Tools provided
Tools the agent exposes — your AI client calls them automatically when it needs them.
- run_full — Run the agent end-to-end: collect dashboard tiles, run deterministic analysis, synthesize a narrative summary + recommendations.
- summarize_dashboard — Summarize a dashboard into a narrative summary + recommendations (dashboard-first alias of run_full).
- analyze_dashboard — Run pure deterministic analysis (no LLM) over a provided dashboard export and return KPIs, findings, highlights, and confidence.
- get_kpis — Extract the deterministic KPI summary from a provided dashboard export.
- check_thresholds — Return only the threshold-breach and no-data findings from a provided dashboard export.
- list_capabilities — List the agent's static capabilities: tools, connector status, and credential slots.
- discover_intent — Understand your goal and co-design the exact input via clarifying questions before running.
- plan_inputs — Plan/brainstorm the inputs for a tool: returns the questions, schema and a ready-to-edit example.