Which IT and DevOps tasks can agents take on?
- Monitoring: uptime, response times, error rates, Kubernetes pod health, database and disk usage, certificate expiry.
- Backups and snapshots: scheduled, verified, and taken before risky operations.
- Incident diagnosis: gathering logs, recent changes and resource graphs into a clear summary.
- Documented recovery: running known, pre-approved fixes for known failure patterns.
- WordPress maintenance: update checks, plugin audits and broken-link and form checks.
- Data updates: refreshing app data such as prices or catalogues through logged processes.
- IT helpdesk: access requests, password reset guidance and how-to answers from your documentation.
What have we done with this in-house?
Our website and infrastructure ops agent looks after self-hosted WordPress on Google Kubernetes Engine for the owner's businesses. In one real incident, a production site returned 503 errors because the MySQL disk was full. The agent diagnosed it, purged old binary logs, set a binlog expiry so it wouldn't recur, and grew the disk. The full story is on our use cases page. It's an in-house system, not a client result.
What does an IT ops agent team look like?
A monitor agent (read-only checks), a backup agent, a diagnosis agent, a recovery agent limited to runbook steps and a team lead that reports in chat. Observation and action are deliberately separated. See architecture.
What is in an IT team's stop rule?
- Alone: monitor, back up, verify backups, diagnose, run documented runbook steps for known incidents, and report.
- With approval: software and plugin updates, scaling that changes cost, database changes, restoring over live data and disk resizing outside agreed limits.
- Hard stops: deleting data, volumes or clusters; DNS, domain or access changes; secrets and IAM; anything unrecognised.
The agent drafts, routes and escalates. A person decides. Before anything is built we write down what the agent may do alone, what needs approval, and when it must stop and hand over with the full context attached.
How is the agent team put together?
Every team we build uses the same architecture: a team lead agent that plans and assigns work, specialist agents with narrow jobs and permissions, a shared task board where every task and approval is visible, tools and connectors limited to what each agent needs, scheduled routines for recurring checks and reports, and approval gates wherever money, customers, data or irreversible changes are involved. Every action is logged, live systems are backed up before edits, and a daily summary arrives in chat so a person always knows what happened.
It is the same pattern we use in-house for our 14-bot SEO team, ads agent and site ops agent on the owner's own businesses (in-house systems, not client results). For a new team we start small, usually a specialist, a reporter and the team lead, and add agents only once the first ones are trusted. See how we build agent teams and real in-house use cases.
What should you prepare before talking to us?
You don't need a technical brief. A useful first conversation needs only a few things, and gathering them is valuable even if you never work with us:
- The process in plain words: what triggers it, who does what, and where it usually goes wrong.
- Rough volumes: how many messages, orders, tickets or invoices per week. A one-week tally is enough.
- Your tools: WhatsApp app or API, CRM, sheets, accounting or helpdesk software, including versions or plans where you know them.
- Three real examples: typical messages or cases, plus one awkward one, with personal details removed.
- What must never happen: the mistakes that would hurt most. These become the first lines of your stop rule.
- An owner: the person who will review the workflow once it runs.
Send these on WhatsApp or by email, or run the pilot scorecard first.
How do you know whether the pilot worked?
We agree the success measure before building, and it should be something your team can count without a dashboard project. Typical measures include the share of enquiries logged the same day, time to first response, the number of follow-ups that actually happened, hours spent on the task per week, or the number of escalations that were correctly flagged. We count the baseline before launch (even by hand for a week) and again after a few weeks of running.
We also review the qualitative side with the people involved. Do they trust the drafts? Are handovers arriving with enough context? Are customers asking for a person more or less often? A pilot can hit its number and still need tuning, or miss it and teach you something important. Either way, the decision to keep, tune, expand or stop is yours, made on evidence. We don't publish generic success figures, because results depend on your process, volumes and team.
How does a pilot with us work?
Every engagement follows the same four steps. Consult: you walk us through the process, the tools and where it breaks. Pick the pilot: we choose one workflow and write down its inputs, outputs, tools, stop rule and success measure. Ship: we build it into the tools you already use and test it on real cases. Review: your team checks what the agent did and what it escalated, then decides whether to tune it, expand it or stop. Read the full pilot process.