Show HN: LLM prompt template to build backend APIs faster

Posted by knutmartin on Wednesday March 19, 2025 @11:32AM
from the show-hn dept.

https://codehooks.io/blog/how-to-use-chatgpt-build-nodejs-backend-api-codehooks

( 2 comments | on HN )

Re:Show HN: LLM prompt template to build backend APIs faster by sdotdev on Wednesday March 19, 2025 @07:12PM (#43418220)

I agree with this, what you put into the prompt will reflect in what you get out, so just be more detailed.

[ Parent | on HN ]

Re:Show HN: LLM prompt template to build backend APIs faster by knutmartin on Thursday March 20, 2025 @07:18AM (#43421733)

One of the frustrating aspects of using prompts to generate code is that the output can vary quite a bit even with the same prompt. Creating an API which use the OpenAI APIs for mission critical solutions feels a bit scary and unpredictable. For structured output, I know people use libraries like Pydantic with Python. I don't now the best approach to deal with this with regards to code generation, though. For now, I guess having an experienced software engineer examine the code is essential.

[ Parent | on HN ]