ThoughtWorks 技术雷达 Vol.35 摘要
ThoughtWorks 技术雷达第 35 期（2026 年 11 月）中文摘要：四大主题、117 个条目与团队行动建议。
Topic
#agent-harness
46 篇笔记
Agent State Machines: Building Deterministic Scaffolding for Agents
If you're not using some type of agent state machine, you're completely at the mercy of the nondeterministic nature of models. Are you reall...
十分钟精读 DSH Super Agent：从 Paper 到 PRD
1. Super-agent作者认为，以 Coding Agent 为代表的单任务 Agent 已逐渐能够独立完成复杂工作，但现有系统仍以单一 Session 为基本单位。用户并行推进多个任务时，需要自行切换会话、管理上下文；文章称一个人通常只能同时跟进 3～5 个活跃 Sess...
Exploring Super-agent Design: Towards a More Autonomous Agent System
The original article is in Chinese. This is a machine translation.This article discusses architectural ideas. It is not an introduction to e...
New context engineering challenges in late 2026
It feels like everyone is converging on the same agent architecture: an LLM, running in a loop, calling tools, running in a sandbox. Claude ...
Building fine-grained version control for agents with Rust and Durable Objects
How DeltaDB streams every edit from humans and agents into one causal graph.
What FDE means at OpenAI
What forward deployed engineering means at OpenAI
AI Agents Are Having Their Kubernetes Moment
Ten years ago, we saw infrastructure responsibilities moving out of microservices and into Kubernetes, service meshes, and proxies. Applicat...
手脑分离与边界治理：企业级 Agent 平台的总体架构设计
在本地终端环境中，开发者早已习惯使用 Claude Code、Cursor 或各类命令行 Agent 进行自主编码与系统运维。模型推理循环与操作系统的 Shell、文件系统和环境变量运行在同一台宿主机上，通过本地进程树与内存字典直接驱动。这种“脑与手同机”的拓扑，在个人开发机上极...
「万字总结」- 我偷来了一份成为 Agent 工程师的学习线路
我之前面试了一家做 AI + web3 业内比较厉害的公司，但是没有通过吧，面试之后面试官给我了一份《Agent工程师入门指南》。我把它整理了一下，分享出来给大家提供参考，这是一份很详细很详细的、关于如何成为 Agent 工程师的文档，并且补充上我自己的学习心得当时给我的答复是 ...
来自 every 的自我批评，不应该让每个员工一个 Agent
Every 是一家做 AI 应用和内容的公司，最近把自己用了半年的企业 Agent 公开，同时批评自己之前的做法：受 OpenClaw 的影响，Every 为员工每人一个 agent，但在实践过程中，发现了在「维护」层面产生了诸多的问题，导致这种方法不可持续。它的联合创始人兼 C...
How to Cut Your Agent Bill by 90% With Jev Engineering and Kimi K3
How to find the decisions hiding inside your agents, write questions a system one model answers well, route on calibrated confidence and han...
Your Agent Harness Should Repair Itself
Everything you need to understand how an agent harness can learn from production failures and repair itself. It covers procedural memory, tr...
The Harness Playbook
Model the agentic harness like a game engine and most of its hard problems — durable state, tools, configuration, the TUI, inference — collapse into ones other people already solved.
Your Inference Server is Secretly a Learner: Open-Sourcing Reef for Continual Self-Improving Agents
1. Before all the “RSI” hype becomes realBefore today's excitement around RSI is fully realized, we want to open-source Reef, an infrastruct...
How to Cut Agent Tokens by 2.7x (using an open harness)
Everything you need to understand where your agent's tokens actually go and what to do about it. It covers what a production harness owns be...
Agent 终章（Harness 成本篇）：一次百炼账单降低 88% 实战
关于优化 token，本文或许能够提供一些经验和参考
Recursive Self-Improvement
Agents can already edit their tools, skills, and harness. Recursive self-improvement still needs a system that can raise the verifier without capturing it.
5 design patterns for long-horizon agent harness
Any agent can look brilliant on a one-shot task. Give it a week of real work and it starts to fall apart."Long horizon" means the agent keep...
Codex as a platform: build on the open agent harness
Build Codex into the products and workflows your users already know.
What is a Harness?
An agent harness is a piece of software that provides an environment for an AI model to operate within.
An open source rival to Claude Managed Agents just launched
TrueFoundry's open source TrueForge challenges Claude Managed Agents with vendor-neutral model choice, claiming 50% lower agent costs and no lock-in.
From context to dreams: architecting memory for AI agents
Have you ever felt that every conversation you have with an LLM across sessions feels like starting over from scratch? LLMs have a problem: ...
The Agent Harness Should Be Open
Today, we are open sourcing TrueForge, the agent harness we use at TrueFoundry to build and run general-purpose agents. Because once agents ...
Designing Agent Context by Scope and Time
When an agent performs poorly, we often blame the model.Then we enlarge the system prompt. When that becomes unwieldy, we add another agent....
How to Design an Agent Harness: six decisions that turn a model into a worker you can leave alone
Your agent says the job is done and the tests never ran. It's sharp for twenty minutes, then forgets a rule you gave it at the start. You re...
Why model routing must be in the harness
Inference spend is rising as agents are deployed more widely, take on more complex tasks, and run longer autonomously. Enterprises are start...
Practical Loop Engineering
Goals, loops, and the discipline of not delegating your judgment
How to Build a Shared AI Harness for Your Team
I am going to show you how to turn the models, agents, skills, and automations living across your team's tools and workflows into one coordi...
Why managed agents are the next big thing in agent building
Today we’re launching Managed Deep Agents - the easiest way to build, run and deploy production agents. We have a full release blog and docs...
Why managed agents are the next big thing in agent building
Today we’re launching Managed Deep Agents - the easiest way to build, run and deploy production agents. We have a full release blog and docs...
Deep Agents vs LangChain vs LangGraph
Deep Agents, LangChain, and LangGraph each offer distinct approaches to building agents. In this post, we cover the key distinctions between...
How Stripe Built Kai on Deep Agents in 1 Week
Learn how Stripe built Kai, a company-wide AI agent on LangChain, LangGraph, and Deep Agents, reaching 5,000 users in roughly 4 weeks.
YC 开源 QM：当每个员工都有 Agent，公司需要怎样的协作系统？
未来一家公司里，可能每个员工都有自己的 Agent。它们能读文件、查数据库、写代码、回复邮件，也能在后台持续运行任务。问题随之而来：这些 Agent 应该看到什么？记住什么？使用谁的账号？哪些能力可以共享？危险动作由谁批准？7 月 31 日，Y Combinator 开源的 QM...
The harness is all you need (mostly)
A practical GitHub Copilot workflow for prototyping, planning, implementing, and reviewing software - without chasing every new AI tool.By @...
We rewrote our agent to run entirely in a Durable Object with Pi, Agents SDK and Code Mode
We recently finished moving the camelAI agent off of virtual machines. The agent now runs inside a Cloudflare Durable Object, its filesystem...
A Taxonomy of Self-evolving Agents
Self-evolving agents are becoming popular. [Hermes Agent](https://hermes-agent.nousresearch.com/docs/user-guide/features/skills) enables aut...
Designing a programmable runtime for agent orchestration
This article introduces Onyx, our VM for programmable agent orchestration. And by extension, a runtime that turns orchestration into softwar...
Towards org-level agent harnesses
Claude Tag has grown rapidly in Anthropic. I want to share some of the reasons for this and the behavioral shifts I’ve seen with this agent ...
30 Core Agentic Engineering Concepts Every Developer Should Know
There are 8 billion people on the planet.Only a fraction of developers understand how AI agents actually work.Not the demos. Not the hype.Th...
The Agent Loop Architecture
Everyone's asking "WTF is a loop?" Here's the question nobody's asking: what runs the loop?The AI discourse has converged on loops as a core...
I Replaced My Entire Growth Team With 6 AI Agents. Here Is the Full System.
The week everything changed, I was not in front of my computer.Three content pieces went out before 9am. Four leads got qualified and follow...
Building cloud agent infrastructure: what's different, and what we learned
Most agent frameworks today assume a desktop. One user, one machine, one process. The agent runs while the laptop is open, writes to a local...
Faking a Filesystem For your Agent: PostgresFS
Faking a filesystem for your agent: why PostgresFS lost to a skillCo written by @SufjanFana Working with agent harnesses, it is hard not to ...
Setting Up and Using the Pi Coding Agent
My experience of setting up the Pi coding agent with DeepSeek, installing packages, and using it for side projects and experiments.
State of Memory in Agent Harness
Agent harnesses are where AI software actually runs. Cursor, Devin, Claude Code, Codex: these environments handle context, orchestrate tools...