Run AI Agents in TeamCity
Blog post from JetBrains
TeamCity’s experimental AI Agents plugin enables Codex and Claude Code to run within CI/CD builds for tasks such as reviewing code, investigating build failures, and updating documentation. It connects agents to providers including OpenAI, Anthropic, JetBrains Air, LiteLLM, and OpenRouter, installs the selected client on demand, and makes credentials available to build agents only for the duration of a build. The plugin also records token usage and agent trajectories, publishing statistics and HTML or JSON reports that teams can use to inspect individual runs or analyze behavior across builds. Setup involves creating a provider connection, adding the AI Agent build feature, and invoking the agent from a command-line step; because generated artifacts may include prompts, source code, and model outputs, access to them should be restricted. The plugin is available through JetBrains Marketplace, and its features may change as development continues.
| Trend | Post Mentions | Total Month Mentions | Posts | Companies | MoM |
|---|---|---|---|---|---|
| AI Agents | 7 | 4,689 | 923 | 218 | -33% |
| LLM | 3 | 2,788 | 618 | 179 | -58% |
| AI Coding Assistant | 1 | 1,395 | 336 | 123 | -29% |
Use this post, company, and trend context to find content marketing opportunities, perform competitive analysis, or address product feature gaps via the Plushcap MCP server or the Plushcap API.