Tools provided
Tools the agent exposes — your AI client calls them automatically when it needs them.
- run_full — Orchestrated path: analyse the provided activation funnel end-to-end — find the biggest drop-off, corroborate it with masked session signals, and return the step-by-step funnel plus three ordered A/B test hypotheses.
- analyze — Run pure deterministic funnel analysis over a provided funnel with no model call: per-step drop-off, the biggest loss point and the ordered test hypotheses.
- compute_conversions — Compute per-step conversion and drop-off for the provided funnel and return the overall activation rate.
- find_biggest_dropoff — Find the single highest-loss transition in the provided funnel — the biggest drop-off step, with its severity.
- suggest_ab_tests — Propose up to three ranked A/B test hypotheses targeting the biggest drop-off, each with its expected lift.
- mask_session_signals — Mask the personal data in provided session-recording observations — redacts emails, phone numbers, long digit runs and IP addresses — available on its own, not just as part of a run.
- list_capabilities — List the agent's static capabilities: the available tools and the drop-off severity 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 funnel steps and any session-recording notes. 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.
