Tools provided
Tools the agent exposes — your AI client calls them automatically when it needs them.
- run_full — Orchestrated path: run the beta program end-to-end — select participants, track invitations, summarise feedback, monitor usage — and return the program dashboard with the GA-readiness score and checklist.
- analyze — Run pure deterministic analysis over a provided program dataset with no model call and return the program report.
- select_participants — Select the beta participants from your candidate pool: opted in and above the activity threshold, ranked by engagement, capped at your target size.
- track_invites — Return the invitation funnel over the selected participants — eligible, contacted, sent, accepted, declined, pending and the acceptance rate.
- summarize_feedback — Summarise the collected feedback: averages, sentiment split, top themes and per-week rollups.
- score_ga_readiness — Compute the composite GA-readiness score and flag, the readiness checklist, the open-risk findings and the KPI row.
- list_capabilities — List the agent's static capabilities: the available tools and the analyzer's thresholds. 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 program name, target size, candidate pool, feedback and usage metrics. 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.
