Live demo
Ask real questions of real data, right inside Claude.ChatGPT.Claude Code.Claude Cowork.Cursor.Codex.
Connect Agami to the AI tool you already use and ask in plain English. Or wire it into an agentic platform for autonomous workflows on the same governed data.
Get started
Two steps to your first answer.
Works in any MCP-capable assistant, including Gemini, Cursor, and Claude Code.
- 1
Add Agami to your assistant
Open Connectors, choose Add custom connector, name it Agami, and paste the demo URL.
See detailed connection guides →https://public.agami.ai/mcp - 2
Connect and sign in
Click Connect, sign in with Google or Microsoft, and pick the demo dataset. You're returned to your assistant, now connected.
Ask away
Ask in plain English. Agami returns the answer, a chart, and the SQL it ran, so you can always check the work.
Stuck or want a hand getting set up? Talk to a founder, we’ll help you connect.
What's in the demo
Pick something to explore.
What it contains, where it came from, and the kinds of questions it answers.
California Schools
Real California education data, from K-12 census to UC admissions.
Postgres 
BigQuery “Which California high schools sent the most admits to UC Berkeley last year, and what are the poverty rates at those feeder schools?”
SaaS Benchmark
Benchmark SaaS metrics across hundreds of public and private companies.
BigQuery Postgres F500 Data
Enterprise ITSM and CRM for a Fortune 500 company.
Redshift Postgres AI Native Startup
Go-to-market, product, and finance data for an AI-native SaaS startup.
Databricks Works where you already work
Connect the tool you already use.
Agami speaks MCP, so it plugs into the tools you already use. Pick yours for a setup guide.
What is Agami
The trust layer between your AI tools and your data.
Anyone in your business asks a question in plain language and gets an answer they can trust. Your data team owns the semantic layer underneath: the definitions, the joins, the rules. Agami turns that into governed answers and shows the query behind every one.
metric arr = SUM(mrr) × 12
grain account · fx usd
filters account_is_deleted = FALSE
account_is_deactivated = FALSE
account_is_test = FALSE
segments region · product_line · tier
vetted_by John Smith · 2026-03-15
→ Q2 ARR pacing +14% above plan.
NA $42.8M · EMEA $31.2M · APAC $18.6M
Ask in plain English
No SQL, no dashboards to hunt through. Just ask like you would a colleague.
Get a governed answer
Your assistant writes SQL against a curated semantic model, so numbers match how your team defines them.
See the work
Every answer comes with a chart, a short read on what it means, and a few follow-ups.
Join across sources
Ask questions that span datasources in one breath; the agent bridges them like an analyst would.
A note on AI and accuracy.
Agami uses AI to turn questions into queries, and AI can make mistakes, so check important numbers (the SQL is shown for every answer). This demo uses public data only; please don't enter anything confidential. Provided as-is for evaluation, with no warranty. By using it you agree to our Terms of Service and Privacy Policy.
Ready to ask your first question?
The demo is free and takes a few minutes to set up.