Tools provided
Tools the agent exposes — your AI client calls them automatically when it needs them.
- run_full — Orchestrated path: score adoption across your provided feature portfolio — reach, segment penetration, repeat-use and sunset flags — and return the full dashboard.
- analyze — Run pure deterministic adoption analysis over a provided portfolio with no model call and return scored per-feature findings.
- score_features — Return per-feature adoption metrics — reach, target-segment penetration, repeat-use, diagnosis and sunset flag — sorted worst-first.
- list_sunset_candidates — Return only the features flagged dead and recommended for sunset.
- summarize_adoption — Return portfolio-level totals: feature counts by diagnosis, averages and total attributed business impact.
- build_insights — Return the decision-support insights that separate a discovery and distribution gap from a value and retention gap.
- build_recommendations — Return the action-oriented recommendations — sunset, boost discovery or fix retention — per feature.
- build_adoption_report — Return the entire deterministic adoption dashboard — scores, totals, insights and recommendations — with no language model involved.
- list_capabilities — List the agent's static capabilities: the available tools and the adoption thresholds behind each diagnosis. Useful for discovery.
- plan_inputs — Plan the inputs for a tool: returns the clarifying questions, the JSON schema and a ready-to-edit example.
- discover_intent — Understand your goal and co-design the exact input through clarifying questions before running.
- open_form — Opens the guided form to collect the reporting period and your feature-usage records. The entry point for running the agent on your own data.
- run_form — Internal: invoked by the guided form when the user submits. Not for direct use.
