Keep pulling the thread on Kun Chen.
Kun Chen developed a tool called "No Mistakes" that automates the code validation and pull request process, including code review, testing, documentation updates, and risk assessment.
Kun Chen claims that using a fresh context window for an AI agent to review code is more effective at catching edge cases, as an agent reviewing in the same session it wrote the code is biased towards believing its work is correct.
Kun Chen stated that he typically has at least 5 different sessions actively running, with an average of 20 to 30 AI agents working in total.
Kun Chen stated that he generates 20 to 40 pull requests per day using his AI agent-assisted workflow.
Linear integrates directly with agent coding tools such as Cursor and Codex.
Product teams at OpenAI, RAMP, and Block use Linear to collaborate with AI agents.
Kun Chen built a visual editor tool called Lavish that uses HTML to facilitate interactive planning and collaboration between a human and an AI agent.
Kun Chen found that using HTML as an output format for AI agents is more effective than Markdown for human-agent collaboration because it can support richer, more interactive artifacts.
Kun Chen built a tool called Treehouse to simplify the management of git worktrees by automatically setting up new workspaces from a managed pool where dependencies are pre-installed.
Kun Chen asserts that most current AI models are not proficient at proactively using subagents, with exceptions like Claude Code or Codex which may use a built-in "Explore" subagent for complex codebase questions.
Kun Chen stated that the primary reason to use subagents is to prevent the context window of the main agent session from becoming too large, especially for isolated investigation or experimentation tasks.
The ProgramBench benchmark, created by the developers of SWE-Bench, evaluates AI agents by tasking them with building complex programs like FFmpeg from scratch.