# Brizz Documentation

> Brizz is the product analytics layer for AI agents — trace every conversation, measure response quality, surface failure patterns, and tie agent behavior to product outcomes.

## Introduction
- [Welcome to Brizz](https://docs.brizz.ai/docs/introduction.md): Brizz is the analytics layer for AI agents. Capture every interaction, measure quality, and connect agent behavior to product outcomes.
- [Core concepts](https://docs.brizz.ai/docs/introduction/concepts.md): A short mental model for Brizz: trace, span, session, event, user, issue, intent, journey.

## Get started
- [Install the SDK](https://docs.brizz.ai/docs/get-started/install.md): Install the Brizz SDK in your Python or Node.js project.
- [Send your first session](https://docs.brizz.ai/docs/get-started/first-session.md): Initialize the Brizz SDK and capture your first session.
- [Verify it landed](https://docs.brizz.ai/docs/get-started/verify.md): Confirm your first session arrived in the Brizz dashboard, and what to do if it didn't.
- [Next steps](https://docs.brizz.ai/docs/get-started/next-steps.md): Where to go after your first session lands — identify users, send events, plug in a framework, explore the dashboard.

## SDKs
- [Choose your SDK](https://docs.brizz.ai/docs/sdks.md): Pick your runtime, then check whether the framework you're using needs explicit wiring.
- [Python SDK](https://docs.brizz.ai/docs/sdks/python.md): Install, initialize, and add sessions/events in Python.
- [TypeScript/Node.js SDK](https://docs.brizz.ai/docs/sdks/typescript.md): Instrument AI libraries in Node.js and emit sessions/events.
- [Browser](https://docs.brizz.ai/docs/sdks/browser.md): Capture product events from a web frontend with @brizz/browser and correlate them with the same backend agent session.
- [LangChain (JavaScript)](https://docs.brizz.ai/docs/sdks/langchain-js.md): Install Brizz alongside LangChain JS and add session tracking.
- [Vercel AI SDK](https://docs.brizz.ai/docs/sdks/vercel-ai.md): Install Brizz alongside the Vercel AI SDK and tag sessions.
- [Vercel eve](https://docs.brizz.ai/docs/sdks/vercel-eve.md): Install Brizz alongside Vercel's eve framework and wire up your DSN.
- [Google GenAI (Gemini)](https://docs.brizz.ai/docs/sdks/google-genai.md): Install Brizz alongside Google's @google/genai SDK — Gemini on Vertex AI or the Gemini Developer API.
- [Agno](https://docs.brizz.ai/docs/sdks/agno.md): Install Brizz with the Agno agent framework.
- [Strands Agents](https://docs.brizz.ai/docs/sdks/strands-agents.md): Install Brizz with the Strands Agents framework.
- [LiveKit Agents](https://docs.brizz.ai/docs/sdks/livekit-agents.md): Install Brizz with the LiveKit Agents voice framework.
- [Claude Code](https://docs.brizz.ai/docs/sdks/claude-code.md): Instrument Claude Code with Brizz using settings.json or environment variables.
- [MCP (auto-instrument your server)](https://docs.brizz.ai/docs/sdks/mcp.md): Add Brizz observability to an MCP server you operate, in Python (FastMCP) or TypeScript.
- [Langfuse SDK](https://docs.brizz.ai/docs/sdks/langfuse.md): Instrument your assistant with Langfuse and let Brizz ingest the OTel spans.

## Instrument
- [Identify users](https://docs.brizz.ai/docs/instrument/identify-users.md): Attach a user identity to your telemetry to unlock user-level analytics and insights.
- [Identify organizations](https://docs.brizz.ai/docs/instrument/identify-organizations.md): Attach the account, workspace, or tenant a user belongs to for org-level analytics.
- [Message IDs](https://docs.brizz.ai/docs/instrument/message-ids.md): Tag individual replies with your own id so you can reference them later — for example, to attach feedback.
- [Custom events](https://docs.brizz.ai/docs/instrument/custom-events.md): Emit custom events to track product actions, business outcomes, and feedback signals.
- [Sessions](https://docs.brizz.ai/docs/instrument/sessions.md): Capture sessions from your code — the primary unit of analysis in Brizz.
- [External links](https://docs.brizz.ai/docs/instrument/external-links.md): Attach an external URL — a Datadog trace, Sentry issue, or internal dashboard — to a Brizz session.
- [User Feedback](https://docs.brizz.ai/docs/instrument/user-feedback.md): Collect user feedback on AI responses, map it to system events, and filter sessions by sentiment.
- [Record feedback](https://docs.brizz.ai/docs/instrument/record-feedback.md): Capture an end-user reaction to a specific reply — a thumbs-up/down, a rating, a reason — as a structured brizz.feedback event. Note: it emits telemetry only, and does not yet drive the session feedback badges, Positive/Negative filters, or the Feedback Ratio chart — those need the system-event mapping on the User feedback page.
- [Record metrics](https://docs.brizz.ai/docs/instrument/record-metric.md): Report a numeric measurement your own system produced about an interaction — an eval score, a rating, a latency — as a first-class metric.
- [Online evaluation](https://docs.brizz.ai/docs/instrument/record-metric/online-evaluation.md): Record a metric from inside the agent, during the session it describes — it attaches to that session automatically.
- [Offline evaluation](https://docs.brizz.ai/docs/instrument/record-metric/offline-evaluation.md): Score conversations after the fact, or from a separate process — one eval job reporting metrics for many services, identifying each conversation by session id or trace id.
- [PII & Privacy](https://docs.brizz.ai/docs/instrument/pii-and-privacy.md): Protect sensitive data with masking and safe integration patterns.
- [Mute messages](https://docs.brizz.ai/docs/instrument/mute.md): Keep internal or unrelated LLM calls out of the captured conversation, so Brizz shows exactly what your users saw.
- [Subagents](https://docs.brizz.ai/docs/instrument/subagents.md): Mark a block of code as a subagent so its work shows as its own lane in the conversation instead of mixing into the main transcript.

## Platform
- [Platform](https://docs.brizz.ai/docs/platform.md): A map of the Brizz dashboard — where to start, and what every page is for.
- [Overview](https://docs.brizz.ai/docs/platform/overview.md): Your tenant's home page — a single-screen read on agent health, top problems, and emerging behavior.
- [Issues](https://docs.brizz.ai/docs/platform/issues.md): Deduplicated problems detected across your agent's traffic — technical failures, capability gaps, behavioral problems — each with a status (open/tracked/ignored/resolved) and a priority (critical/high/medium/low).
- [Sessions](https://docs.brizz.ai/docs/platform/observe/sessions.md): Read the sessions you've captured — timeline, filters, replays, and conversation context.
- [Users](https://docs.brizz.ai/docs/platform/observe/users.md): Per-user analytics — one row per identified end user, with activity, cost, and session metrics.
- [Organizations](https://docs.brizz.ai/docs/platform/observe/organizations.md): Per-organization analytics for B2B agents — engagement, retention, and cost rolled up per account.
- [User intents](https://docs.brizz.ai/docs/platform/analyze/user-intents.md): Semantic clusters of user prompts — what your users are actually asking for, grouped automatically.
- [User journeys](https://docs.brizz.ai/docs/platform/analyze/user-journeys.md): Common paths users take through your agent — aggregated flow patterns, not single sessions.
- [Classifications](https://docs.brizz.ai/docs/platform/analyze/classifications.md): Dimensions you define yourself — a set of categories, and an LLM that sorts every session, trace, or issue into them.
- [Dashboards](https://docs.brizz.ai/docs/platform/dashboards.md): The dashboard tabs — what they share, how to scope them, and which tab answers which question.
- [Performance](https://docs.brizz.ai/docs/platform/dashboards/performance.md): A system-health view of your agent — session volumes, error rates, and cost over time.
- [Latency](https://docs.brizz.ai/docs/platform/dashboards/latency.md): Where the time goes in a turn — response times, time-to-first-response, and turns per session.
- [Leaderboard](https://docs.brizz.ai/docs/platform/dashboards/leaderboard.md): Rank users, organizations, and segments by activity, cost, satisfaction, outcomes, and more.
- [Cost](https://docs.brizz.ai/docs/platform/dashboards/cost.md): The Cost dashboard — LLM spend over time, broken down by model, user, organization, and billing component, plus the most expensive sessions and per-tool token volume.
- [How cost is computed](https://docs.brizz.ai/docs/platform/dashboards/cost-calculation.md): How Brizz computes and displays the cost of each session.
- [Tools](https://docs.brizz.ai/docs/platform/dashboards/tools.md): Per-tool dashboard — call volume, run time, error rate, the issues each tool is involved in, and the satisfaction and estimated token volume of the sessions that use it.
- [Custom dashboards](https://docs.brizz.ai/docs/platform/dashboards/custom-dashboards.md): Build your own dashboards — named boards of charts and filtered session lists, scoped to a trace service and shared with your team.
- [Custom charts](https://docs.brizz.ai/docs/platform/dashboards/custom-charts.md): Build charts over your telemetry — pick a dataset, a metric, a chart type, and how to group and filter it.
- [Subagents](https://docs.brizz.ai/docs/platform/dashboards/subagents.md): Compare delegated agents by issues, tool failures, orchestration, run volume, and duration.
- [Skills](https://docs.brizz.ai/docs/platform/skills.md): Inventory the skills your agent loads, then compare their usage, completion, cost, hand-offs, reloads, and tool failures.
- [Labels](https://docs.brizz.ai/docs/platform/labels.md): Categorize sessions and other entities — manually, by rule, or with AI — then filter and group your analytics by them.
- [External metrics](https://docs.brizz.ai/docs/platform/external-metrics.md): Bring your own scores into Brizz — eval results, ratings, latencies — and filter and slice sessions by them.
- [Notifications](https://docs.brizz.ai/docs/platform/notifications.md): Deliver digests, alerts, and AI summaries to Slack or Email — built through a wizard, delivered on a schedule.
- [AI assistant](https://docs.brizz.ai/docs/platform/ai-assistant.md): Ask Brizz in plain language — about your own telemetry and about the product itself — and get answers with inline charts, clickable entity cards, and downloadable CSV or JSON reports.

## Integrations
- [Slack Integration](https://docs.brizz.ai/docs/integrations/slack.md): Ask the Brizz agent questions and receive alerts and reports in Slack
- [Issue trackers](https://docs.brizz.ai/docs/integrations/issue-trackers.md): Connect Jira, Linear, or Monday so a Brizz issue becomes a ticket in the tracker your team already works from.
- [Jira Integration](https://docs.brizz.ai/docs/integrations/jira.md): Connect Brizz to Jira to create and track issues found by Brizz directly from your Jira workspace.
- [Segment Integration](https://docs.brizz.ai/docs/integrations/segment.md): Send Segment events to Brizz for observability alongside your AI agent traces
- [MCP server (connect Brizz to your AI tools)](https://docs.brizz.ai/docs/integrations/mcp-server/overview.md): Expose Brizz as an MCP server so Claude Code, Claude Desktop, Cursor, Codex, and other AI agents can query your data.
- [MCP server tools](https://docs.brizz.ai/docs/integrations/mcp-server/tools.md): Every tool the Brizz MCP server exposes — name, what it does, required scope, and full arguments — in one page.

## CLI
- [Brizz CLI](https://docs.brizz.ai/docs/cli.md): Install and authenticate the brizz CLI — read sessions, issues, intents, and metrics from the terminal, and hand structured investigations to an AI coding agent.

## Admin
- [Server DSN](https://docs.brizz.ai/docs/admin/server-dsn.md): Authenticate an SDK with a single connection string that carries the credential, the ingestion endpoint, and the service name.
- [API keys](https://docs.brizz.ai/docs/admin/api-keys.md): Create, store, and rotate the API keys your SDKs and integrations use to authenticate to Brizz.
- [JumpCloud SSO (SAML)](https://docs.brizz.ai/docs/admin/sso-jumpcloud.md): Configure JumpCloud as a SAML 2.0 identity provider for Brizz
- [Organization & members](https://docs.brizz.ai/docs/admin/organization-and-members.md): Your organization's identity, the people in it, and the role each person holds.
- [Plan & billing](https://docs.brizz.ai/docs/admin/plan-and-billing.md): Your subscription plan and tier, and how plan limits surface across the product.
- [Audit logs](https://docs.brizz.ai/docs/admin/audit-logs.md): The audit trail of administrative and security-relevant actions taken in your tenant.
- [Data controls](https://docs.brizz.ai/docs/admin/data-controls.md): Tenant-level controls over what enters your analytics — a blocklist to exclude activity, and bulk import.
- [Services & configuration](https://docs.brizz.ai/docs/admin/services-and-configuration.md): The AI services configured for your tenant, and the per-service settings that control each one.
- [Labeler instances](https://docs.brizz.ai/docs/admin/labeler-instances.md): Configure the automatic labelers that classify your telemetry — which labeler runs, on what scope, and which label it writes into.
- [Projects](https://docs.brizz.ai/docs/admin/projects.md): Group services into projects and restrict which people see them on the project-aware, service-scoped pages.

## API reference
- [API Overview](https://docs.brizz.ai/docs/api/overview.md): Overview of the Brizz REST API
- [Telemetry ingestion](https://docs.brizz.ai/docs/api/telemetry.md): Low-level HTTP endpoints for sending traces and events to Brizz.
- [Reading data](https://docs.brizz.ai/docs/api/reading-data.md): Fetch sessions, transcripts, traces, spans, and analysis results back out of Brizz over HTTP.
- [Outbound webhooks](https://docs.brizz.ai/docs/api/webhooks.md): Receive an HTTP callback when a session or trace matures, signed with the Standard Webhooks spec.

## Help
- [Troubleshooting](https://docs.brizz.ai/docs/help/troubleshooting.md): Fix common setup and ingestion issues quickly.
- [Glossary](https://docs.brizz.ai/docs/help/glossary.md): Alphabetical reference for terms used throughout the Brizz docs.

## Optional
- [Full documentation (single file)](https://docs.brizz.ai/llms-full.txt): Every page concatenated into one file — fetch when you want the entire corpus at once.