# Getting Into Flow State with Agentic Coding

DevFeed: [Getting Into Flow State with Agentic Coding](<https://devfeed.tech/articles/getting-into-flow-state-with-agentic-coding-25210.md>)

Original publisher: [Read original article](<https://kau.sh/blog/agentic-coding-flow-state/>)

Author: Kaushik Gopal

Published: 2025-07-23T07:15:47Z

Content type: tutorial

Language: en

Sources: [Kaushik Gopal's Site](<https://devfeed.tech/sources/kaushik-gopal-s-site.md>)

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [ai-coding](<https://devfeed.tech/topics/ai-coding.md>), [Development](<https://devfeed.tech/topics/development.md>), [Code](<https://devfeed.tech/topics/code.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>)

Tags: [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [openai](<https://devfeed.tech/tags/openai.md>), [refactor](<https://devfeed.tech/tags/refactor.md>), [review](<https://devfeed.tech/tags/review.md>), [verify](<https://devfeed.tech/tags/verify.md>)

## AI overview

A developer documents a workflow for using Claude Code and other AI coding agents in production software development. The process emphasizes maintaining shared instructions, planning work explicitly, and organizing implementation into discrete pull requests so agents can resume tasks with sufficient context.

## Source excerpt

I recently found myself in a deep state of flow while coding -- the kind where time melts away and you gain real clarity about the software you're building. The difference this time: I was using Claude Code primarily. If my recent posts are any indication, I've been experimenting a lot with AI coding -- not just with toy side projects, but high-stakes production code for my day job. I have a flow that I think works pretty well. I'm documenting it here as a way to hone my own process and, hopefully, benefit others as well. set the stage plan with the agent (no really 🤮) spawn your agents verify and refactor the final review Skeptics vs cynics Many of my friends and colleagues are understandably skeptical about AI's role in development. That's ok. That's actually good. We should be skeptical of anything that's upending our field with such ferociousness. We just shouldn't be cynical.1 Step 0: Set the stage # You know what'll definitely get you out of the flow? Having to constantly repeat basic instructions to your agent. "This is an Android app that does X, using the Y architecture..." "When styling the front end web client, only use tailwind css v4..." "Use `make test` to run a single test; `make tests` to run the entire test suite..." "To build the app without running lint use `make`..." ... These are all very important instructions that you shouldn't have to repeat to your agent every single time. Invest a little upfront in your master ai instructions file. It makes a big difference and gets you up and coding quickly with any agent. trivial to get started with claude /init these days Of course, I also recommend consolidating your ai instructions to a single source of truth, so you're not locked in with any single vendor. Step 1: Plan with the Agent # Update: Checkout my post ExecPlans. I now use OpenAI's Aaron Friel ExecPlans approach for this. I won't lie. The idea of this step did not exactly spark joy for me. There are times where I plan my code out in a neat list, but rarel