Changelog

A new Analysis tab on every Pipeline surfaces insights about your scope before you build a Deployment — no usage required.

Counts shows the size of your Pipeline's population, individuals and residences, broken down by state and by zip code (when the population spans 250 zip codes or fewer). Use it to size addressable markets and understand cohort distribution at a glance.

Prediction distribution shows how your scope is distributed across probability bins for each outcome and recommender, with cumulative individual and residence counts. Use it to pick deployment cutoffs (e.g. "top 20% by predicted likelihood") before exporting.

Both are also available via the scope analysis API. The existing Efficacy, Diagnostics, and Market opportunity views have moved from the Pipeline overview into the new Analysis tab.

The Talk to your Personas feature has been deprecated. The MCP server — now in beta — is a more flexible and powerful way to bring your Faraday data and predictions into AI-powered workflows.

Rather than a fixed chat interface, the MCP gives any LLM agent real-time access to your personas, cohorts, and predictions via a standard protocol, making it easy to build dynamic, context-aware applications on top of your Faraday data.

You can now see exactly how each row of your data matched (or didn't) every time a dataset ingests. A new ingress log gives you a full matching waterfall for every ingestion event — from total rows received all the way through to which rows were eligible for enrichment.

Each ingress log entry captures:

• Row counts at every stage — from total rows received through processable, valid, allowed, recognized, and enrichable
• Recognition rate — what share of your allowed rows matched known identities in the Faraday Identity Graph
• Enrichability — how many rows and unique people were eligible for enrichment

The most recent log entry is shown by default with the matching waterfall already open, so you get an at-a-glance read on your data quality every time you visit a dataset.

Logs are also accessible via the API at GET /datasets/{dataset_id}/logs/ingress. See the dataset documentation for details.

The Lookup API now always emits every payload key declared on the target's scope, even when a particular value is unavailable. Previously, fields backed by data we couldn't produce — most commonly an fdy_outcome_<UNDERSCORED_OUTCOME_ID>_propensity_* field for a person whose Identity Graph data was too sparse for the propensity model to score — were simply absent from the response. Now those fields are always present, with the value set to null when there's nothing to report.

This makes the response shape stable regardless of how much data we have on a given matched person, so client integrations can iterate over a fixed set of keys instead of conditionally checking for presence.

If your integration was using key presence ('fdy_outcome_xxx' in response) as a proxy for "did we get a score," update it to check for a non-null value instead.

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, 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.

We’ve introduced Talk to your Personas, a new LLM-powered interface that allows you to engage directly with your Persona definitions. The chat agent comes preloaded with your specific Persona distributions and salient traits, enabling you to instantly rewrite marketing copy, generate relevant hooks, and brainstorm campaign strategies—without having to “teach” the AI who your customers are.

Talk to your Personas is built with privacy in mind, operating on aggregate patterns and statistical definitions rather than accessing PII. Because the agent operates as a "fresh slate" in every session to ensure total creative control, you can simply drop in your brand guidelines or current campaign goals to get highly tailored outputs.

You can find the new feature directly within the Chat tab of your existing Persona Sets.

Availability: Talk to your Personas is now active for customers on Faraday’s usage-based plans. If you’re on a legacy plan or trialing Faraday, you’ll need to switch to a usage-based plan to access the feature—reach out to your account team to get set up.

We’ve updated how Faraday determines the number of personas in a set. By moving to a proportional scaling model, we ensure your segments are always optimized for your specific audience size.

What's new

• Dynamic scaling: We replaced the "elbow method" with a proportional function (k=floor(log10​(cohort.size))).
• Utility-first clustering: Persona counts now scale from 2 to 8 based on cohort volume, preventing over-segmentation of small lists and under-segmentation of large ones.
• Improved trait visibility: Larger audiences now receive the granularity they deserve, making unique buyer traits more actionable.

This change is live for all new persona sets. Learn more in the persona set documentation.

We’ve refreshed the invite experience in the Faraday Dashboard to make account access clearer and more secure.

What’s new

When you invite someone to join your account from Settings → Team, the person you invite now always receives an email with a unique invite link, regardless of whether they’ve previously signed into Faraday with email/password or Google. Account membership is only granted after they click the invite link and complete sign-in or sign-up, which verifies email ownership before access is added.

Pending invites now appear in the account users view with status (for example, pending or expired), last sent time, inviter, and actions to resend or revoke. The account users list itself only shows users with active access, so it’s easier to see who’s actually in the account at a glance.

More information can be found in our docs.

We’ve added a new security feature to the Faraday platform that requires all users to verify their email before accessing the Dashboard.

If an existing user’s email isn’t verified yet, they’ll be prompted on login and sent a one-time verification link.

We’ve added full support for MotherDuck, the cloud-based DuckDB platform, as a new connection type in Faraday.

MotherDuck is gaining traction across modern data stacks, and this update ensures teams using DuckDB can keep their data continuously synced with Faraday for enrichment, scoring, and prediction workflows—just like our existing connections to BigQuery, Redshift, Snowflake, and others.

This release also supports ongoing work with partners exploring agentic use cases powered by lighter-weight databases.

To get started, see the new connection guide.

We’ve stopped auto-creating “test accounts” with synthetic "Farazona" data when new accounts are provisioned. This feature was underutilized and often caused confusion. Existing test accounts will be removed.