Prompt Engineering at Work
Move from one-off prompts to repeatable systems — templates you reuse, reliable ways to summarise long documents, a method for fixing prompts that go wrong, and a shared library your whole team can lean on.
Reusable prompt templates
A template is a good prompt with the changeable parts pulled out You have probably written a prompt that worked beautifully, then had to rebuild it from memory a week later. A template fixes that. It is a prompt you wrote once, with the parts that change from job to job replaced by clearly marked […]
Writing for a program, not a person
Nobody is watching when this one runs A prompt you run in a chat window has a safety net: you. You see a strange answer and retry. The moment a prompt runs inside a script, a scheduled job or a product feature, that net is gone — the output goes straight to a database, a […]
Handling failure on purpose
The call will fail. Decide now what happens then Model calls fail in ways ordinary functions do not: they time out, they get rate-limited, they return the right shape with the wrong content, and occasionally they return something no schema anticipated. A pipeline that assumes success is a pipeline that will corrupt data quietly. Four […]
Prompts as team assets
The prompt in someone’s notes app is a liability Once prompts affect real work, they stop being personal notes and start being infrastructure. The failure is familiar to anyone who has watched a spreadsheet become load-bearing: it works, one person understands it, and then that person is on holiday. Treat a production prompt like code […]