Getting AI to work in complex codebases

Re:Getting AI to work in complex codebases by danielbln on Tuesday September 23, 2025 @03:14PM (#45351462)

I can recommend one more thing: tell the LLM frequently to "ask me clarifying questions". It's simple, but the effect is quite dramatic, it really cuts down on ambiguity and wrong directions without having to think about every little thing ahead of time.

[ Parent | on HN ]

Re:Getting AI to work in complex codebases by iagooar on Tuesday September 23, 2025 @04:57PM (#45352650)

When do you do that? You give it the PRD and tell it to ask clarifying questions? Will definitely try that.

[ Parent | on HN ]

Re:Getting AI to work in complex codebases by BeetleB on Tuesday September 23, 2025 @06:25PM (#45353590)

The "ask my clarifying questions" can be incredibly useful. It often will ask me things I hadn't thought of that were relevant, and it often suggests very interesting features.

As for when/where to do it? You can experiment. I do it after step 1.

[ Parent | on HN ]

Re:Getting AI to work in complex codebases by danielbln on Tuesday September 23, 2025 @05:01PM (#45352695)

Before or after.

"Here is roughly what I want, ask me clarifying questions"

Now I pick and choose and have a good idea if my assumptions and the LLMs assumptions align.

[ Parent | on HN ]

Re:Getting AI to work in complex codebases by dhorthy on Tuesday September 23, 2025 @06:38PM (#45353702)

yeah if you read our create_plan prompt, it sets up a 3+ phase back and forth soliciting clarifying questions before the plan is built!

[ Parent | on HN ]