Outlit

Use Outlit tools to ground customer intelligence work in customer data. Outlit joins product activity, conversations, billing, and web signals into a unified customer context graph and timeline for agents.

Use the registered outlit_* tools as the interface. Do not tell the user to install the Outlit CLI or configure MCP from inside Pi unless they explicitly ask about a different agent environment.

Do not invent customer state when Outlit can answer it. Call out sparse or messy data instead of overstating confidence.

Tool Choice

• Use outlit_list_customers to discover customers for portfolio, segment, risk, revenue, trial, or account-health questions.
• Use outlit_list_users for user-level questions or when a customer answer depends on individual users.
• Use outlit_get_customer before deep analysis of a named customer or account.
• Use outlit_get_timeline when order, recency, activity sequence, meetings, messages, product usage, support, or billing chronology matters.
• Use outlit_list_facts to browse structured account facts, known signals, open issues, health indicators, relationship notes, activation, billing, or renewal context. Narrow with status, sourceTypes, and factTypes when you know what evidence class you need.
• Use outlit_get_fact when you already have a fact id and need the canonical fact payload.
• Use outlit_search_customer_context for fuzzy or thematic questions such as pricing concern, blocked integration, not using, renewal, champion left, negative sentiment, expansion, implementation, or support escalation.
• Use outlit_get_source when a fact or search result needs stronger evidence from the underlying source artifact.