NEW RUNTIME

Topic hub

Agent Loops

A New Runtime topic hub collecting signals, patterns, field notes, and public sources about agent loops.

Short answer

  • Agent Loops is tracked here as an evidence-linked topic, not as a static glossary entry.
  • The page connects raw observations to pattern hypotheses, longer analysis, and public sources.
  • Use it as the canonical landing page before drilling into individual records.

Pattern memory

Current hypotheses

1 patterns
  1. high

    Goal-scoped loops replace manual continuation

    An autonomous loop becomes operationally useful when completion is an external contract rather than a model's subjective decision to stop.

Raw signals

Recent observations

5 signals

  1. Airbnb frames agentic coding as a loop inside development

    The workflow separates planning, delegated implementation, verification, and integration instead of treating the coding agent as the whole process.

  2. Deep Agents packages a harness for long-running tasks

    LangChain's Deep Agents combines planning, files, memory, subagents, middleware, and backends for multi-step work.

  3. Claude Code can recover after a failed command

    A runtime update lets the coding agent inspect a command failure and continue its loop without waiting for a generic human prompt.

  4. Loop Engineering Expands Beyond Coding

    The same goal, action, evaluation, and retry structure can automate research, operations, and product work when completion is observable.

  5. Codex Can Run as a Maintainer Loop

    Reusable scripts turn issue triage, project maintenance, and review into recurring goal-driven jobs rather than one-off coding prompts.