After a week with Opus 5.5: 6 practical tips for getting the most out of it
every · x · 2026-09-23
The Every team tested Claude Opus 5.5 for a week and shared 6 practical tips:
- Set a time goal — it won't stop on its own and will eat your weekly limit; say "10 minutes, produce X"
- Name the deliverable — asking for a run of show got training materials but no schedule
- Ask it to critique its own work — it catches things you missed
- Give it notes — Opus 5.5 builds on feedback instead of arguing
- Move the point up yourself — most readable prose they've measured, but still buries the lede
- Point it at visual work — game UI, 3D, animations, and prototypes come out right (and funny) on the first try
More from coding & agent
- Stripe explains how agents detect and use checkout via WebMCP — jeff_weinstein · 2026-09-23
- Anthropic's Opus 5.5 system card: multi-agent runs match single-agent outcomes faster — jyangballin · 2026-09-23
- Stripe demos WebMCP integration: a deep dive through a checkout page's new tools — jeff_weinstein · 2026-09-23
- Building AI agent harnesses that improve across 6 editable control dimensions — MaryamMiradi · 2026-09-23
- Drop launches: rootless Linux sandbox that isolates coding agents at the OS level — aronchick · 2026-09-23
- Splitting Reasoning From Tool Use: Two Lightweight AI Models Screen 30,000 Crystal Candidates in 48 Hours — bravo_abad · 2026-09-23