---
schema_version: "newruntime-topic-hub-v0.1"
type: "topic_hub"
slug: "agent-ops"
title: "Agent OPS - New Runtime"
description: "A New Runtime topic hub collecting signals, patterns, field notes, and public sources about agent ops."
answer: ["Agent OPS 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."]
search_intents: ["agent ops","agent ops AI agents","agent ops software"]
status: "tracked"
last_updated: "2026-07-21"
counts: {"total":7,"signals":2,"patterns":0,"posts":3,"atlas":2,"sources":12}
routes: {"html":"https://newruntime.com/topics/agent-ops/","markdown":"https://newruntime.com/topics/agent-ops.md","json":"https://newruntime.com/topics/agent-ops.json"}
top_sources: ["https://addyo.substack.com/p/own-the-outer-loop","https://anthropic.com/research/AI-assistance-coding-skills","https://code.claude.com/docs/en/goal","https://code.claude.com/docs/en/scheduled-tasks","https://code.claude.com/docs/en/sub-agents","https://creatoreconomy.so/p/how-i-plan-build-and-run-loops-with-claude-code-thariq-shihipar","https://github.com/NousResearch/hermes-agent","https://info.langchain.com/guide/the-agentic-operating-model","https://ir.gitlab.com/news/news-details/2026/GitLab-Research-Reveals-Organizations-Are-Generating-AI-Code-Faster-Than-They-Can-Control-It/default.aspx","https://modelcontextprotocol.io/docs/concepts/architecture","https://sonarsource.com/state-of-code-developer-survey-report.pdf","https://www.humanlayer.dev/blog/writing-a-good-claude-md"]
---

# Agent OPS - New Runtime

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

## Short Answer

- Agent OPS 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.

## Patterns


## Field Notes

- [LangChain Says Agents Need an Operating Model, Not Just a Framework](https://newruntime.com/posts/langchain-agentic-operating-model/): LangChain frames production agents as a governed operating model where reliability, governance, tracing, improvement loops, and accountability matter more than a prototype.
- [Long-Running Loops Need Goals, Not Keep-Going Prompts](https://newruntime.com/posts/claude-code-long-running-loops/): Long-running agent work is useful only with a testable goal, checkpoints, a terminal condition, and recovery policy; otherwise the loop becomes expensive blind continuation.
- [The Four Stages of AI-Native Development](https://newruntime.com/posts/ai-native-development-stages/): An AI-native team does not start by buying agent tooling; it starts by turning one engineer's working method into reproducible rules, memory, and checks.

## Recent Raw Signals

- 2026-07-16: [Verification capacity becomes the coding-agent bottleneck](https://newruntime.com/signals/verification-capacity-coding-agent-bottleneck/)
- 2026-07-15: [A local agent is a runtime, not one model](https://newruntime.com/signals/local-agent-is-a-runtime-not-one-model/)

## Public Sources

- https://addyo.substack.com/p/own-the-outer-loop
- https://anthropic.com/research/AI-assistance-coding-skills
- https://code.claude.com/docs/en/goal
- https://code.claude.com/docs/en/scheduled-tasks
- https://code.claude.com/docs/en/sub-agents
- https://creatoreconomy.so/p/how-i-plan-build-and-run-loops-with-claude-code-thariq-shihipar
- https://github.com/NousResearch/hermes-agent
- https://info.langchain.com/guide/the-agentic-operating-model
- https://ir.gitlab.com/news/news-details/2026/GitLab-Research-Reveals-Organizations-Are-Generating-AI-Code-Faster-Than-They-Can-Control-It/default.aspx
- https://modelcontextprotocol.io/docs/concepts/architecture
- https://sonarsource.com/state-of-code-developer-survey-report.pdf
- https://www.humanlayer.dev/blog/writing-a-good-claude-md