I’ve been successfully shipping software since 1998. I just got the first payment on a greenish-field software product I’m doing on the side solo (that I couldn’t have done solo in 2019 without the tools). This is my workflow:
1. Client asks you to add a feature(s)
2. Spend two weeks unpaid walking the client through scoping down to the most minimal viable set of features that tests the business hypothesis and roadmap
2. I wrote up a reasonably exhaustive bullet list and sent it to a CGPT to write a draft formal definition of features describing what it should (and should not) do, how users can access it and what the suite of tests that we will need through TDD
3. Chat for 30 minutes with CGPT researching which data structures, algorithms, code libraries and external services might serve best to implement this feature.
4. Generate mockups and data schema alongside CGPT, to build the new feature, the tests to make sure it works as expected, and the documentation telling users how to use it and telling other engineers what they’ll need to know to maintain and debug it.
5. Generate minimum code to test the full data workflow.
6. Send repo and or working application binary to Claude and Gemini to critique
7. Adjust as needed. Deploy for client review and acceptance in sandbox. Promote to production
8. GOTO3 and loop
I can do in a week what would have taken a month a decade ago
You’re the founder and CEO of an AI startup but also vibecoding side gig work?
Part 6 to me seems always totally useless.
Whenever I let these tools look at existing repos they are too influenced by what's already there.
I could even say "feel free to completely refactor or rewrite anything" and they'll still just do small performative changes.
I've now changed my workflow to only using AI for prototyping and rewriting by hand once I can see something is viable. Takes longer but the results are always much better.