# A Practical Workflow for Agentic Development

A repeatable agent-assisted workflow that moves from grilling and specification to scoped issues, implementation, and review.

Published 2026-08-22 · https://thisissaeed.com/blog/practical-agentic-development-workflow

If you use agents every day to create features, fix bugs, or diagnose problems, you need a solid workflow. With one in place, you should not have to keep cleaning up poor AI-generated code after every task.

We use a strong internal workflow set up by [Stas Kokshin](https://www.linkedin.com/in/stas-kokshin-5a7b53112). You can also use [Matt Pocock's](https://www.linkedin.com/in/mapocock) workflow.

## My usual workflow

1. Grill the idea with the relevant documentation.
1. Turn the result into a spec.
1. Break the spec into issues.
1. Implement the issues. This step already uses code review by default.

When the task needs an architecture decision or deeper diagnosis, add:

- Improve codebase architecture
- Diagnosing bugs

Other useful skills include:

- Codebase design
- Domain modeling
- Test-driven development

Pstack by [Lauren Tan](https://www.linkedin.com/in/laurenelizabethtan) is also worth exploring, especially if you use Cursor.

## References

- [Matt Pocock's agent workflow](https://www.aihero.dev/skills)
- [Pstack](https://cursor.com/marketplace/cursor/pstack)

Originally posted on [LinkedIn](https://www.linkedin.com/posts/stringsaeed_tldrif-you-are-have-a-good-step-so-i-activity-7496758796502106112-Jdy4).
