The decision model

What the decision model is

After your AI product finishes collecting, something important happens before the outcome appears. The AI evaluates what it learned. It makes a determination about this person: where they are, what they need, how ready they are, how strong a fit they are for what you do. That evaluation is the decision model.

The decision model is the hidden intelligence layer of your AI product. It turns a collection of answers into a structured verdict — and that verdict flows into every outcome the product generates.

Without a decision model, the AI produces an outcome that is informed by the conversation but not structured around a conclusion. With a decision model active, every outcome — Standard, Page, Advisor — is shaped by the AI's specific determination of who this person is and what they need.

Three modes

AI Judgement

The AI weighs the full conversation and makes a holistic call. There are no scored questions behind it — the evaluation is qualitative, contextual and AI-driven. The AI considers everything: confidence level, depth of answers, contradictions, signals the person may not have stated directly.

Use AI Judgement for advice, intake and other nuanced products where context matters more than a number. It needs no configuration. Each lead still gets a score: Claude gives every finished lead an AI fit score from 0 to 100.

AI Scorecard

The product's scored questions produce a score for each person, and that score gives them a consistent rating — low, medium or high. You don't set the points yourself: when you build a scorecard, assessment, diagnostic, audit, readiness check or quiz, Build with AI or Claude chooses the scored questions, the points for each answer and each question's weight.

Use AI Scorecard when you want to be able to say "this person rated high" and mean the same thing every time. It adds predictability without removing the AI's qualitative reasoning from the outcome.

Advanced Manual

Full control. You configure score thresholds, dimension weights, per-field score maps, and outcome labels explicitly. The AI uses this structured scoring to determine status, but the outcomes are still AI-generated — the scores inform the reasoning, they do not replace it with static pages.

Use Advanced Manual only when you have a specific segmentation requirement and are comfortable with the configuration. The default thresholds are: 0–39% = low, 40–69% = medium, 70–100% = high.

Decision objectives

The objective shapes what the decision model is trying to determine, and in turn shapes how the outcome is framed.

Lead Fit — evaluates how well this person fits your ideal client profile. The conclusion produced is a fit assessment: Low fit, Moderate fit, High fit. Use this for qualification products and lead capture tools.

Readiness — evaluates how ready this person is to act. Conclusions: Low readiness, Moderate readiness, High readiness. Use this for products where the key question is timing and preparedness.

Diagnosis — evaluates the health or strength of something the person is working on or within. Conclusions: Needs attention, Mixed signals, Strong baseline. Use this for diagnostic products and assessment tools.

Recommendation — evaluates the clarity of the next step this person should take. Conclusions: Needs guidance, Promising direction, Clear next step. Use this for advisory and strategy products.

Offer Match — evaluates how strongly this person's situation maps to a specific offer or engagement. Conclusions: Low offer match, Possible match, Strong offer match. Use this for products designed to qualify into a particular service.

Custom — define your own objective label and outcome labels. The AI will reason toward the objective you describe.

What the decision model produces

At the end of the collection phase, the decision model produces a DecisionResult for the person. When there's a score behind it, that includes:

• the overall status — low, medium or high
• the label for that status (your custom labels, or the defaults for the chosen objective)
• a short summary and a confidence level
• the full score context — total score, maximum possible score, percentage, a breakdown per scored question, and top strengths and gaps

A status and label are only given when there's a real score behind them. Without scored questions there's no status: the AI reasons about the person directly in the outcome, and the lead gets an AI fit score instead.

This result is passed to every connected Outcome. The Report uses it to shape the tone of the verdict, the emphasis of the breakdown, and the strength of the CTA. The Document uses it to frame recommendations. The Offer uses it to calibrate the pitch. Every outcome receives the full picture.

How status and confidence work

Status is straightforward: low, medium or high, from the person's score. The default cut-offs are 0–39% low, 40–69% medium and 70% and above high. It maps to the outcome labels you configure (or the defaults for your chosen objective). A lead rated high is a hot lead on the Leads page.

Confidence reflects how reliably the score was computed. It's based on how many scored questions the person answered: four or more gives high confidence, two or three medium, and fewer low. Higher confidence means the outcome can be more specific and more assertive.

Practical advice

For advice, intake and other nuanced products, AI Judgement is the right choice. It needs no configuration and handles nuance well, and Claude still gives every lead an AI fit score.

For scorecards, assessments, diagnostics, audits, readiness checks and quizzes, AI Scorecard is set up for you when the product is built, so every lead gets a consistent, explainable score.

Use Advanced Manual only when you have a specific requirement: a known scoring framework, a particular threshold you need to enforce, or a structured diagnostic where the dimension breakdown is itself part of the value delivered.