The app for independent voices
After weeks of researching how our team at PostHog builds with AI tools like Cursor and Claude Code, I published a deep dive to help you get the most out of them. Here are the best ones:
Treating your big codebase differently than a small codebase. Most AI coding advice is written for vibe coders going from zero to one. You need to care much more about context windows, automation tests, and prompting in larger codebases.
Provide the right context, rules, and guardrails. Without them, LLMs go off the rails fast. Reference example code, add documentation, use rules files for different languages, write a spec. And use non-AI tools like linters, type hinting, and testing suites.
Learn what AI is good at. Our team finds it excels at autocomplete, adding more tests, rubberducking, and doing research. It’s not so good at writing code in an unfamiliar language, using the correct methods/classes/libraries, following up-to-date best practices, and writing tests from scratch.
Always be leveling up your workflow. Great product engineers are always experimenting. To help them do this, we raised our AI tool budget to $300/m, test new tools, try different models, dogfood AI in PostHog itself, and build with AI in hackathons.
Remember that as much as you might dislike AI personally, your competitors are using it and so are your users. In both cases, knowing the capabilities and limits of AI helps.
To learn more, read my post on AI coding mistakes to avoid →
