Every says Opus 5 works better when given one clear job and left alone
every · x · 2026-07-29
Every says its team got better results from Opus 5 by giving it one substantial job with a clear finish line, then leaving it alone.
The workflow it highlights:
- Dan Shipper and Marcus Moretti each handed Opus a well-scoped task and let it run.
- Jack Cheng told it he was stepping away, then batched questions instead of interrupting constantly.
- Anthropic's own prompting guide recommends the same approach: put the full brief in the first prompt, let the model work, then evaluate the final artifact on its own.
Every says this was the workflow that made Opus 5 perform better, even though it had been hard for the team to love.
Related event: Claude Opus 5: Powerful but Requires Proper Handling(2 posts)→
More from coding & agent
- Agent Farm spotlights worktree management for coding agents — jasonkneen · 2026-07-29
- MCP 2026-07-28 drops sessions and aligns the protocol with static sites — VeryWellVersed · 2026-07-29
- A Unity RPG prompt pushes multi-agent coding loops to absurd AAA perfection — chongdashu · 2026-07-29
- Chance launches x402 Verifier: ensures AI agents verify every payment before signing — kleffew94 · 2026-07-29
- Whiteboard diagram separates chatbots, RPA, RAG, and real AI agents — SucceededMind · 2026-07-29
- Developer shares learnings from building visualization tools with Claude — MaxLenormand · 2026-07-29