recommend_improvements
Read-onlyIdempotent
Converts Stop or Fix AI initiative scores into concrete recommendations to achieve Accelerate classification. Provides pillar-level targets, named actions, and rationale for next steps.
Instructions
For an initiative classified Stop or Fix, return concrete, deterministic recommendations that would flip classification toward Accelerate. Pillar-level targets with named actions and rationale. Answers the "what do I do next" question after score_initiative. Pure deterministic calculation — no network, auth, or side effects.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| scores | Yes | ||
| ai_tier | Yes | gen1=automation/RPA, gen2=GenAI, gen3=agentic. | |
| function | Yes | Business function where the AI will operate. | |
| industry | Yes | Your industry. See list_taxonomy if unsure. | |
| readiness | Yes | Organisational readiness. Honest self-assessment. | |
| revenue_eur | Yes | Approximate annual revenue in EUR. |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| notes | Yes | Caveats or context on the recommendation set. | |
| feasible | Yes | Whether the target is reachable via the listed pillar moves. | |
| bvf_version | Yes | AI BVF protocol version used. | |
| recommendations | Yes | Per-pillar improvement actions. | |
| advisory_next_step | No | Optional CTA, present only for Fix/Stop verdicts. | |
| target_classification | Yes | Verdict the recommendations aim to reach. | |
| current_classification | Yes | Verdict as the initiative stands today. | |
| projected_decision_confidence | Yes | Confidence in the verdict if the recommendations land, 0-100. |