Let your AI check a real expert’s decisions
Professionals turn the decisions they have made, with their reasons, into a Decision Model. Add one to Claude, ChatGPT, or Cursor, and your AI reads it before it answers you.
What it looks like when it is working
You ask your usual AI app. It checks the expert’s model first, and says which past decision it is leaning on.
Example inside your AI app: an exchange avva wrote for a reference model
We're a 20-person Series A fintech. Our marketing site looks dated next to our two biggest competitors and the board keeps bringing it up. Do we redesign the brand or the site first?
Checked Ines’s Decision Model
Neither, in the way the board means it. Keep the name and the mark. Rewrite the homepage headline so it says what you do, for whom and the number you move; replace every illustration with a real screenshot; and move the site's type and color closer to the category leaders, not further away.
Why, and what would change it
Why. In finance, looking like a bank is what "safe" looks like, and that trust is free if you borrow it. What makes the competitors look newer is that they show their product and say one sharp sentence. Difference belongs in the sentence; a new logo spends the one design budget you have where no buyer is looking.
What would change this. If your buyer has changed — you now sell to CFOs where you sold to analysts — the mark may be telling the new buyer the product is for somebody else, and then the brand goes first. That is a change of audience, not of taste.
Outside this model. Nothing here about what the redesign should cost or how to run an agency relationship. This model covers what to change, what to copy on purpose, and what to leave alone.
See the technical outputWhat your AI gets back, for anyone wiring this up
Each tool call returns a verification packet: the published Decision Model plus instructions for applying it, never a finished answer. Your own AI does the reasoning.
- How they work
- The steps they take and what they do in the ordinary case, each line with the conditions it holds under. Returned first by about_expert, where the model has one.
- Their decisions
- The decisions they made, with what each one turned on where the record says. At full access, ordered against your situation.
- Pressures and their order
- The pressures in play, grouped by which tended to settle their cases. Fitted from the decisions and silent where the cases do not decide. Nobody ranks them by hand.
- Stop rules and what changes their answer
- Where they stop, checked first, and each condition under which they would decide differently.
- An output format
- Including a line for what the model was silent on, so silence is never returned as approval.
Five task tools: review before finalizing, red_flag_check as a cheap gate, expert_questions before an approach is locked, compare_options for A/B, about_expert for scope. Plus search and fetch, for browsing and citation.
What a Decision Model carries that your prompt does not
Your AI can argue either side of a trade-off. A Decision Model gives it one person’s decisions to go on.
- vs. a system prompt
- “You are a senior marketer” leaves your AI guessing. Here it reads what one person decided, routine cases included, and why.
- vs. a knowledge base
- A knowledge base holds facts. This adds one person’s choices and reasons, for cases they never saw.
- vs. a prompt you wrote once
- When the expert updates their model, your AI reads the new version the next time it asks. Your prompt keeps a short note on when to check it.
Where the order inside a model comes fromWhat it is fitted from, and where it stays silent
01
One decision reveals several contests
Where the expert gave a reason, a case records which pressures settled it and which lost, and nobody ranks anything by hand.
02
Pressures fall into groups
A paired-comparison fit on those contests groups the pressures by which tended to settle cases. Where they do not decide, the model says so and your AI weighs the collision itself.
03
Which case counts as nearest
A case built on pressures you do not have is about something else and is penalized in full, while extra pressures on your side cost little.
Every published rule carries the count of approved decisions behind it. What is kept, and what never reaches us, is in the Privacy Center.
Connecting takes one line
If you can add a link to Claude, ChatGPT, or Cursor, you can do this.
Choose a Decision Model
Read a sample of their decisions before you connect anything.
Try it free
Copy the link from their page into your AI app. No account. The trial gives your AI a smaller part of the model and 40 requests a day, per model.
Keep it on
Sign in for the complete model; a reference model answers in full either way. Add the short note, and your AI checks it on its own.
Your AI does the thinking, and avva runs no AI of its own
The expert builds it with their AI, you use it with yours. No second subscription.
- Their AIdrafts the model from the expert’s work. They approve every decision.
- avvastores the finished model and hands it over. It writes no answers.
- Your AIreads it before it answers you.
What to expect
- It is a standard link. MCP is how AI apps plug in outside tools; Claude, ChatGPT, and Cursor take it.
- The sources stay with the expert. avva receives only the decisions they approved, with names taken out by their own AI.
- Nobody is on the other end. The expert isn’t notified, and nothing you ask reaches a person.
- Coverage labels describe breadth, not accuracy. We publish no score for how often anybody is right.
- Gaps get named. Your AI says what the model had no view on.
Free during beta
No account and no card to try one, and avva charges nothing per request.