Expert judgment your agent can ask for.
Your agent knows facts. It does not know which trade-off a particular person would make. Avva publishes that judgment as something your agent can call. Paste one link into Claude, Cursor, Gemini, or ChatGPT, and it consults a named expert before it commits.
Inside a published model
A model is not the output of a questionnaire. It is a small graph, fitted from calls the expert already made. It holds those calls, the forces each one turned on, and the order those forces resolve in when they collide. Nobody fills in a ranking. The math reads it off the decisions themselves.
A rules file converges: the fortieth decision and the four-hundredth both land on roughly the same handful of criteria. A case base does not — one decision in is one case out, so it is the half that keeps getting better as the expert keeps working.
How the order gets fitted
Three steps, and the expert is never asked to rank anything — every number here is read off decisions they already made.
One decision reveals several contests
Each case records which forces settled it and which lost. That split alone is a set of head-to-head contests — one decision gives four here, and the expert is never asked to rank anything.
Forces get a resolution order
The same method tournament statistics uses to rank players from match results. It answers the one question that changes what an AI does: when two of this person’s forces collide, which wins. Fitted from the contests, never stated by the expert — and printed only with the sample behind it.
Which case counts as nearest
A case built on forces you do not have is about something else, so it is penalized in full. Extra pressures on your side cost little — the shared forces still hold. Measuring both sides the same way would be backwards for a buyer.
The math cannot settle everything, so the rest runs on hard minimums instead. Every published claim carries the count of approved decisions behind it. A hard stop rule needs at least two. One decision becomes at most one case. Coverage labels (Light / Solid / Broad) say how much of the expert's record the model rests on, not how accurate it is.
Avva runs no model of its own. Your agent does the reasoning, and the verdict it reaches is its own, made under the expert's published judgment.
What your agent actually receives
Nothing here says the second answer is more correct — it says the expert’s record arrives before the answer instead of after it. That is what the protocol does: your agent consults the model before it commits to a call, not once you have already pushed back.
Avva doesn’t invent an answer for you. It returns the expert’s verification protocol: what to notice and how much it weighs, when to stop, what changes the answer, and which questions to ask first. Your own AI applies that protocol to your context, on your tokens, in your tools.
Raw decision stories stay out of storage. Published models keep reusable judgment only. Details live in the Privacy Center.
If you want an expert’s judgment
A standing reviewer inside Claude, Cursor, Gemini, or ChatGPT — not another chatbot to talk to.
Pick an expert
Read the calls they have made, the reasons they gave, and where they would tell you to stop.
Copy their link
One URL from their page, pasted into your AI’s settings. No account, no key, and it works right away.
Make it standing
Save the note from their page into the file your AI already reads, and it consults the expert without being asked.
If you publish your decisions
Not a resume, not a clone. The calls you already made, turned into rules your clients’ AIs can ask for.
Start from the assistant you already use
One link into the AI that already has your work history. It searches, then shows you titles first — you cut anything private before any text reaches us.
Your assistant builds the model
It reads what you approved, works out the rules behind your calls, and checks its own draft against them. Two questions at most, then it hands you the result.
Skim, confirm, sign in to own it
You read the finished rules, not the raw stories, and confirm they are yours. Sign in only at publish — the model is yours, and you can unpublish any time.
What you end up with
- A public page and an MCP endpoint you own. Hand the link to a client and their AI works under your rules, by name.
- You can unpublish or delete any time. Republish onto the same page as your judgment changes.
- A count of how often your model was actually consulted — in your dashboard, nowhere else.
- Your source material is never stored. Keep
avva-decisions.json— the file your assistant saved. That is the rebuild copy. We do not offer a published-model file to download. - Only the finished model publishes, with client names, employer names, and source quotes stripped out.