AI agents

We build AI agents that take actions in your systems, with scoped tools, guardrails, and approval gates.

Support that resolves tickets

An agent that reads the ticket, checks the customer record, fixes what it can, and escalates the rest with the full context attached.

Back-office automation

Data moved between systems that don't talk to each other: orders into accounting, emails into the CRM, reports into spreadsheets.

Real-time voice agents

Booking, intake, and answering lines built on the OpenAI Realtime API. Callers get answers, your team gets structured records.

Research and monitoring

Agents that watch sources, gather what changed, and deliver a digest a human can act on, on a schedule.

Kept on a leash.

Before an agent goes anywhere near production, we settle what it's allowed to do. Every agent we ship comes with three controls.

Scoped permissions

An agent can only touch the tools we give it. Read access is cheap to grant, write access is earned per action.

Approval gates

Anything irreversible, like sending money or deleting records, waits for a human click. The agent prepares, you approve.

Full audit trail

Every tool call and decision is logged. When something looks off, you can replay exactly what happened and why.

Anatomy of an agent we'd ship

Every agent is a loop of model calls and tool calls. A production agent needs more around that loop than a demo does. This is what we add.

A tool layer with the narrowest permissions that do the job
Memory and state, so it picks up where it left off
Approval gates before anything irreversible
Hard budget caps per run, so a bad loop costs cents, not hundreds
Full logging, so any run can be replayed and explained
Evals on real cases, so changes get measured before they ship

When we say no

Agents add cost, latency, and new ways to fail. If your workflow has fixed steps and clean inputs, we'll tell you a plain script beats an agent, and build that instead. The agent projects we take on are the ones where messy input or case-by-case judgment makes the loop worth its price.

Questions clients ask

Short answers, no sales language. If yours isn't here, ask an engineer directly.

Ask us anything

What stops an agent from doing something wrong?

We assume the model will sometimes be wrong, and we make those mistakes cheap. Agents get the narrowest set of tools that does the job, destructive actions sit behind human approval, and every step is logged.

Agent or automation script, how do you choose?

If the steps are fixed and the input is clean, a script is cheaper and more reliable, and that's what we build. An agent earns its cost when the input is messy human language or the path changes case by case.

What do you build agents with?

The OpenAI Agents SDK, the Claude Agent SDK, and the Vercel AI SDK, chosen per project. All of them come down to a model calling tools in a loop. Most of the engineering is in the tools, guardrails, and evals around that loop.

What does running an agent cost?

More than a single AI call, because an agent thinks in steps. We design the loop for cost with smaller models on routine steps, caching, and hard budget caps per run, and you see projected costs before anything ships.

What is the difference between an AI agent and a chatbot?

A chatbot answers questions. An agent takes actions. A chatbot can tell a customer the refund policy. An agent can look up the order, check the policy, prepare the refund in your system, and ask a person to approve it. That extra power is why agents need scoped tools, approval gates and logs. If answers are all you need, a chatbot costs less.

AI agents: all posts

Have work an agent could take over?

Describe the workflow. We reply with whether an agent fits, and what it would take.

Start a project Book a meeting