Introducing AI observability notebooks for Managed ClickStack in Private Preview

Summary

ClickHouse has launched AI Notebooks for Managed ClickStack in private preview to assist site reliability engineers during system investigations. Instead of isolating interactions in a standard chat window, the platform embeds Anthropic's Claude models directly into a cell-based notebook canvas. The system connects the model to internal ClickStack APIs, translating natural language questions into structured queries that leverage ClickHouse optimizations like materialized views and query chunking. Engineers can inspect reasoning, edit generated SQL queries, add manual visualizations, and branch investigations to evaluate multiple hypotheses independently. While currently utilizing a last-write-wins model for shared canvases, the roadmap includes true concurrent editing, customizable context, and external tool integration via an MCP server.

Context

Production debugging across logs, metrics, and traces is iterative and structured, yet isolated AI chat windows do not match how site reliability engineers investigate incidents. SREs need a transparent workspace that preserves investigation context, avoids hidden logic, and keeps engineers in control while validating intermediate reasoning and exploring alternative hypotheses.

Approach / What changed

Managed ClickStack launched AI Notebooks in private preview, embedding Anthropic's Claude models into a step-by-step canvas. The system connects the LLM to ClickStack internal APIs to run optimized queries, compute metrics, and generate charts against ClickHouse data. Investigations capture reasoning, queries, and manual cells in a visible sequence with branching capabilities and team-level access controls.

Takeaways

• AI Notebooks use Anthropic Claude models connected to internal ClickStack APIs that execute optimized ClickHouse queries, chunk scans, and utilize precomputed views.
• Engineers can branch investigations from any canvas cell, preserving independent hypotheses and lines of inquiry as a navigable tree rather than a transient chat history.
• The interface allows manual SQL editing, chart insertions, and note additions alongside AI-generated steps, with AI features togglable at the team level.

Related reading