Structuring context, examples, and constraints to steer outputs.
22votes
0answers
2.3kviews

Planning-loop prompt that makes an agent decompose before it touches any tools

Our agents were too eager. Given a task they'd immediately start editing files, then discover halfway through that the approach was wrong and thrash. Latency and token cost ballooned from all the back
12votes
0answers
1.9kviews

Deterministic triage prompt for classifying inbound tickets into fixed buckets

I needed to route thousands of support tickets into a small set of categories for a dashboard. My first prompt was "classify this ticket" and it happily invented new categories every few hundred rows
13votes
0answers
1.3kviews

Chart theming as design tokens so every chart in the app matches

We had six charts built by four people and they all looked slightly different: different grays for gridlines, different fonts, three shades of the same 'brand blue'. I wanted the model to generate a s
18votes
0answers
2.0kviews

A reusable chain-of-thought scaffold as a system prompt, not inline rambling

I maintain a shared prompt library for my team and the biggest inconsistency was reasoning quality. People would tack "think step by step" onto the end and get mushy, unstructured chains that were har
13votes
0answers
1.5kviews

Making the model generate a config loader with validation instead of raw os.environ reads

Half our incidents traced back to config: an env var typo'd to an empty string, a port that was actually the literal text "8080" compared against an int, a feature flag that was the string "false" (wh