Found myself spending 30% of my programming time on [aistudio.google.com](https://aistudio.google.com/) chatting about the high-level code architecture. _Gemini 2.5 Pro_ is a genius model that is ridiculously nerfed in Cursor and other wrappers. Here’s the approximate workflow I use:

**1.** Pack the entire codebase into one prompt using Repomix or RepoPrompt, then copypaste it in the conversation. It makes a HUGE difference to include all project code in the input, and most AI IDEs don’t do that for you&#33;

**2.** Braindump all requirements and implementation ideas related to the feature you’re building. Simply make a _<braindump>...</braindump>_ section, AI just gets you most of the time. «Convert this into an elegant implementation design».

**3.** Skim through the design draft trying to identify obvious blunders and overcomplications, regenerate 2–3 times until the draft appears good. If it still has some minor issues, «Please update the design based on my feedback: …»

**4.** Read the polished version of the design very carefully, make sure you understand it. Question everything, like: «Why did you choose SHA-256 for hashing, wouldn’t BLAKE3 be faster?», «Let’s simulate what happens if this server handles 100k SSE connections simultaneously» and so on.

**5.** When you are confident that the design would work, ask AI to «write a step-by-step implementation plan for the finalized design for a developer who has no context of the previous conversation».

**6.** Finally, copypaste this very detailed implementation plan to Cursor or any other AI coding agent to actually make changes to files. _GPT-4.1_ is excellent for this due to its good instruction following ability.

**7.** As a final check, copypaste the diff of the changes back to your _Gemini 2.5 Pro_ conversation and ask it to review them. I like how it usually writes a checklist of what needed to be done and verifies the changes against it.

**8.** Brag about 100% of your code being AI-generated. 