Why not get it 1st time right before it's sent to the Sr. Devs?
Granted AI creates sloppy code, but there are ways to make it Sr. Dev grade, mainly by getting rid of what I call Builder's Debt:
- iterate the shit out of it to make it production grade OR
- extract ACs from Jira, requirements from docs, decisions and query resolutions from Slack, emails, meeting notes, stitch them together, design coding standards relevant to the requirements and context before coding
If you use the models like we execute coding tasks, older models outperform latest models.
There's this prep tax that happens even before we start coding, i.e., extract requirements from tools, context from code, comments and decisions from conversations, ACs from Jira/Notion, stitch them together, design tailored coding standards and then code.
If you automate the prep tax, the generated code is close to production ready code and may require 1-2 iterations max.
I gave it a try and compared the results and found the output to be 92% accurate while same done on Claude Code gave 68% accuracy. Prep tax is the cue here
That's another way to look at it. Getting AI to reliable and accurate output is where we feel there are steps that'll need better structure, like for Ingesting and chunking strategies.
Granted AI creates sloppy code, but there are ways to make it Sr. Dev grade, mainly by getting rid of what I call Builder's Debt: - iterate the shit out of it to make it production grade OR - extract ACs from Jira, requirements from docs, decisions and query resolutions from Slack, emails, meeting notes, stitch them together, design coding standards relevant to the requirements and context before coding