Multi-step Prompts Are Still More Effective
sanderssays · x · 2026-07-11
The author notes that even heading into 2026, they still find multi-step prompts yield better results.
Their go-to structure:
- Prompt 1: Do absolutely nothing
- Prompt 2: Continue to do nothing
- Step 1: Perform reasoning
- Step 2: Generate the output
They add: of course, you could also just hand this entire process over to an agent.
More from coding & agent
- An MCP server signs every AI agent tool call into a verifiable Merkle chain — Funky_Chicken_22 · 2026-07-22
- Annotated transcript of a Claude Code team interview is now available — trq212 · 2026-07-22
- Claude Code skill uses 10 Markdown rules to make outputs ADHD-friendly — alex_verem · 2026-07-22
- A Firecracker-based platform says it can host 6,000 AI agents on one 256 GB server — maritime_sh · 2026-07-22
- A better path to agent autonomy is running waves, finding friction, and iterating — JnBrymn · 2026-07-22
- AI agent designers map the visual and tonal cues behind companionship products — Unlikely-Platform-47 · 2026-07-22