Product guidance, technical deep dives, and customer lessons for building trusted analytics on your data.
At OpenAI's Data Agent launch, almost nobody asked about the agent. Every question was about the layer between the agent and the answer: context, governance, reproducibility. Here's why that layer, not the model, decides whether the number is right.
At OpenAI's Data Agent launch, almost nobody asked about the agent. Every question was about the layer between the agent and the answer: context, governance, reproducibility. Here's why that layer, not the model, decides whether the number is right.
Git Sync moves your open-source Wren project, the MDL semantic model, and the knowledge that makes answers correct into Wren Cloud as plain YAML and Markdown files in a git repository you own.
Wren AI Cloud is now 16× cheaper and 37% faster per task, with accuracy holding at 95% of evaluation assertions passed — GPT-5.6 Luna is the new default model. Here's what we measured before flipping the switch.
At OpenAI's Data Agent launch, almost nobody asked about the agent. Every question was about the layer between the agent and the answer: context, governance, reproducibility. Here's why that layer, not the model, decides whether the number is right.
Git Sync moves your open-source Wren project, the MDL semantic model, and the knowledge that makes answers correct into Wren Cloud as plain YAML and Markdown files in a git repository you own.
Wren AI Cloud is now 16× cheaper and 37% faster per task, with accuracy holding at 95% of evaluation assertions passed — GPT-5.6 Luna is the new default model. Here's what we measured before flipping the switch.
The Gallery is a growing library of real dashboards and reports built by the Wren AI agent from a single prompt. Open any example to see the exact prompt and every step behind it, then point the same template at your own warehouse.
Wren AI is now listed on Microsoft Marketplace. Ask a question in plain language inside a Teams chat or channel and get the answer in-thread, with the SQL and a chart, resolved against the same context layer every other surface uses.
Wren AI is now listed in the Claude Directory. Add the connector inside Claude, authorize with OAuth, and Claude asks questions of your context layer instead of your raw schema, with row-level security and a full audit trail at query time.
For twenty years we treated the dashboard as the deliverable, but the durable asset was always underneath it: what your numbers actually mean. Dashboards depreciate. Context compounds.
Databricks turned the Genie meter on, and agents get no free tier. Why full autonomy makes an agnostic GenBI layer, any model on any platform, the whole decision.
An AI agent that answers business questions has to be debuggable and measurable, or 'earned trust' is just a slogan. How thread tracing, benchmarks, and the AI Advisor close the loop.