# Agentic Development

> Status: Exploring

Practical ways to make coding agents useful inside real engineering constraints.

## Established practice, open direction

Claude Code, OpenAI Codex, and Cursor are already part of day-to-day investigation, planning, implementation, debugging, testing, review, and documentation. Here I am working through how to make that practice more reliable and repeatable.

## Working loop

1. **Context**: Supply product, architecture, code, and constraints.
2. **Decompose**: Turn a goal into bounded engineering work.
3. **Execute**: Use agents where they improve the workflow.
4. **Verify**: Check decisions and output against evidence and tests.

## Topics

- Agents
- Context
- Verification