Create a specialized AI agent to automatically investigate and triage bug reports from Sentry. This harness uses the Claude Agent SDK to gather evidence, identify root causes, and generate actionable engineering reports.
Before coding, map out the system components. Plan for a frontend (e.g., a Terminal UI with Ink), a core built on the Claude Agent SDK, specific tool adapters for APIs like Sentry and Linear, and a file-based artifact store for saving investigation results.
Use a large language model like Claude or Codex to help generate the initial code structure. Be specific in your request, detailing the desired SDK and workflow to ensure the AI creates an agentic system, not just a simple script.
Help me build a harness. I want to use the Claude Agent SDK to triage Sentry bugs. Here's the workflow I want it to follow.Create small, focused modules that connect to your tools (Sentry, Linear, GitHub) in a very specific way. Instead of general API access, build functions that pull only the exact data needed for bug triage, making the agent's job faster and more reliable.
Write a highly specific system prompt for your agent. This prompt should be encoded directly into the harness to set the context, define the task's scope, and clarify the expected output every time the agent runs.
you are working inside the chat purity engineering harness. It's chat, be specific. It's not an open-ended coding system we wanna use. These artifacts as a source of truth. And here's the plan to attack a very specific problem. And what I want you to return is X, Y, and Z.Build a simple, developer-friendly interface to run the harness. A command-line or terminal UI (TUI) built with a library like Ink (for Node.js) is an effective way to kick off investigations by simply pasting a Sentry link.
Execute the harness with a specific bug report link. Once the run is complete, review the generated artifacts in the designated folder. The key output should be a structured 'investigation brief' summarizing the findings.
Use an AI agent with browsing capabilities to automate the tedious process of finding valuable, underpriced collectible cards on eBay, turning hours of manual search into an automated background task.
Set up a cloud-based 'software factory' where AI agents autonomously handle coding tasks assigned and managed through a Linear project board. This workflow turns you from a coder into an AI agent manager.
Combine objective LLM-as-judge scores with subjective human 'taste' scores to create a final, definitive model ranking. This workflow shows you how to build a weighted index that reflects your unique priorities.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.