Tag
Cognition replaced the Opus model with Fable in Devin's Fusion architecture, achieving higher performance at lower cost despite Fable's higher per-token price, through better delegation and reduced lead model turns.
Open-sourced a pre-call spend gate and tamper-evident audit log to prevent runaway API costs from recursive loops in autonomous agents, MIT-licensed with Postgres+TypeScript demo.
The author shares lessons from instrumenting AI agent tool calls, revealing that tools like web_search can account for ~50% of spend, and highlighting the importance of tracking p95 latency and attributing costs per workflow or customer to avoid surprises.