A list of articles on how data teams built their analytics agents.
Recommended first reads · Internal builds · Browse by problem · Related reading · Contribute
- Anthropic — How a team makes self-service analytics work.Skills, metric definitions, documentation, and evaluations (Jun 2026), including how the team keeps them current as data models change.
- OpenAI — Inside an in-house data agent.The architecture behind context preparation, retrieval, permissions, and evaluations (Jan 2026).
- Ramp — Building one around an existing dbt project.SQL and Jinja examples for context tables and domain documentation (Oct 2025).
Read an article directly from the right column, or click a company for its full reading notes. Dates are publication dates; stacks reflect what the authors used at the time.
- Giving the agent context:Ramp ,Gorgias ,AngelList ,BlaBlaCar ,OpenAI .
- Testing answers and model changes:Gorgias ,Anthropic ,Ramp ,LinkedIn ,Uber .
- Fixing mistakes and keeping context current:GitHub ,Gorgias ,Replit .
- Reducing cost and latency:Gorgias ,Vercel .
- Getting people to use it:Alan ,Faire ,Ramp ,LinkedIn .
Product engineering, technical studies, and benchmarks that complement the internal builds.
Cube: Building an Agentic Analytics Harness ·Vendor implementation . Errors, result limits, and permission-aware tools.Stack and notes . #
Omni: Benchmarking Omni’s agentic analytics harness ·Vendor implementation . Testing quality, latency, and cost on a vendor’s analytics workload.Stack and notes . #
Cassis: A blank beats a guess ·Vendor implementation . Building the first context from existing data assets, with an open-source bootstrap kit.Stack and notes . #
Cassis: Context engineering for analytics agents ·Vendor implementation . How we structure tables, metrics, and business rules so an agent can find what it needs.Stack and notes . #
Benchouse: The Analytics Agent Benchmark ·Benchmark . Compare accuracy, completeness, restraint, and cost per question across analytics agents.Notes .
Know a team that has written up its internal build? Open an issue or pull request with the link and a sentence about what makes it useful. See the contribution guide for the format. Corrections and broken-link reports are welcome too.