Embedded GenBI
Ship conversational analytics inside your product.
Embed Wren's governed data agent, white-label, through Threads, APIs, or MCP, on any of 20+ databases. One context layer governs every answer. Your brand, your policies, live in days.
- Embedded Threads
- AI API
- MCP
- Slack and Teams
Trusted by data teams worldwide, with 17,925 GitHub stars
Live demos · Inside a real product
Your users ask. Your platform answers.
Four working products with Wren AI embedded where the work happens. Each one answers from live tables, in the host’s brand, scoped to whoever is signed in. Pick an industry and try it.
Explain what moved a stock, right next to the chart.
A governed analyst panel lives inside a stock-watch app. It answers from the same daily prices, volume, analyst ratings, and news events behind the dashboard, and knows which symbol and timeframe the investor is looking at.
Scoped to Signed-in investor, their watchlist, and the chart on screen
Try asking in the demo
- “Which stocks in my watchlist gained the most over the past year?”Prices
- “Which news events moved Costco the most?”News
- “Is COST’s trading volume unusual compared to its 30-session average?”Volume
Sample product and data, for illustration only. Answers are read-only and describe what already happened; Wren AI does not place trades or give investment advice.
Embedded Threads docsWhite-label
Match your colors and logo so analytics feels native to your product.
Embedded Threads
Conversational analytics in your app, in an afternoon.
Embed the full Wren AI thread experience with an iframe. Your users explore their own data in plain language without leaving your product, and every answer stays inside your governance boundary.
Embedded AI API
Your UX on top. Wren's data agent underneath.
Two endpoint families cover the whole loop: natural language to SQL with execution, and chart generation as Vega-Lite specs. Conversation context carries across follow-up questions.
MCP, Slack and Teams
Meet your users in the tools they already open.
Wren AI speaks MCP natively and ships Slack and Teams integrations. Agents and teammates query through the same definitions your product embeds; nobody touches raw tables.
Multi-tenant by design
Every tenant sees exactly what they should. Provably.
Embedding analytics means putting your customers' trust on the line. Wren AI enforces the boundary in the engine, not in your application code.
- sessionjwt.verify(HS256)valid
- tenantsolstice, user 4821scoped
- policyrow_level = tenant_idapplied
- policycolumn_mask(email)applied
- auditq_8f21, 1 row returnedlogged
Signed JWTs
Your backend signs every embedded session with a shared secret. The key never reaches the browser.
Row-level and column-level controls
Access policies are enforced inside the engine at query time, per end user.
Full activity logs
Provable who asked what, and which query produced which number.
Projects and per-app tokens
Separate tenants by project. Issue one API token per surface and revoke it independently.
Months to build. Days to embed.
Building an enterprise-grade text-to-SQL context layer in-house takes months of engineering and constant maintenance. See how much you save on development cycles and cloud margins by embedding Wren AI.
