The new skill in AI is not prompting, it's context engineering

Re:The new skill in AI is not prompting, it's context engine... by fwn on Tuesday July 01, 2025 @08:42AM (#44433350)

That’s pretty typical, though not especially reliable. (Allthough in my experience, Gemini currently performs slightly better than ChatGPT for my case.)

In one repetitive workflow, for example, I process long email threads, large Markdown tables (which is a format from hell), stakeholder maps, and broader project context, such as roles, mailing lists, and related metadata. I feed all of that into the LLM, which determines the necessary response type (out of a given set), selects appropriate email templates, drafts replies, generates documentation, and outputs a JSON table.

It gets it right on the first try about 75% of the time, easily saving me an hour a day - often more.

Unfortunately, 10% of the time, the responses appear excellent but are fundamentally flawed in some way. Just so it doesn't get boring.

[ Parent | on HN ]

Re:The new skill in AI is not prompting, it's context engine... by simonw on Tuesday July 01, 2025 @09:10AM (#44433568)

Try reformatting the data from the markdown table into a JSON or YAML list of objects. You may find that repeating the keys for every value gives you more reliable results.

[ Parent | on HN ]

Re:The new skill in AI is not prompting, it's context engine... by fwn on Wednesday July 02, 2025 @06:25AM (#44441987)

Thanks for the suggestion! I’ll start benchmarking my current md table setup against one using YAML. It's apparently slightly less verbose than JSON.

[ Parent | on HN ]

Re:The new skill in AI is not prompting, it's context engine... by v3ss0n on Tuesday July 01, 2025 @03:55PM (#44437465)

Gemini does a lot better at long context.

[ Parent | on HN ]