Ask HN: What AI prompts have you found most reliable for actual work?
The article discusses effective AI prompts for work-related tasks. The author shares their approach to using AI for brainstorming, designing, and implementing projects. They emphasize the importance of critical feedback and iterative refinement throughout the process.
- ▪The author uses a core system prompt that encourages critical feedback on their ideas.
- ▪They engage in a back-and-forth dialogue with the AI to refine their project concepts.
- ▪Once a clear plan is established, they request a detailed design document and implementation plan.
Hacker News (AI / LLM) files mainly under ai. We currently carry 3,323 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Ycombinator |
| Canonical URL | https://news.ycombinator.com/item?id=48226384 |
| Publication time | Thu, 21 May 2026 17:39:23 +0000 |
| Retrieval time | 2026-05-21T17:41:35.361Z |
| Last seen | 2026-05-21T17:41:35.361Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | w7EF3OLvLTbS · 3 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
I'm not an expert by any means, but I feel like this has worked for me. First off my core system prompt (or similar) contains a piece about how I want it to be critical of what I say or suggest, and to not assume what I say is a good idea.Unless I have a very clear plan for what I want to build, I say I want to brainstorm X. I'll say what I had in mind, ask what it thinks. We then go back and forth, I might ask for alternatives and such along the way. Once I know what I want to build, I say make a detailed design document of what we've arrived at, include rationales for the decisions made. If it's a larger project I say to split the design into phases that can be implemented incrementally.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Ycombinator.