Agentic AI
I have been building an agentic analytics platform for ClickHouse that allows you to define and run your own intelligent agents against your data. Agents can perform on demand analysis, run on a schedule, respond to events, and send alerts when they detect anomalies. It is designed to make agentic analytics on ClickHouse quick to stand up and easy to govern.
Latest Thinking On ClickHouse and Agentic AI
Why ClickHouse Is The Best Data Platform For Agentic AI
A deeper look at why ClickHouse is uniquely well suited to the concurrency, freshness and price/performance demands of AI workloads.
What Do We Mean By Agentic Analytics
Agentic analytics is much more than text to SQL. Planning, decomposition and iteration unlock investigations that a single query could never answer.
Using Open Source and Open Weight LLMs With ClickHouse
How to combine open source and open weight models such as GLM, DeepSeek and Kimi with ClickHouse, using third party inference providers like Fireworks.ai and Baseten.
Self Hosting An Open Source Model With ClickHouse
A walkthrough of self hosting an open source model on modest hardware, connecting it to ClickHouse, and the benefits around data locality, cost and privacy.
The Agentic Data Stack
ClickHouse, the ClickHouse MCP server and LibreChat combine into an integrated agentic data stack for building conversational analytics and agent teams.
Deploying Agentic Analytics In Financial Services
How capital markets and banking teams can move beyond dashboards into scenario modelling, strategy development and trade surveillance with agentic analytics.
Using Gemini and Claude For SQL Analytics — A Bake Off
A head to head bake off of Claude and Gemini generating analytical SQL against a ClickHouse database.
Building Agentic AI On ClickHouse?
Whether you are exploring your first agentic analytics prototype or scaling an existing deployment, get in touch to discuss how ClickHouse can sit at the centre of your AI strategy.
Get In Touch