Tools provided
Tools the agent exposes — your AI client calls them automatically when it needs them.
- run_full — Orchestrated path: model all three packaging scenarios over your provided usage, billing, competitor and CRM snapshot, simulate each one's per-customer invoice change and net revenue impact, and return the full model with the recommendation, risk findings and narrative.
- analyze — Run pure deterministic scenario scoring over a provided snapshot with no model call, returning one finding per scenario plus the CRM price-loss risk signal.
- model_scenarios — Model all three packaging scenarios and return each one's per-customer invoice change and net revenue impact.
- model_usage_based — Model only the usage-based scenario — pay-per-unit at a blended rate derived from your total revenue over total usage.
- model_tiered — Model only the tiered scenario — three usage bands, each flat-priced at the in-band median invoice.
- model_flat_overage — Model only the flat-plus-overage scenario — a low-usage-percentile base fee plus a competitor-informed overage rate.
- recommend_scenario — Return the deterministic recommendation: the scenario with the best net revenue that does not shrink revenue by more than 5%, with its full modelled result.
- assess_price_risk — Return only the commercial risk signal — what share of your lost deals cite price as the reason.
- list_capabilities — List the agent's static capabilities: the available tools and the three modelled packaging scenarios. 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 pricing question and an optional customer segment. 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.
