Tools provided
Tools the agent exposes — your AI client calls them automatically when it needs them.
- run_full — Orchestrated path: turn your provided research data into a sourced research brief — findings, opportunity hypotheses and a narrative. With no data it opens the form; with only a domain name the brief is explicitly flagged as simulated.
- analyze — Run pure deterministic analysis over your provided research object with no model call and return scored, source-checked findings.
- find_complaint_themes — Return only the forum and review-site complaint themes, severity-scored by mention volume.
- list_entry_barriers — Return only the entry-barrier and regulatory-constraint findings.
- derive_opportunities — Derive opportunity hypotheses by crossing the loudest complaints against thin player coverage. Each one traces to a source — never invented.
- estimate_market_size — Return the sourced market-size estimate on its own.
- map_players — Return the competitive player map on its own.
- list_capabilities — List the agent's static capabilities: the available tools and the sourcing guardrails. 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 problem domain and your research data. The entry point for running the agent on your own material.
- run_form — Internal: invoked by the guided form when the user submits. Not for direct use.
