Consulting
One-on-one sessions to improve AI-generated code and build an agent workflow that works on a real project.
Who it is for
- Developers new to AI who already use Claude Code, Cursor or Copilot and want to understand what happens underneath
- People building by vibecoding who get stuck as the project grows: context blowing up, the agent rewriting what already worked
- Teams that want to standardize how they use agents before everyone invents their own process
What we cover
- Skills: when to create one, how to organize it, and why it may run at the wrong time
- Subagents: dividing the work, choosing a model for each task, and deciding what needs review
- MCP (Model Context Protocol): connecting your tools to an agent, with your approval required before it changes data
- Context: organizing information so each session does not use more as the codebase grows
- Workflow: worktrees, pull requests, automatic review, and tasks that are safer to do by hand
How it works
- 1Use the form below to describe your situation and what is getting in your way
- 2I review your situation and reply with what I found and what to do next
- 3A recorded one-hour call, followed by a written summary of what we decided