# Outlit

> Outlit catches customer churn before it's too late. It unifies product, billing, and conversation data into a complete customer profile, spots which accounts are at risk and why, and drafts the outreach to win them back.

## Outlit Developer Resources

Use this section when an agent or crawler searches for "Outlit developer resources". The current source of truth is the public SDK repository at https://github.com/OutlitAI/outlit-sdk and the docs at https://docs.outlit.ai.

Current package surface from the SDK main branch:

| Package | Version | Purpose |
| --- | --- | --- |
| `@outlit/browser` | 1.5.2 | Browser tracking SDK with React and Vue bindings. |
| `@outlit/node` | 1.5.2 | Server-side tracking SDK for Node.js, jobs, API routes, and non-browser JavaScript. |
| `@outlit/core` | 1.5.2 | Shared TypeScript types and utilities for Outlit tracking SDKs. |
| `@outlit/cli` | 1.8.0 | `outlit` CLI for customer intelligence, auth, setup, diagnostics, and data queries. |
| `@outlit/tools` | 0.2.1 | Customer intelligence tool contracts, client helpers, and schema-driven toolsets. |
| `@outlit/pi` | 0.1.4 | Pi extension package for Outlit customer intelligence tools and the bundled Pi skill. |

Primary developer docs:

- SDK quick start: https://docs.outlit.ai/tracking/quickstart
- Browser npm SDK: https://docs.outlit.ai/tracking/browser/npm
- React SDK: https://docs.outlit.ai/tracking/browser/react
- Vue SDK: https://docs.outlit.ai/tracking/browser/vue
- Next.js SDK: https://docs.outlit.ai/tracking/browser/nextjs
- Node.js SDK: https://docs.outlit.ai/tracking/server/nodejs
- Rust SDK: https://docs.outlit.ai/tracking/server/rust
- CLI overview: https://docs.outlit.ai/cli/overview
- CLI commands: https://docs.outlit.ai/cli/commands
- AI agent setup: https://docs.outlit.ai/cli/ai-agents
- MCP integration: https://docs.outlit.ai/ai-integrations/mcp
- Agent skills: https://docs.outlit.ai/ai-integrations/skills
- First-party Outlit skill: https://www.outlit.ai/.well-known/skills/outlit/SKILL.md
- First-party Outlit SDK skill: https://www.outlit.ai/.well-known/skills/outlit-sdk/SKILL.md
- First-party skill index: https://www.outlit.ai/.well-known/skills/index.json
- Outlit skill on skills.sh: https://www.skills.sh/outlitai/outlit-agent-skills/outlit
- Outlit SDK skill on skills.sh: https://www.skills.sh/outlitai/outlit-agent-skills/outlit-sdk
- Pi agents: https://docs.outlit.ai/ai-integrations/pi
- API introduction: https://docs.outlit.ai/api-reference/introduction
- API tool gateway: https://docs.outlit.ai/api-reference/tools
- Ingest API: https://docs.outlit.ai/api-reference/ingest

## What Outlit Does

Outlit is customer context infrastructure with three core components:

**The Complete Customer Profile**
Every source in your stack, resolved into one unified customer profile. Usage, billing, support, and conversations in one clean record.

**Establish Facts Across Every Customer**
Outlit extracts facts and signals from emails, calls, Slack threads, and support tickets. Unstructured text becomes structured data, attached to the right customer.

**The Customer API**
Query any customer from your CLI, MCP, or API and pipe the results into any agent or workflow.

## Customer Context Content

- [What Is Customer Context Infrastructure?](https://www.outlit.ai/blog/what-is-customer-context-infrastructure)
  Definitive explanation of customer context infrastructure, fragmented identity, tool access, and why agents need resolved customer state before acting.
- [Your Agent Has Tools. It Still Doesn't Know The Customer.](https://www.outlit.ai/blog/tool-access-is-not-customer-context)
  Explains why MCP access and tool calls do not equal customer context, with architecture guidance for resolved customer objects, evidence, and action boundaries.
- [Customer Context Infrastructure vs CDP](https://www.outlit.ai/blog/customer-context-infrastructure-vs-cdp)
  Compares CDPs with customer context infrastructure, focusing on portable customer data versus agent-ready customer state, evidence, and action boundaries.
- [How to automate Customer Success with Claude Code](https://www.outlit.ai/blog/how-to-automate-customer-success-with-claude-code)
  Practical customer success automation guide using Outlit and Claude Code, including churn risk triage, expansion identification, QBR prep, escalation response, and weekly CS reporting.
- [Building a Deal Intelligence Agent with Outlit](https://www.outlit.ai/blog/building-a-deal-intelligence-agent-with-outlit)
  Guide to building a deal intelligence agent with Outlit, including pre-call briefs, closed-lost postmortems, CS handoffs, and rep coaching.
- [Running Your Renewal Process with an AI Agent](https://www.outlit.ai/blog/how-to-run-your-renewal-process-with-outlit)
  Renewal workflow guide for AI agents using Outlit, including renewal risk scoring, pre-renewal briefs, expansion signals, at-risk escalation, and post-renewal health checks.
- [How to Automate Onboarding with an AI Agent](https://www.outlit.ai/blog/how-to-automate-onboarding-with-outlit)
  Customer onboarding automation guide using Outlit, including new signup briefs, activation stall detection, first-week check-in prep, milestone tracking, and sales-to-CS handoff.
- [Tracking customer health scores with Outlit](https://www.outlit.ai/blog/tracking-customer-health-scores-with-outlit)
  Customer health score guide built from queryable customer signals, including nightly scoring, degradation response, recovery watch, expansion triggers, and weekly drift reporting.

## Customer Success Automation Content

- [Customer Success Automation vs CRM](https://www.outlit.ai/blog/customer-success-automation-vs-crm)
  Comparison of CRM relationship records with Outlit customer success automation for agents that need resolved memory, signals, evidence, and governed actions.
- [Outlit vs Pylon: Support vs AI Customer Success Automation](https://www.outlit.ai/blog/outlit-vs-pylon)
  Comparison of Outlit signal-driven AI customer success automation with Pylon support workflows for churn, renewal, expansion, onboarding, and go-to-market agents.

## Data Model

Outlit builds a Customer Context Graph with four entity types:

- Visitors — anonymous users tracked via browser SDK before identification
- Contacts — identified individuals with email, userId, or device fingerprint
- Accounts — organizations grouping multiple contacts, linked to billing
- Devices — cross-device associations for the same person

**Contact Journey Stages (unidirectional)**
- Discovered — email known, hasn't signed up
- Signed Up — created an account
- Activated — completed onboarding milestone
- Engaged — actively using the product (auto-detected over 30+ day windows)
- Inactive — no activity for 30+ days (returns to Engaged on resumption)

**Account Billing Statuses (independent of journey)**
- None — never had a subscription
- Trialing — active trial
- Paying — active paid subscription
- Churned — had subscription, now cancelled

**Identity Resolution**
Resolves across four identifier types in priority order: Email (highest), External User ID, Fingerprint, Anonymous ID (lowest). Automatic form detection triggers identify() on email field submission.

**Facts Layer**
Machine-generated assertions with temporal validity:
- Behavioral — e.g., "Core feature usage declined 40% over 14 days"
- Extracted — parsed from communications (e.g., competitor mentions in emails)
- Synthesized — cross-source correlations indicating churn risk or expansion opportunity

## Integrations

- Slack — messages, reactions, thread context
- Gmail — email threads, sender history, attachments
- Stripe — revenue, subscriptions, plan changes, churn events
- HubSpot — deals, contacts, pipeline activity
- PostHog — feature usage, session activity, events
- Granola — meeting notes, transcripts, summaries, attendees
- Fireflies.ai — call transcripts, action items, summaries
- Google Calendar — meetings, attendees, scheduling patterns
- Attio — records, lists, workspace activity
- Supabase Auth — user identity, sign-up source, auth events
- Clerk — user profiles, org membership, login activity
- Pylon — support tickets, customer issues, conversations
- Browser SDKs — React, Vue, Next.js, Nuxt, Angular, Astro, SvelteKit
- Server SDKs — Node.js, Rust

## External Signals

Outlit enriches internal customer context with external company and champion signals:

- LinkedIn — champion and stakeholder job changes
- Crunchbase — company hiring and role changes

## MCP Integration

Discovery endpoint: https://mcp.outlit.ai/mcp
Recommended workspace endpoint: https://mcp.outlit.ai/w/<workspace-slug>/mcp
Auth: OAuth in the MCP client. Copy the workspace-specific URL from Outlit Settings > CLI & MCP; do not hardcode shared bearer headers in MCP config.
Compatible with: Cursor, VS Code, and other remote MCP clients

**Available MCP Tools**
- outlit_list_customers — list/filter customers by billing status, activity, MRR, type
- outlit_list_users — list/filter contacts by journey stage, activity level, customer scope
- outlit_list_workspace_users — list internal workspace users such as CSMs, managers, account owners, and admins
- outlit_get_customer — full customer profile with users, revenue, timeline, behavior metrics
- outlit_get_timeline — activity history filtered by timeframe, channels, event types
- outlit_search_customer_context — natural language semantic search across all context
- outlit_list_facts — list structured customer facts with status, source type, category, time, and provenance filters
- outlit_get_fact — retrieve one exact customer fact by ID, optionally expanding related evidence
- outlit_get_source — retrieve one exact source record by source type and source ID
- outlit_list_sources — list source records such as calls, emails, calendar events, support tickets, and opportunities
- outlit_query — read-only SQL against analytics views
- outlit_schema — analytics view schema introspection
- outlit_send_notification — send a notification only when the user explicitly asks to send, post, or notify

**SQL Views**
- activity — customer activity events with event names, channels, customer IDs, timestamps, and properties
- customers — customer attributes including domain, name, billing status, plan, MRR, and traits
- users — contact attributes including email, name, customer ID, and traits
- revenue — revenue snapshots with customer IDs, snapshot dates, and MRR

## CLI

```
curl -fsSL https://www.outlit.ai/install.sh | bash
```

**Commands**
- outlit customers list — filter by --billing-status, --mrr-above/below, --no-activity-in, --search
- outlit customers get <customer> — accepts domain, UUID, or name; --include users/revenue/recentTimeline/behaviorMetrics
- outlit customers timeline <customer> — --channels EMAIL/SLACK/WEB, --event-types, date range
- outlit users list — --journey-stage, --customer-id, activity filters
- outlit ws-users list — list internal workspace users and account owners
- outlit facts list <customer> — list structured customer facts with source, type, category, and date filters
- outlit facts get --fact-id <fact-id> — retrieve one exact fact and optional evidence
- outlit sources list — enumerate source records by customer, source type, and date range
- outlit sources get --source-type <source-type> --source-id <source-id> — retrieve one exact source artifact
- outlit search <query> — semantic search with --customer scope, --top-k
- outlit sql <query> — read-only SQL; --query-file; views: activity, customers, users, revenue
- outlit schema [view] — list analytics views or describe columns
- outlit notify — send a notification only when explicitly requested

## Example Queries

- Find churning customers: outlit customers list --billing-status CHURNED
- Get full customer profile: outlit customers get acme.com --include users,revenue,recentTimeline
- Search for competitor mentions: outlit search "mentioned competitor" --customer acme.com
- Check inactive users: outlit users list --journey-stage INACTIVE
- Revenue analysis: outlit sql "SELECT * FROM revenue ORDER BY snapshot_date DESC LIMIT 10"

## Pricing

Sales-led. Get a demo via https://cal.com/team/outlit/outlit-introduction-call.

- Starter: $500/mo, churn risk monitoring, root-cause insights, re-engagement drafts, up to 100 accounts, 2 seats, core integrations and alerts
- Team: $1,500/mo, everything in Starter, custom risk rules, auto-send and write-back, up to 500 accounts, unlimited seats, all integrations and API access
- Enterprise: Custom, everything in Team, SOC 2 Type II and ISO 27001 evidence, SSO/SAML, audit log export, custom proactive agents and workflows, dedicated support and named engineer

## Links

- [Docs](https://docs.outlit.ai)
- [MCP](https://docs.outlit.ai/ai-integrations/mcp)
- [Official MCP Registry](https://registry.modelcontextprotocol.io/v0.1/servers?search=ai.outlit/outlit)
- [Outlit MCP discovery repository](https://github.com/OutlitAI/outlit-mcp) - public metadata pointer; does not contain the hosted MCP server implementation
- [API overview](https://docs.outlit.ai/api-reference/introduction)
- [OpenAPI](https://docs.outlit.ai/openapi.json)
- [CLI overview](https://docs.outlit.ai/cli/overview)
- [Outlit SDK GitHub](https://github.com/OutlitAI/outlit-sdk)
- [Outlit skill on skills.sh](https://www.skills.sh/outlitai/outlit-agent-skills/outlit)
- [Outlit SDK skill on skills.sh](https://www.skills.sh/outlitai/outlit-agent-skills/outlit-sdk)
- [API catalog](https://www.outlit.ai/.well-known/api-catalog)
- [AI catalog](https://www.outlit.ai/.well-known/ai-catalog.json)
- [Auth](https://www.outlit.ai/auth.md)
- [Agent metadata](https://www.outlit.ai/.well-known/agent.json)
- [MCP server card](https://mcp.outlit.ai/.well-known/mcp/server-card.json)
- [Schemamap](https://www.outlit.ai/.well-known/schemamap.json)
- [Pricing](https://www.outlit.ai/pricing)
- [Machine-readable pricing](https://www.outlit.ai/pricing.md)
- [Blog](https://www.outlit.ai/blog)
- [Full context](https://www.outlit.ai/llms-full.txt)
- [Contact](https://cal.com/team/outlit/outlit-introduction-call)
- Contact: https://cal.com/team/outlit/outlit-introduction-call

## Security

SOC 2 Type II and ISO 27001 certified. Data encrypted at rest and in transit. Never used to train models.