Blog
Running AI agents in production
Guides to running AI agents in production: observability, approvals, testing, cost and scheduling, and how we run our own company on AgentOS.
Guide · 9 November 2026A booking page that works while you do not
Three emails to find one time is too many. How a booking page with your hours and your calendar behind it fills the diary, and what to set up first.
Guide · 9 November 2026Be found: your site and what Google knows of it
A site nobody finds is a brochure. What to check on each page, what Google knows of it, and how to make the few changes that matter, week by week.
Guide · 9 November 2026Know what is wrong: your email, your site and your rivals
Three things go wrong without a sound: your email setup, your website and what competitors are doing. How to check each in plain words, and who decides.
Guide · 9 November 2026Not your job: having it built and run for you
Building an AI system is one job and keeping it running is another. Why owners forget the second, and what it means to have both done for you.
Guide · 9 November 2026Where an owner's week goes: the work around the work
Most of an owner's week is not the work they sell. How to name the work around the work, decide what to hand over, and start with one job.
Case study · 27 September 2026How we run AgentOS on AgentOS
Our support, outreach, onboarding and social posts run on our own agents. What that looks like, and four things it taught us.
Case study · 27 September 2026Every post on our LinkedIn page is drafted by an agent and approved by a person
How our company page is run by two agents and one approval, what went wrong, and what we changed.
Guide · 27 September 2026What shipped: late September 2026
Approvals that read like the thing being approved, a plain-language summary on every run, safer errors, and a new look across the product.
Guide · 26 September 2026How to add human approval to AI agents
Which agent actions need a person's sign-off, how an approval gate should work, and how to keep the queue from turning into a bottleneck.
Guide · 26 September 2026A weekly review for your AI agents
A short routine, in the same order every week, that catches the slow problems no alert fires for. With examples from our own fleet.
Guide · 25 September 2026What to log for every AI agent run
The record you need to answer "what did the agent do, why, and what did it cost", and the alerts that tell you when to look.
Guide · 20 September 2026Template: Inbound Support Triage
A ready-made agent that sorts your support inbox, answers how-to questions from your own product notes, and flags the rest for a person.
Guide · 13 September 2026Who owns an AI agent? Roles, audit and accountability
As agents take on real work, someone has to be accountable for each one. How to decide who can build, change and approve, and how to keep a record of it.
Guide · 6 September 2026Scheduling AI agents: what should run on its own
Which agents should wait to be asked and which should just show up, how to pick a cadence, and how to notice when a scheduled agent goes quiet.
Guide · 30 August 2026How to build a support inbox agent that knows when to stop
A worked example of a support agent that answers the routine questions, leaves the sensitive ones to a person, and shows its work.
Guide · 23 August 2026How to know when an AI agent breaks
Agents fail quietly. The signals worth watching, the alerts that catch them, and how to get from a failure to a fix without reading every run.
Guide · 16 August 2026Human-in-the-loop without the bottleneck
The difference between approving an action and answering a question, and how to bring a person into an agent's run only when it matters.
Case study · 9 August 2026What we learned from letting agents do our cold outreach
We built a pipeline of agents to find prospects and write to them. The writing worked. The finding did not. What we learned, and what we do now.
Guide · 2 August 2026How to trace AI agents you already run
Three ways to get a full trace of an agent you have already built, from a few lines of SDK to pointing your OpenTelemetry exporter somewhere new.
Guide · 26 July 2026What an AI agent really costs, and where it hides
Why the monthly bill is the wrong place to look, the usual sources of waste, and how per-agent budgets catch a runaway agent early.
Guide · 19 July 2026How to test an AI agent before it goes live
Write down what good looks like as test cases, check what the agent did and not only what it said, and run them after every change.