Structured outputs that do not break: schemas, Zod and a repair retryA few years ago the hard part of getting JSON from a language model was getting JSON at all. You asked nicely, you got a code fence with a trailing comma, and you wrote a regex to dig the object out. 4h ago · 10 min readmahmadmanzoor.hashnode.dev
Evals before prompts: a small eval harness for an LLM featureEvery LLM feature I have built started the same way: a prompt that worked on the three examples I had open. On the roof report extraction work, the examples I had open turned out to be the easy ones. 5h ago · 12 min readmahmadmanzoor.hashnode.dev
Make coding agents prove their workThe most expensive sentence a coding agent writes is "Everything should work now." It is said with confidence, and sometimes it is even true. An agent's summary of its own work is the least reliable p5h ago · 9 min readmahmadmanzoor.hashnode.dev
