Agent Harness in 7 Days: Let an Agent Run Unattended Through the Night
Course questions · 28 / 28
53 more tagsShow fewer tags
D1 Why an Agent Starts Degrading Once It Runs Past the Second Context Window
What is the difference between the context window and state? Why can a long-horizon agent's authoritative progress not live only in the window?上下文窗口和状态有什么区别?为什么长时程 Agent 的权威进度不能只存在窗口里?
Common in ChinaCommon overseasIntermediate#long-horizon#state-management#context-window🔒 Unlock D1 to see the answer keys.
Why should the model-facing interface not know which harness features are switched on? What happens if it does?为什么给模型的接口不该知道当前开了哪些 harness 功能?如果知道了会发生什么?
Common in ChinaCommon overseasDeep dive#experiment-design#interface-boundary#false-green🔒 Unlock D1 to see the answer keys.
An agent that ran unattended overnight tells you in the morning that every task is complete. How do you verify that claim?一个无人值守跑了一夜的 Agent 早上告诉你全部任务已完成。你会怎么验证这句话?
Common in ChinaCommon overseasIntermediate#verification#long-horizon#reporting🔒 Unlock D1 to see the answer keys.
Same model, same prompts, but swapping the harness lifts the benchmark score by more than ten points. What does that tell you?同一个模型、同一套提示词,换一个 harness 成绩提升十几个点。这说明了什么?
Common in ChinaCommon overseasIntermediate#harness-engineering#benchmarks#model-capability🔒 Unlock D1 to see the answer keys.
D2 The Line Between State and Context: Moving the Authoritative State Out of the Window
Designing the state layer for a long-horizon agent, what goes to disk and what stays out of it?设计一个长时程 Agent 的状态层,你会把哪些东西写进磁盘,哪些坚决不写?
Common in ChinaCommon overseasIntermediate#state-management#long-horizon#persistence🔒 Unlock D2 to see the answer keys.
After a window reset, is replaying the full prior transcript into the model a good idea?窗口重置后,把之前的完整对话历史重新喂给模型是个好主意吗?
Common in ChinaCommon overseasIntermediate#context-engineering#long-horizon#cost🔒 Unlock D2 to see the answer keys.
You added a state layer and the metrics improved. How do you show the state layer caused it, rather than coincidence?你加了一个状态层,跑下来指标变好了。怎么证明是它起的作用,而不是碰巧?
Common in ChinaCommon overseasDeep dive#evaluation#mutation-testing#state-management🔒 Unlock D2 to see the answer keys.
What happens if the process is killed while the state file is being written?状态文件在写入过程中进程被杀了怎么办?
Common in ChinaCommon overseasDeep dive#crash-safety#persistence#state-management🔒 Unlock D2 to see the answer keys.
D3 The Initializer Agent: init.sh, a Progress File and the First Commit
Before letting an agent develop a project unattended overnight, what do you have it do first?让一个 Agent 无人值守地开发一个项目,开工前你会先让它做哪几件事?
Common in ChinaCommon overseasIntermediate#initialization#failure-modes#long-horizon🔒 Unlock D3 to see the answer keys.
What belongs in a progress file, and how does a human-readable log differ from a summary written for the next window?进度文件应该写什么?写成给人看的日志和给下一个窗口看的摘要有什么区别?
Common in ChinaCommon overseasIntermediate#progress-file#state-management#long-horizon🔒 Unlock D3 to see the answer keys.
Why make initialization its own phase instead of letting the first pass of the main loop handle it?为什么初始化要独立成一个阶段,而不是让主循环第一轮顺手做掉?
Common in ChinaCommon overseasDeep dive#architecture#initialization#failure-handling🔒 Unlock D3 to see the answer keys.
How do you judge whether a workspace is friendly enough for a newly arrived agent? Give an executable test.怎么判断一个工作区对新来的 Agent 足够友好?给一个可执行的检验方法。
Common in ChinaCommon overseasDeep dive#acceptance-criteria#verification#developer-experience🔒 Unlock D3 to see the answer keys.
D4 One Thing at a Time: The Feature List and git Discipline
When may an agent run git commit on its own, and when must it never?什么情况下 Agent 可以自己执行 git commit,什么情况下绝对不行?
Common in ChinaCommon overseasIntermediate#git#state-management#boundaries🔒 Unlock D4 to see the answer keys.
How do you force an agent to do one thing at a time? Is putting it in the prompt enough?怎么强制一个 Agent 一次只做一件事?写在提示词里够吗?
Common in ChinaCommon overseasIntermediate#feature-list#constraints#harness-design🔒 Unlock D4 to see the answer keys.
An agent botches one feature - do you roll back or let it keep fixing? On what basis?Agent 做坏了一条 feature,你会让它回滚还是继续修?依据是什么?
Common in ChinaCommon overseasDeep dive#rollback#green-point#risk-exposure🔒 Unlock D4 to see the answer keys.
What can go wrong when an agent drives git, and how do you prevent it in code?让 Agent 操作 git 有哪些具体的危险?你会怎么在代码层面防住?
Common in ChinaCommon overseasDeep dive#git#safety-invariants#assertions🔒 Unlock D4 to see the answer keys.
D5 Self-Verification: The End-to-End Gate, Premature Completion Claims and Automatic Intervention on Doom Loops
An agent reports a task done - what evidence should your harness use to decide whether to believe it?Agent 报告任务完成,你的 harness 该用什么依据决定信不信?
Common in ChinaCommon overseasIntermediate#self-verification#false-completion#gates🔒 Unlock D5 to see the answer keys.
Browser automation versus HTTP-only end-to-end verification - what does each buy and cost?端到端验证用浏览器自动化和只打 HTTP 接口,各有什么得失?
Common in ChinaCommon overseasIntermediate#end-to-end#trade-offs#capability-boundary🔒 Unlock D5 to see the answer keys.
How do you detect an agent spinning in place, and what do you do once you have?你怎么发现一个 Agent 在原地打转?发现之后该做什么?
Common in ChinaCommon overseasDeep dive#stall-detection#intervention#rollback🔒 Unlock D5 to see the answer keys.
A verifier built to catch false completions - how do you confirm it is not tautological itself?一个防谎报的验证器,你怎么确认它自己不是恒真的?
Common in ChinaCommon overseasDeep dive#assertions#mutation-testing#probe-design🔒 Unlock D5 to see the answer keys.
D6 Crash Resume, the Budget Circuit Breaker and Governance Decay
An agent process that had been running for six hours gets killed - how should it come back on the next start?一个跑了六小时的 Agent 进程被杀了。你希望它下次启动时怎么恢复?
Common in ChinaCommon overseasDeep dive#crash-resume#checkpoint#idempotence🔒 Unlock D6 to see the answer keys.
Are a budget circuit breaker and a post-hoc cost report two different things, and what does each solve?预算熔断和事后成本报表是两件事吗?分别解决什么问题?
Common in ChinaCommon overseasIntermediate#budget#circuit-breaker#real-time-control🔒 Unlock D6 to see the answer keys.
Repeated context compaction makes an agent drift away from its original safety constraints - how would you defend against that?反复压缩上下文会让 Agent 逐渐不遵守最初的安全约束。你会怎么防?
Common in ChinaCommon overseasDeep dive#governance-decay#constraint-pinning#compaction🔒 Unlock D6 to see the answer keys.
You already have probes that check factual fidelity after compaction - why do they miss constraints being erased?你已经有一套压缩后的事实校验探针了,为什么它发现不了约束被擦掉?
Common in ChinaCommon overseasDeep dive#probe-blind-spot#constraint-fidelity#capability-boundary🔒 Unlock D6 to see the answer keys.
D7 Putting It Together: Let It Run All Night, Then Check the Work in the Morning
Six modules developed independently get merged into one system - what worries you most, and how would you find it?六个独立开发的模块合并进一个系统,你最担心出现什么问题?怎么发现它?
Common in ChinaCommon overseasDeep dive#silent-failure#module-merge#switch-experiment🔒 Unlock D7 to see the answer keys.
Design the morning report for an unattended run - what goes in, and what gets cut?设计一份无人值守运行的早间报告,你会放哪些内容、砍掉哪些内容?
Common in ChinaCommon overseasIntermediate#report-design#human-readable#single-source🔒 Unlock D7 to see the answer keys.
An agent ran overnight and finished 18 of 30 items - is that a good result or a bad one?Agent 跑了一夜完成了三十条里的十八条。这个结果算好还是不好?
Common in ChinaCommon overseasDeep dive#acceptance-criteria#false-progress#stop-reason🔒 Unlock D7 to see the answer keys.
Looking back at the whole harness, if you could keep only one module, which one and why?回顾整套 harness,如果只能保留一个模块,你留哪个?为什么?
Common in ChinaCommon overseasDeep dive#tradeoff-reasoning#trust-vs-throughput#course-recap🔒 Unlock D7 to see the answer keys.