Agentic coding at ClickHouse

Summary

Industry perspectives on AI coding agents remain divided between dismissal and excessive automation claims. ClickHouse integrated agentic coding across internal workflows, progressing from simple boilerplate scripts to active backend C++ development. Engineers primarily use command-line agents such as Claude Code with Claude Opus 4.5 and Codex CLI alongside observability platforms like Langfuse and Librechat. While agents effectively investigate continuous integration logs, generate internal dashboards, and assist with small C++ tasks, they lack architectural competence and require rigorous code review. ClickHouse treats agents as pair programmers for contained tasks, retaining human ownership over product strategy, attention to detail, and core code quality.

Takeaways

1. 1

   CLI agents provide frontier capabilities—such as subagent orchestration, plan mode, clangd integration, and CI log parsing—making them preferable to IDE-integrated alternatives.

2. 2

   Frequent provider outages require engineering teams to maintain operational fallbacks across model providers, such as pairing Claude Code with Codex CLI.

3. 3

   Coding agents function effectively as pair programmers for well-scoped tasks but struggle with autonomous architectural decisions, demanding rigorous human code reviews.