by saqadri on 11/17/23, 5:06 PM with 16 comments
by saqadri on 11/17/23, 6:00 PM
Our basic premise is that AI application development should be config-based, so you can track the prompts, models and model parameters being used more rigorously. Having this AI artifact then lets you iterate on it separately from your application code, and also set up evals that provide "test coverage" for the gen AI parts of your application.
We were also inspired by the ipynb format for Jupyter notebooks, and you'll see parallels to that in the aiconfig format.
Please ask any questions, and share your thoughts on config vs. code.
by jdwyah on 11/17/23, 8:08 PM
In particular for 1. teams that have complex slow deploys, but want to change prompt now 2. when there are data analyst types doing the prompts and people don't want them to be able to "break things". 3. being able to alpha test / rollout / target new prompts easily.
Definitely an interesting question whether prompts is code or configuration.
by activescott on 11/17/23, 7:16 PM
by kordlessagain on 11/17/23, 9:51 PM
by smy20011 on 11/17/23, 6:18 PM
by joshka on 11/18/23, 3:37 AM
by thatxliner on 11/17/23, 9:37 PM