Service 02 · Custom AI Agents

Custom AI agents that do the work, not just the talking.

A chatbot answers a question and forgets you. An agent has a job. It reads your real data, decides what should happen, acts inside your systems, and comes back with what it did and why — every step logged, and a human on anything that counts.

The Distinction That Matters

Chatbots answer. Agents finish.

Almost every business that has “tried AI” has tried a chat box. Someone types a question, the model produces a fluent paragraph, and then nothing happens — because the model has no hands. It cannot look up the actual order, cannot update the record, cannot send the thing, cannot check whether it worked.

An agent has hands. It is given a job, a set of tools it is permitted to use, and a definition of done. It can read your database, call your systems, draft the document, put it in front of a person for approval, and report back. When it is unsure, it says so instead of inventing an answer.

That is a software engineering problem far more than a prompt-writing one. Which tools it can touch, what it may do without asking, how it behaves when a system is down, what gets written to the log, and who is accountable for the output — those decisions are the build. The clever wording is the easy part.

What They Do

Jobs we give agents.

Read and decide

Take an unstructured pile — emails, documents, records, notes — and reach a defensible conclusion about what it is and what happens next.

Act in your systems

Create the record, update the status, raise the ticket, send the message. With permissions, so it can only do what it is allowed to do.

Talk to your customers

Intake, qualification and support that actually knows your business, holds a real conversation, and hands over to a person cleanly.

Work in a team

Several specialised agents with an orchestrator over them, because one enormous do-everything prompt is where quality goes to die.

Watch and alert

Monitor something continuously and speak up only when it matters — a background colleague rather than another dashboard.

Explain themselves

Show the reasoning and the sources behind an answer, so a person can check it in seconds rather than trusting it blindly.

We Eat Our Own Cooking

You are talking to one.

Ray — the assistant on this site — is one of ours. He reads what you write, works out what you actually need, drafts a build path, and hands it to a human before anything reaches you. He is not a widget bought from somewhere and dropped in; he runs on the same platform we build for clients.

That is deliberate. If our own agent were flaky, you would find out before we did, on our own front page, in front of everybody. The case studies cover the rest — agents in pharmacy operations, property, media production and market research — with the problem, the build and the awkward part written down honestly.

Non-Negotiables

How ours are built.

Least privilege. An agent gets the narrowest set of tools that lets it finish its job, and nothing beyond it.

Human in the loop where it counts. Anything that reaches a customer, moves money or touches a record of consequence gets a person’s signature.

Full audit trail. What it saw, what it decided, what it did, when. Not for compliance theatre — for the Tuesday when something looks wrong.

Graceful failure. Models and APIs go down. The agent degrades to something a human can pick up rather than dropping the work on the floor.

Model-portable. Built so the underlying model can be swapped as the field moves, because it moves every few months.

Questions

The ones we actually get asked.

What is the difference between an AI agent and a chatbot?
A chatbot produces text. An agent has tools, permissions and a definition of done — it can look up a real record, act in your systems, and confirm the job is finished. If it cannot do anything except talk, it is a chatbot no matter what the vendor calls it.
Can an agent work with the software we already use?
That is the normal case. Agents are connected to existing systems through their APIs, or through integration built for the purpose where no API exists. The aim is that the work happens where your team already works, not in another tab.
What stops it doing something stupid?
Scope and supervision. It only gets the tools it needs, anything consequential is reviewed by a person before it lands, every action is logged, and low confidence escalates rather than guessing. Those constraints are designed at the start, not added after an incident.
Which AI models do you use?
Whichever suits the job, and systems are built so the model can be swapped later. Model choice moves every few months, so anything welded to one provider is a liability by design.
Do we need our data in perfect shape first?
No. Data being a mess is the normal starting condition and part of what gets solved. What matters is that the data exists somewhere — getting it into a shape a model can reason over without inventing the gaps is part of the build.
The Rest of the Lab

These combine.

Most builds use two or three of them together. See all services.

Step One

Start with one honest sentence.

“Here’s what’s quietly eating my week.” Tell Ray in your own words. A clear, priced build path comes back, and a human signs off everything that leaves the lab.

Start the scan — free
Free scan · Fixed prices · You own everything