daniel_mac8's blog expands on the four habits behind Asana's 89% prompt cache hit rate
daniel_mac8 · x · 2026-10-11
A blog post expanding on danielmac8's thread about how Asana cut its Codex browser agent's cost on GPT-6.1 Sol from $1.97 to $0.47 per run with an 89% prompt cache hit rate. The four habits: append-only sessions, no mid-session model/effort/tool switches, deliberate use of /compact, and measuring cache hit rate via codex exec --. The original thread has the full details.
Related event: Asana Cuts Codex Agent Costs via Stable Prompt Caching(3 posts)→
More from coding & agent
- Regents Labs runs a daily AI paper digest with ChatGPT Pro, spotlighting Prime Intellect's agent stack — seanwbren · 2026-10-11
- Python vs Go vs Rust for production agentic systems: a six-dimension practical evaluation — mostly_deterministic · 2026-10-11
- Agent Use Cases: a free site scanning the web daily for 1,000+ real AI agent use cases — Roger_M_Taylor · 2026-10-11
- Theo: Modern models handle mid-task steering well enough to skip message queueing — pvncher · 2026-10-11
- 1,680 A/B trials show 50-year-old Unix formalisms crush English prompt rules, 98.3% vs 0.8% — RandalSchwartz · 2026-10-11
- Creator tests viral open-source REA to reverse engineer CapCut's hidden tricks — vista8 · 2026-10-11