Scout Persona
A near-free developer tool: upload a persona charter, paste a model API key, run it against our probe library, see exactly where your persona holds and where it drifts before you ship.
What you get
A standalone tool where you upload a persona charter (or paste a system prompt), provide a model API key, and run it against our probe library — invariant probes, adversarial probes, consistency probes. You get a structured report showing where your persona holds and where it drifts.
What makes it different
Most teams test their AI persona by talking to it and trusting their gut. Scout Persona is the discipline of testing it against probes designed to break it — at near-zero cost, in your own environment, before you ship. It's also a marketing surface for our deeper AI Persona research work.
What it can do for you
Catch personality drift before it ships to users. Stress-test your brand voice against adversarial prompts and edge cases. Compare persona-charter versions side by side. Validate that a model swap doesn't change behavior. Give your team a discipline they didn't have.
- Free for individual developers; paid for team accounts
- Self-serve, web-based, no engagement required
- Invariant + adversarial + consistency probes
- Compare two charter versions side by side
- Model-swap testing (does behavior change across providers?)
- Structured report with deviation scores
- API for CI integration
- Funnel into AI Persona service if needed
Who it's for
AI engineers, prompt engineers, and anyone shipping a persona-based AI who wants confidence that the persona holds. Solo developers and small teams who can't justify the full AI Persona engagement but want the discipline.
How we ship it
Self-serve. Sign in, paste charter, paste API key, run. Account creation is the only barrier; the rest is automatic.
Questions people actually ask
What does it actually test that talking to our bot doesn't?
Discipline. Instead of trusting your gut after a few chats, it runs your persona against a probe library built to break it — invariant probes (does it stay itself), adversarial probes (can it be pushed off-character), and consistency probes — and gives you a structured report with deviation scores showing exactly where the persona holds and where it drifts.
I'm pasting my system prompt and an API key. Where does that go?
The probes run against your model through the key you provide, so the model usage happens on your own provider account and the charter stays your material. The tool exists to test your persona, not to collect it — and the report it produces is yours.
What does it cost and how do we start?
It's self-serve: sign in, paste your charter or system prompt, paste a model API key, run. Free for individual developers, paid for team accounts, and account creation is the only barrier. There's also an API so you can wire the probes into CI and catch drift on every change.
What if the report shows problems we can't fix ourselves?
The tool tells you where the persona breaks; fixing a stubborn one is sometimes real design work. That's what our deeper AI Persona engagement is for — same probes, same discipline, with us doing the charter engineering. Scout Persona stands on its own, though; plenty of teams just use the report and iterate themselves.
Frequently paired with
Related products
A one-week engagement that maps your AI-readiness — what's in your data substrate, what's missing, what AI capabilities you could deploy today, and what would need to be built first.
We take 60 days of your production AI traces, build a real eval set, and hand it back with a working harness — so you can finally measure whether your AI is getting better or quietly worse.