Yadnesh Salvi

Story · Gagan Bhat & Isabella Kai He (Anthropic)

Evolution of agentic surfaces (Gagan Bhat & Isabella Kai He (Anthropic))

talk · Story page

Two stacked assembly-line diagrams labeled BEFORE and AFTER. In the top one a mouth icon is chained in series with tool stations and its clock shows a long wait; in the bottom the mouth sits on its own track with tools on a parallel rail, its clock nearly empty.

Anthropic's Applied AI team on harness assumptions going stale: a context-reset workaround built for Sonnet 4.5 became pure overhead once Opus 4.5 shipped without the quirk. Decoupling the agent loop from tool execution cut time to first token 60% at P50 and over 90% at P95.

In plain words

  • Anthropic found that a workaround for one artificial intelligence system became wasteful when the next system no longer needed it.
  • The earlier system stopped work before its memory filled, so engineers repeatedly cleared the information it was holding.
  • They separated decision-making from the computer running actions, so setup could happen at the same time and first responses arrived 60% faster.
  • This matters for teams building artificial intelligence workers because old workarounds can slow newer systems.

Appeared in

Subscribe

Get the brief in your inbox

Pick daily, weekly, or both. Nothing is gated either way: every issue is on the site and in the feeds.

  • Weekdays at 8:45am IST, one lead story and 6 to 9 items.
  • Sundays, an argued synthesis rather than a recap.
  • One click to leave, and quiet days say so in the subject line.
How often

Weekdays 8:45am IST + Sundays. Unsubscribe in one click.

You're asking for The Agentic Brief by email at the cadence you picked. You can unsubscribe in one click from any issue, and your address is never sold or shared.

Subscribe by RSS →