Like many established retailers, they possessed solid historical transaction records and had just rolled out a new marketing automation platform to power their engagement. Despite these massive investments, getting one-time buyers to come back was proving incredibly difficult.

The missing link? They fell into the classic "empty CRM" trap. They knew exactly what was purchased, but they didn't truly understand the people behind the purchases. Without a clear, multi-dimensional picture of the individual, even the most sophisticated automated outreach falls flat.

## The fix: foundational data enrichment

Before diving into complex predictive modeling or black-box AI, the organization took a step back to repair its data foundation. You can't personalize a customer journey if your database only consists of an email address and an order number.

They collaborated with Faraday to safely append external consumer intelligence to their internal records. This foundational data enrichment meant looking beyond the transaction and attaching the most relevant third-party demographic, psychographic, and lifestyle data points to their existing profiles.

By organizing these newly acquired details into distinct clusters, the brand successfully mapped comprehensive personas onto their audience. This granted the marketing team immediate, actionable visibility into the real people making up their market—shifting their perspective from "order #12345" to a complete view of a household's life stage and purchasing behaviors.

## A clear view of their customers

While the ultimate objective is always revenue growth and repeat purchases, the immediate victory here was absolute clarity.

This data enrichment proved vital for internal reporting, empowering leadership to finally comprehend the diverse segments within their ecosystem. Instead of treating all one-time buyers as a monolith, they could now diagnose the root cause of their retention struggles. They could clearly see the difference between a price-sensitive shopper who only converts during a major sale, and a high-value loyalist who simply needs a nudge about a new product line.

By establishing this identity-level understanding first, the marketing team is now fully unblocked to design highly personalized customer journeys. This solid groundwork acts as the perfect launchpad for their upcoming advanced initiatives, paving the way for dynamic product suggestions, highly tailored promotional strategies, and adaptive discounting.

The takeaway is simple: you cannot create personalized experiences at scale if you don't know who you are communicating with.

Want to learn more about how data enrichment could improve your retention? [Let's walk through it together](/talk-to-sales).

A DTC children's apparel brand used Faraday's data enrichment to integrate identity-level insights into their CRM, unblocking their predictive personalization strategy and gaining clarity on their customer base.

How one DTC apparel brand proved identity-level context is the key to unlocking retention

**See our complete guide:** [Powered by Faraday — embedding predictive AI in your platform](/blog/powered-by-faraday-complete-guide-embedded-predictive-ai).

---

AI agents are reshaping how brands interact with consumers. Shopping assistants, recommendation engines, agentic marketing tools—all of them promise to deliver personalized experiences at scale. But there's a fundamental problem: personalization requires context, and context requires identity. For the vast majority of your website traffic, you have neither.

Roughly 95% of website visitors are effectively anonymous. Safari's Intelligent Tracking Prevention, Firefox's Enhanced Tracking Protection, Chrome's evolving privacy restrictions, widespread ad blocker adoption, and incognito browsing have collectively dismantled the cookie-based identity model that personalization has historically relied on. Without cookies, there's no persistent identifier. Without an identifier, your agent has no idea who it's talking to—and falls back to the same generic experience it would serve anyone else.

This is the bottleneck for personalized agentic experiences. It doesn't matter how sophisticated your agent is if it has zero context about the person it's serving. The agent needs to know _something_ about the visitor—what they're likely interested in, how price-sensitive they are, whether they're a first-time browser or a high-intent buyer—and right now, for almost all of your traffic, it knows nothing.

### Pixel providers: resolving anonymous visitors

A growing category of tools—often called pixel providers—directly addresses this gap. The concept is straightforward: you install a lightweight JavaScript snippet in your site's `<head>`, typically via Google Tag Manager or a platform-specific integration like a Shopify app. The pixel fires on every page load and resolves anonymous visitors to a known identity—email address, name, mailing address—using a combination of device fingerprinting, IP intelligence, and the provider's own identity graph.

Numerous providers operate in this space ([reach out to ask about our recommended partners](/talk-to-sales)), each with their own identity graph and installation flow. The specific mechanics vary—some offer configurable collection rules to filter for high-intent visitors before resolution, others resolve on every page view—but the output is the same: a resolved identity record delivered to your systems via webhook, API, or warehouse sync.

### Adding consumer context with Faraday

A resolved identity is a critical first step, but an email address alone doesn't tell your agent much. To truly personalize, you need rich consumer context: demographic and lifestyle attributes, purchase propensities, persona classifications, predicted next-best-offer. This is where Faraday comes in. Faraday takes the resolved identity from your pixel provider and enriches it against the [Faraday Identity Graph](https://faraday.ai/blog/series/fig)—returning 1,400+ consumer attributes alongside custom predictive scores you've configured (propensity to convert, persona membership, cohort affinity, and more) via the [Lookup API](https://faraday.ai/docs/features/lookup-api).

![Batch and real-time workflows both work](/images/blog/pixel-providers-agentic-personalization/workflow.png)
_Batch and real-time workflows are both available_

The combination of pixel-based identity resolution and Faraday's consumer context enrichment creates a complete pipeline: anonymous visitor → known identity → rich, actionable context → personalized agentic experience.

### Option A: batch enrichment

The batch path is ideal when you're running scheduled enrichment, building audiences, or doing offline analysis.

Your pixel provider delivers identified visitor records—email, name, address—to your data warehouse (Snowflake, BigQuery, Redshift, Postgres, S3, or similar). You connect that warehouse to Faraday as a [data source](https://faraday.ai/docs/abstractions/datasets). Faraday resolves the identities against FIG, enriches each record with consumer attributes and predictive scores, and [deploys](https://faraday.ai/docs/abstractions/deployments) the results back to your warehouse or to downstream systems via managed connections.

From there, your agent applications query the enriched data directly from the warehouse. Because the enrichment happens on a schedule, this patyh works well for use cases where near-real-time isn't critical: bulk audience segmentation, periodic model retraining, cohort-level analysis, and offline campaign planning.

### Option B: real-time enrichment

The real-time path is where things get interesting for agentic experiences that need to personalize on the fly.

The pixel fires on page load, and the provider resolves the visitor to a known identity in real time—typically within seconds of the page rendering. Your application backend immediately calls Faraday's Lookup API (`POST /v1/targets/{target_id}/lookup`) with the resolved PII (email, address, phone + last name, or any combination). Faraday returns the full enrichment payload—propensity percentiles, persona classifications, cohort membership, FIG attributes—in milliseconds.

Your agent now has everything it needs. A shopping assistant can recommend products based on predicted category affinity. A retention tool can calibrate discount depth based on price sensitivity scores. An agentic marketing platform can select the optimal channel and message for a given persona. All of this happens while the visitor is still on the page, transforming what would have been a generic interaction into a contextually rich, personalized experience.

### Getting started

To get this workflow started, reach out and [talk to sales](/talk-to-sales). Or, if you'd like to get moving immediately, you can [sign up for Faraday](https://faraday.ai). Our [documentation](https://faraday.ai/docs) covers the full setup for both batch and real-time integration paths.

AI agents need consumer context to personalize, but most website visitors are anonymous. Pixel providers resolve anonymous traffic to known identities -- and Faraday enriches those identities with 1,400+ attributes and predictive scores so agents can deliver real-time, personalized experiences.

How pixel providers unlock consumer context for AI agents

_Faraday automatically groups your customers into distinct, actionable subgroups based on shared traits. To ensure your segments are highly useful, we dynamically scale the number of Personas based on your total audience size. This gives you the perfect level of granularity for personalized marketing._

In 2026, marketers know that a generic message is a campaign killer. Your buyers are unique. Blasting your entire list with the same offer won't win the deal anymore. In this context, the question is: how do you effectively segment a massive, messy audience into groups you can actually talk to? And the answer is generally by building customer [Personas](https://faraday.ai/docs/abstractions/persona_sets).

But how many Personas do you need? If you have a customer list of 1,000 people, organizing them into a few distinct personas makes sense. But what if your list is 100,000 people? Or 10 million?

If you are still squeezing a massive, diverse audience into those same basic Personas, you aren't personalizing at all. You are just generalizing at a slightly more granular scale.

## The problem with traditional Persona clustering

Historically, many data scientists have used a technique called the “elbow method” to help decide how many personas (or clusters) to create. The method tests different numbers of groups—one, two, three, four, and so on—and measures how tightly each customer fits within each grouping. As you add more clusters, the fit improves, but the improvement slows over time; each additional cluster helps a little less than the one before it. The “elbow” is the point where adding another group no longer meaningfully improves the separation.

In theory, that elbow represents an optimal number of personas.

In practice, real customer data rarely produces a clean, obvious elbow. Human behavior overlaps. Traits blend together. Instead of a sharp bend in the curve, you often get a gradual flattening. When that happens, the algorithm generally defaults to a standard output: three clusters. And often, three is not what you need

## The myth of the "true" persona

The elbow method breaks down because it is optimized to find a mathematically correct answer. It is hunting for what data scientists call “true clusters”.

But when our product team talks to clients, we often say: “In marketing there is no such thing as correct personas, only useful personas”.

For a mathematically true persona to exist, your audience data needs a massive, undeniable gap. For example, if your brand sells two entirely unrelated things—like skateboards for teenagers and mobility aids for seniors—your buyers will naturally split into two separate demographic groups. The math easily finds that gap. But if your groups are that distinct, you probably didn't need clustering tools to point them out to you at all.

For almost every other brand, human data is messy. Your customers have overlapping traits and nuanced behaviors. Because those massive gaps don't exist, the elbow method gets confused and tends to lump everyone into the default number of buckets: three. But often, three personas is not what you actually need.

## Segmenting for usefulness, not perfection

To build personas that drive value, we realized we needed to stop chasing mathematical perfection and start optimizing for utility.

Instead of relying on an algorithm that forces arbitrary limits, Faraday has rewritten the rules. We now dynamically scale your persona count based directly on the size of your audience. Using a proportional sizing model, Faraday now assigns a persona count ranging from a minimum of 2 up to a maximum of 8 based on the volume of your cohort.

Here is why this changes the game for your campaigns:

- **Granularity that scales with you:** An audience of 1,000 yields 3 personas. 10,000 yields 4\. 100,000 yields 5\. Massive lists finally get the rich segmentation they deserve.
- **Characteristics shine through:** Because large audiences are no longer crammed into three tiny boxes, the unique traits that define your buyers become visible and actionable.
- **No more micro-segments:** Conversely, smaller cohorts will never be artificially chopped into too many tiny, useless personas. Your groupings stay distinct and easy to manage.

Marketing isn't about hitting an arbitrary number of segments. It's about finding the best way to speak directly to your customers' unique characteristics. With proportional personas, you have the exact right number of segments to make your next campaign your highest-converting one yet.

**Ready to see your new segments?** Log in to Faraday to explore your dynamically scaled persona sets today, or read the updated docs for more details on analyzing your audience.

Faraday has replaced traditional persona clustering with a dynamic scaling model that automatically adjusts the number of personas based on audience size, ensuring marketing segments are always granular enough to be actionable without becoming overly complex.

Smarter segmentation: why we rewrote the rules on Persona sizing

When you’ve built high-performing predictive audiences in Faraday, the goal is to get them into your marketing channels as quickly and securely as possible. For many of our clients, [Meta](https://business.facebook.com/latest/home?nav_ref=bm_home_redirect&asset_id=1564501063761817) (Facebook and Instagram) is the primary destination.

However, the manual process of exporting CSVs, ensuring correct SHA256 hashing, and uploading them to Meta Business Manager is often a bottleneck for agile testing and introduces unnecessary security risks.

## The trouble with manual uploads

Traditionally, syncing data to Meta requires manual intervention:

- Formatting data to meet Meta’s specific requirements.
- Manually hashing personally identifiable information (PII) to ensure privacy.
- Managing a constant stream of manual uploads, which often leads to stale audience data.

## How Faraday managed connections solve this

To solve this, Faraday offers a managed connection service. We act as your technical partner—effectively functioning like an agency within your Meta ecosystem—to automate the delivery.

By leveraging Hightouch, our r-ETL service, we handle the SHA256 hashing and data delivery directly. This ensures your audiences are pushed into your account with zero manual data handling, keeping your targeting fresh and your workflows secure.

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

The following process ensures a secure, automated link between your Faraday predictive models and your Meta Ads account.

1. **Set up the connection:** Create a Facebook connection in your Faraday account and share your Meta ad account ID.
2. **Finalize setup:** Submit a support ticket for the Faraday team to finalize the connection setup.
3. **Grant access:** Faraday will request access to manage your Facebook account (acting as an agency) so we can access Meta Business Manager and push data directly.
4. **Configure the workspace:** We set up a [Hightouch](https://hightouch.com/) workspace on the backend to sync specifically to your Facebook account.
5. **Create the pipeline:** You create a pipeline in Faraday to deploy the specific audience payload to Facebook.
6. **Request deployment:** Submit a support ticket asking to deploy that specific audience to Facebook.
7. **Sync completion:** We complete the sync for you and notify you as soon as the audience is ready for use in your campaigns.

> **Note:** The connection itself only needs to be set up once. However, you will need to submit a support ticket for each specific audience you want to deploy to ensure the naming (prefixed with `fdy_`) and sync parameters are correct.

## We’re here to help

And remember, if this process is still giving you trouble, just reach out to support. We're here to help\!

Faraday’s managed Meta connection automatically syncs predictive audiences—handling hashing and delivery—so you can skip manual uploads and keep targeting fresh and secure.

All posts