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 Official Prompting Guide and Practical Tips(7 posts)→
More from coding & agent
- Harness open-sources desktop and mobile apps for orchestrating agent fleets across frameworks and machines — dee_hw · 2026-10-16
- Open-Source Google Analytics MCP Server Lets LLMs Query GA Data via Natural Language — modelcontextprotocol · 2026-10-16
- LLM ideation experiment: just ask for non-obvious ideas — and Opus beats smaller models by a wide margin — arjunrajlab · 2026-10-16
- a16z podcast: AI cut a 6-month feature to 10 days and widened engineer gaps 10x — a16z · 2026-10-16
- "Hold On, My Agents Are Freezing My Screen": The Daily Grind of the Agent Era — every · 2026-10-16
- Dev builds MCP feeding Claude 3,000 real launch videos to fix samey AI output — Designer_Landscape25 · 2026-10-16