--- title: "Agent operations Articles | Len P. van der Hof" description: How to run and retire production agents so credentials, triggers, and spend stop when the agent should stop. image: "https://lenvanderhof.com/photos/len-portrait-1.jpg" --- Tag # Agent operations How to run and retire production agents so credentials, triggers, and spend stop when the agent should stop. AI Systems ## [Agent audit trail: reconstruct the action, approval, and outcome](https://lenvanderhof.com/en/blog/agent-audit-trail/) If the only witness is the agent, you do not have an audit trail. You have a testimony. Len P. van der Hof3 October 2026 AI Systems ## [Agent runtime budget: keep retries inside the same ceiling](https://lenvanderhof.com/en/blog/agent-runtime-budget/) A cap that resets on every retry is a cap per attempt, not per task. Len P. van der Hof3 October 2026 Venture Building ## [An agent scorecard turns output review into a permission decision](https://lenvanderhof.com/en/blog/agent-scorecard-vs-thumbs-up/) One good-looking brief can hide an unsupported claim. Grade the work against the job it was given, then decide what the role may do next. Len P. van der Hof27 October 2026 AI Systems ## [Agent shadow mode: evaluate proposals before granting action rights](https://lenvanderhof.com/en/blog/agent-shadow-mode/) Let the agent be wrong on paper first, where a mistake costs a comparison instead of a customer. Len P. van der Hof4 October 2026 AI Systems ## [The Agent Trust Ladder: how an AI role earns autonomy](https://lenvanderhof.com/en/blog/agent-trust-ladder/) A scorecard records how the role performed. The ladder decides what it may do next. The action still sets the ceiling. Len P. van der Hof30 October 2026 AI Systems ## [AI fake citations: a 15-minute check for the claims that matter](https://lenvanderhof.com/en/blog/ai-fake-citations-check/) A citation makes two claims: this document exists, and it says this. Check both in the source itself, not by asking the tool. Len P. van der Hof19 October 2026 AI Systems ## [Cost per route vs the monthly AI bill: meter where the money goes](https://lenvanderhof.com/en/blog/cost-per-route-vs-monthly-bill/) A flat monthly bill can hide a route that doubled its spend. Attribute each charge, separate volume from cost per request, and give the route an owner. Len P. van der Hof7 November 2026 AI Systems ## [Governed agent memory: what may persist, and who may write it](https://lenvanderhof.com/en/blog/governed-agent-memory/) An agent's memory is a database that the agent writes itself. Give it the rules you would give any other database. Len P. van der Hof30 September 2026 AI Systems ## [How many AI agents can one person supervise?](https://lenvanderhof.com/en/blog/how-many-agents-can-you-supervise/) Starting another agent is a one-time decision. Reading its work, checking its handoffs and handling its exceptions come back every week. Len P. van der Hof28 October 2026 AI Systems ## [When nobody approves in time, your AI agent must not act](https://lenvanderhof.com/en/blog/human-approval-timeout-test/) An expired request records silence. A rejected request records a decision. Both must block the action. Len P. van der Hof20 October 2026 AI Systems ## [Model registry vs vendor list: know which models run](https://lenvanderhof.com/en/blog/model-registry-vs-vendor-list/) A contract can clear a supplier while a production model remains unknown. Compare actual calls with the register before you trust it. Len P. van der Hof1 November 2026 AI Systems ## [Privacy tier vs vendor promise: which data may reach a cloud LLM?](https://lenvanderhof.com/en/blog/privacy-tier-vs-vendor-promise/) A vendor's privacy page describes the vendor. A privacy tier describes your data and decides which model hosts may receive it. Len P. van der Hof6 November 2026 AI Systems ## [Prove you can stop an agent: interrupt the run and revoke access](https://lenvanderhof.com/en/blog/prove-you-can-stop-an-agent/) An instruction to stop is a request. A stop is a control that someone outside the agent can operate. Len P. van der Hof30 September 2026 AI Systems ## [How to retire a production agent (stopping it is not enough)](https://lenvanderhof.com/en/blog/retire-a-production-agent/) A stopped agent is not a retired agent. The next schedule, a copied key or a monthly plan can keep it working and billing. Len P. van der Hof5 October 2026 Venture Building ## [What is a roster? From the Monday rota to a team of AI agents](https://lenvanderhof.com/en/blog/roster-meaning/) The word started as a Dutch gridiron. The idea still fits your staff, your agencies and your AI agents. Len P. van der Hof1 October 2026 Venture Building ## [When credible sources disagree: diagnose before choosing sides](https://lenvanderhof.com/en/blog/source-disagreement-vs-tiebreak/) Before you back the source with the bigger name, check whether the claims actually conflict. Then name the check that could help resolve whatever disagreement remains. Len P. van der Hof6 November 2026 AI Systems ## [TRACE vs RAG: one fetches the text, the other checks what it proves](https://lenvanderhof.com/en/blog/trace-vs-rag/) An answer can quote the right document and still draw the wrong conclusion. Len P. van der Hof28 September 2026 Venture Building ## [Trigger map vs cron job: a schedule is one row, not the map](https://lenvanderhof.com/en/blog/trigger-map-vs-cron-job/) A weekly brief can start at nine. A client email, an arriving draft and a repeated form submission still need routes of their own. Len P. van der Hof28 October 2026 AI Systems ## [What is ROSTER? How one person manages a team of AI agents](https://lenvanderhof.com/en/blog/what-is-roster/) A role is defined by what it may not do. Six written decisions turn an AI agent into a specialist you can grade, fix or retire. Len P. van der Hof26 September 2026 AI Systems ## [What is TRACE? Five steps to check research before you act on it](https://lenvanderhof.com/en/blog/what-is-trace/) Three links can be one source. TRACE is how you find out before the decision does. Len P. van der Hof25 September 2026 AI Systems ## [When not to use an AI agent: five signs, and what to use instead](https://lenvanderhof.com/en/blog/when-not-to-use-an-agent/) An agent earns its cost only when the next step depends on what it finds. Most tasks never get there. Len P. van der Hof28 September 2026 AI Systems ## [Why your RAG answer is wrong: find the broken step before you change the model](https://lenvanderhof.com/en/blog/why-your-rag-answer-is-wrong/) The model is the last thing to blame, not the first. Len P. van der Hof18 October 2026