Busywork
handled.
You stay
in charge

I design and build connected AI systems for small and growing businesses. They read what comes in, know your documents, keep your records up to date, report back in plain English, and ask before doing anything that matters.

Your system · this morning Illustration
  1. 3 new enquiries sortedAdded to your customer list. Replies drafted in your tone.
    Done
  2. Invoice from Harbour SuppliesLine 4 doesn’t match the price you agreed. Held for you.
    Needs you
  3. “What’s our refund window?”Answered for Jess, with a link to the policy it came from.
    Done
  4. Weekly sales summaryUp on last week. Chart and three key points ready.
    Ready
2 things waiting for your OKReview

01 What this actually is

Not a chatbot.
A system

Most people meet AI as a chat window. Handy, but it can’t see your inbox, doesn’t know your price list and can’t update your records.

A business AI system is different: a few connected pieces, each with one clear job, working inside the tools you already use.

Part one

It reads.

Emails, web forms, invoices, order sheets, your own documents and your sales figures. It picks out what matters and files it in the right place.

Part two

It does.

Updates your spreadsheet or customer list, drafts the reply, prepares the quote, builds the report. The repetitive steps you’d otherwise do by hand.

Part three

It checks in.

Anything important waits for your OK. Everything it did is written down, so you can see what happened, why, and what it cost.

02 The building blocks

Eight pieces.
One control
room

You don’t need all of them. Most businesses start with one or two. Tap a piece to see what it does, in plain English.

Every piece reports to the control room. That’s where you approve things and see what happened.

Enquiry autopilot Demo planned

New enquiries sorted before you’ve opened them.

When a message, form or booking request arrives, it’s read, sorted by what the person wants, logged in your customer list, and answered with a draft reply that waits for your OK.

Before

Copy the name, paste it in the spreadsheet, write the same reply again.

After

It’s already logged and the reply is drafted. You tap approve.

  • Quote requests
  • Bookings
  • Support emails
  • Lead follow-up

The nerd name Workflow automation + structured extraction

Watch the animated version

Knowledge assistant Demo planned

Answers from your own documents. With receipts.

It reads your policies, price lists, manuals and FAQs, then answers staff or customers in seconds and shows exactly which page each answer came from. If it isn’t sure, it says so and passes the question to a person.

Before

“Where’s that policy again?” Twelve times a day.

After

Instant answer, with a link to the source. New staff get up to speed faster.

  • Staff handbooks
  • Customer FAQs
  • Product details
  • Procedures

The nerd name Retrieval-augmented generation (RAG) with citations

Paperwork reader Demo planned

Documents in. Clean, checked data out.

Invoices, order forms, applications, even phone photos of paper. The important details are pulled out, checked against what you expected, and laid out on a review screen before anything is saved.

Before

An afternoon of squinting at PDFs and typing numbers into boxes.

After

A tidy review screen. Mismatches are flagged in red. Glance, approve, done.

  • Supplier invoices
  • Order forms
  • Applications
  • Receipts

The nerd name Multimodal document extraction with human review

Connectors Part of every build

It plugs into the tools you already use.

No need to move your business onto something new. The system connects to your email, spreadsheets, customer list, calendar or accounting software, and only gets the access each job actually needs.

Before

Five apps that don’t talk to each other, and you as the go-between.

After

Information moves between them on its own, the same way every time.

  • Email
  • Spreadsheets
  • CRMs
  • Calendars
  • Accounting

The nerd name Integration layer with least-privilege tool access

Control room Flagship · In development

One screen to see, approve and steer everything.

The heart of the system. A simple dashboard showing what each piece did today, what’s waiting for your approval, anything that went wrong, and what it all cost. Approve, edit or reject with one tap.

Before

“Is the AI doing anything? Did that email actually go out?”

After

A clear history of every action, a queue of things to approve, and a spending total.

  • Approvals
  • Activity history
  • Error alerts
  • Spending limits

The nerd name Agent harness + operations console

Ask your numbers Working demo

Ask a question. Get a chart back.

Type “how did each location do last quarter?” and get a clear dashboard built from your real data, with charts, maps and a few key points. The numbers on screen come straight from your data, never from the AI’s imagination.

Before

“I’ll get that report to you by Friday.”

After

The answer, with a chart, before your coffee cools.

  • Sales reports
  • Stock levels
  • Customer trends
  • Team dashboards

The nerd name Tool-calling analytics agent + generative UI

Try Agent Workbench, the live demo

Custom apps Demo planned

The screens your team and customers actually use.

A booking page, a customer portal, a members’ area or an internal tool that replaces three spreadsheets. Sometimes AI is part of it, sometimes it isn’t. Good software doesn’t need AI to be useful.

Before

A patchwork of spreadsheets, shared inboxes and sticky notes.

After

One tidy app, with logins, built around how you actually work.

  • Portals
  • Booking systems
  • Internal tools
  • Membership sites

The nerd name Full-stack web application

Marketing studio Demo planned

A brief in. A week of drafts out.

Describe a promotion or announcement once, and get matching drafts for email, social posts and your website, all in your brand’s voice. Nothing is published until a person has edited and approved it.

Before

Writing the same news five different ways for five different places.

After

Consistent first drafts in minutes. You do the final polish.

  • Newsletters
  • Social posts
  • Product copy
  • Short videos

The nerd name Multi-stage content pipeline with brand context

Research desk Demo planned

Homework done, sources attached.

Ask it to look into a competitor, a supplier or a new market. It searches, reads, keeps track of where every fact came from, and hands back a short report you can check line by line.

Before

Forty open tabs and a half-finished document.

After

A clear summary with every claim linked to its source.

  • Competitor checks
  • Market research
  • Supplier vetting
  • Briefings

The nerd name Research orchestration with source tracking

03 A day with the system

How the
pieces work
together

Here’s an ordinary Tuesday at a small wholesale business. Each piece does its bit, and they share what they know.

  • Reads & reports
  • Knows & flags
  • Checks & drafts
  • You

An illustrated example. Every business’s version is a little different.

  1. Enquiry autopilot

    An order arrives by email.

    “Could we get 24 cases of the oat milk and 10 of the cold brew for Friday?” The items, quantities and delivery date are picked out and matched to the customer’s account.

  2. Knowledge assistant

    Prices and stock are checked.

    The customer’s agreed prices come from your price list. One item is low in stock, so that line is flagged rather than promised.

  3. Control room

    A confirmation is drafted and waits.

    Order confirmation and invoice ready, with the stock note included. It sits in your approval queue. Nothing has been sent.

  4. You

    You approve it from your phone.

    One tap. The email goes out, the order is logged, and your spreadsheet updates itself. Total time from you: about ten seconds.

  5. Paperwork reader

    A supplier invoice turns up as a PDF.

    Every line is read and compared with the purchase order. Line 4 is charged at the old price, so it’s highlighted for you instead of being filed.

  6. Knowledge assistant

    A new team member has a question.

    “What do we do if a delivery arrives damaged?” Answered in seconds, with a link to the exact paragraph in your returns procedure.

  7. Ask your numbers

    “How did this week compare to last?”

    A chart of sales by product and a few plain-English observations, built from your real figures, ready before you leave.

04 Ground rules

What you can
count on

AI is powerful, and sometimes wrong. So every system is built around a few rules that don’t bend.

1

Nothing important happens without your OK.

Sending emails, changing records, paying or ordering anything: those wait in your approval queue until you say yes.

2

It shows its work.

Answers come with sources. Every action is logged, so you can always see what happened and why.

3

It only touches what it needs.

Each piece gets the smallest access that does the job. The assistant that answers questions can’t edit your accounts.

4

Spending has a ceiling.

AI usage costs money, usually small amounts. You see the running total, and hard limits stop surprises.

5

Mistakes get caught.

Outputs are checked automatically, odd results are flagged, and errors are retried or brought to you, not quietly ignored.

6

Your information stays careful.

Passwords and keys stay on the server, sensitive details are kept out of logs, and the AI only sees what a task requires.

05 How you’d get there

Start with
one piece

You don’t buy the whole thing up front. Each stage is useful on its own, quoted in advance, and the next one only happens if the last one earned its place.

  1. Stage 1

    Fix one annoying job.

    We pick the most repetitive thing in your week and automate it, with you approving the important bits.

    e.g. enquiries logged and replies drafted

  2. Stage 2

    Connect a second piece.

    Once the first is running smoothly, add another that shares what it knows. Now they start helping each other.

    e.g. replies now use your real price list

  3. Stage 3

    Run it from one place.

    The control room ties everything together: one queue of approvals, one history, one spending total.

    e.g. your whole back office on one screen

Not sure where to begin? The AI consultation is a short session to find the realistic wins, and the ones that aren’t worth it.

06 Where things stand

The honest
progress
report

I’m building a complete, working version of this system as a public demonstration, one piece at a time. It will live at its own address so you can try it yourself. Until then, here’s exactly what exists.

  • Working demo
    Ask your numbersAgent Workbench: ask questions about real retail and games data and watch the dashboard build itself. Try it live ↗
  • In development
    Control roomThe approvals, history and spending dashboard that ties the pieces together.
  • Demo planned
    Everything elseEnquiry autopilot, knowledge assistant, paperwork reader, research desk, marketing studio and a custom business app.

Demo status describes the public showcase. Each piece can be built for your business now, scoped and quoted up front.

07 Good questions

Before you
ask

Do I need all eight pieces?

No, and most businesses never will. Start with the one that would save you the most time. Each piece is useful on its own; connecting them is a bonus, not a requirement.

Will it replace my staff?

It’s designed to take the repetitive parts off people’s plates, like copying details, chasing paperwork and answering the same question again. The judgement calls, relationships and interesting work stay with your team.

What does it work with?

Usually the tools you already have: email, spreadsheets, your customer list, calendar or accounting software. If a tool has a way for other software to connect to it, it can normally be included. We check this together before anything is quoted.

What does it cost to run?

There’s the one-off cost of building it, quoted up front, and then small ongoing costs for AI usage and hosting. The control room shows what’s being spent, and hard limits mean it can’t run away from you.

What if the AI gets something wrong?

The system is built expecting that it sometimes will. Important actions wait for your approval, answers show their sources, numbers come straight from your data, and every step is logged so mistakes are easy to spot and fix.

Is my data safe?

Security is designed in from day one: access is limited to what each job needs, passwords and keys never sit in a web browser, sensitive details are kept out of logs, and anything consequential needs a human yes.

How long does it take?

It depends on what we build first. A single focused piece is a much smaller project than a whole system, which is exactly why we start there. You get a clear scope and timeline before work begins.

08 Your move

What would you
hand over
first?

Tell me about the task you’d most like to stop doing. I’ll tell you honestly whether a system would help, and what the first step would look like.