Tools provided
Tools the agent exposes — your AI client calls them automatically when it needs them.
- run_full — Orchestrated path: score and tier the prospects you provide, draft a personalised outreach email for each, and return the full ranked result with its guardrail warnings.
- analyze — Run pure deterministic scoring over the provided prospect list with no model call and return the scored findings.
- score_prospects — Return the full scored prospect list — domain, rating, traffic, relevance, outreach score, tier, contact and draft — best first.
- draft_emails — Draft a personalised outreach email per prospect and return them with the contact. Drafts only — nothing is ever sent.
- tier_prospects — Return the compact triage view — domain, outreach score and tier, best first — for deciding who to contact first.
- list_capabilities — List the agent's static capabilities: the available tools and the scoring model, including the weights and the tier 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 topic, the competitor domains and how many prospects to return. The entry point for running the agent on your own list.
- run_form — Internal: invoked by the guided form when the user submits. Not for direct use.