Sheela
Sheela
Home
Add
Questions
Thinkers
Claims
People
Concepts
Jargon
Sources
Health
Predictions
Collections
Domain Landscape
Contribute
Review
Dedup
Topic requests
Settings
Help

← Jargon

Jargonmachine learning· 2 claims· 1 episode

multi-turn agent

An AI agent that makes long sequences of dependent decisions and tool calls across many turns, requiring memory of prior steps.

As defined in Scott Wu - Building Cognition - [Invest Like the Best, EP.402]


Where it comes up · 1
  • Scott Wu - Building Cognition - [Invest Like the Best, EP.402]2 claims

Most important claims · 2 of 2Search all claims for “multi-turn agent” →
  • A single model query costs a tiny fraction of a cent, but Devin may make hundreds or thousands of decisions over half an hour of work, so agents will dominate GPU usage and push foundation labs to optimize for multi-turn traces and long context.Scott Wu - Building Cognition - [Invest Like the Best, EP.402]
  • Fixing a bug is a multi-step decision sequence: reproduce the bug locally, inspect logs and variables, read relevant files, edit, retest, and add a unit test, and an agent must choose actions that maximize the chance of success across many steps rather than produce a single answer.Scott Wu - Building Cognition - [Invest Like the Best, EP.402]