Tools provided
Tools the agent exposes — your AI client calls them automatically when it needs them.
- run_full — Orchestrated path: score a provided competitor snapshot batch across all five signal categories and synthesize the weekly digest, ready for Slack or email.
- analyze — Run pure deterministic analysis over the provided snapshot batch with no model call and return the full scored findings across all five signals.
- analyze_pricing — Run the pricing signal alone and return the pricing finding per competitor. Any pricing-model change counts as significant on its own.
- analyze_product — Run the product signal alone and return the feature-launch finding per competitor.
- analyze_hiring — Run the hiring signal alone and return the job-postings-delta finding per competitor — a leading indicator of where a rival is investing.
- analyze_reviews — Run the reviews signal alone and return the G2 and Capterra rating-delta finding per competitor.
- analyze_changelog — Run the changelog signal alone and return the release-cadence finding per competitor.
- list_capabilities — List the agent's static capabilities: the available tools and the analyzer's signal-category 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 competitors to watch and the cadence. 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.
