ON new email or web form
Inbox and enquiry triage
Every message read, sorted by type and urgency, and the useful details pulled out. The right item reaches the right person with the context already attached.
auto-routed, sender gets a first reply
The ops floor that runs before anyone clocks in.
AI workflow automation that runs your busywork while you run the business.
We design, build and run AI workflows for UK businesses. The triage, the drafting, the filing and the chasing that quietly eats staff hours, handed to systems that do it the same way every time and log every step for a person to check.
RUN 01 What we mean by workflow automation
Watch a channel, understand what arrived, do the next step, log everything.
Workflow automation is not a mystery. Something arrives on a channel worth watching: an inbox, a web form, a phone line, a shared folder. An AI step reads it and works out what it is. The system then does the next obvious thing, drafts a reply, files a document, updates a record, notifies a person, and writes down what happened so a human can check the trail later.
That is the whole shape of it. Watch, understand, act, log. The intelligence sits in the understanding step, where older rules-based automation used to break the moment an email was phrased differently or a form was filled in the wrong order. An AI reading step copes with the mess that real work throws at it.
What it is not: it is not a chatbot bolted onto your website, it is not a stand-in for human judgement, and it is not a robot clicking around your screen pretending to be a person. Those are different jobs. Redesigning a whole process, or reading your own documents to answer questions, live one step along from here, and we link to both further down.
The four moves
- Watch: keep an eye on the inbox, form, folder or line.
- Understand: read it and decide what it actually is.
- Act: draft, file, update, route or notify.
- Log: record every step for a human to audit.
A good workflow feels almost boring after launch. That is the point.
RUN 02 What we automate first
The work that repeats, follows a pattern, and steals whole afternoons.
ON document or invoice arrives
Document filing with an audit log
Invoices, certificates and PDFs read, the key fields extracted, filed in the right place and recorded in a log that shows exactly what happened and when.
exceptions held for a human
ON reply needed
Drafting replies and follow-ups
A first draft written in your tone, with the relevant record and history in front of it, ready for a person to glance at, adjust and send.
awaiting approval before it sends
ON record changes
CRM hygiene and stage nudges
Contacts matched and tidied, duplicates flagged, stages moved as things progress and a quiet nudge raised when a deal has gone silent for too long.
no silent overwrites
ON schedule, weekly
Weekly digest reporting
The numbers and events that matter compiled into one short digest, so the team starts Monday knowing where things stand without anyone building a spreadsheet.
delivered before the week starts
ON renewal or deadline nears
Compliance and renewal chasing
Certificates, licences and recurring obligations tracked, with a notice drafted and the right people prompted well before the date, not after it has passed.
notice drafted, held for sign-off
Every one of these keeps a human checkpoint. Anything that reaches a customer, moves money or carries risk waits for a person to approve it. The system does the reading and the routing. People keep the decisions that ought to stay with people.
RUN 03 Where this goes deep
One workflow usually needs three other things done well.
This is the umbrella. When a build gets serious it leans on the engine that keeps it reliable, the wiring into your tools, the knowledge layer that grounds its answers, and the process work that comes before any of it. Here is where each of those lives.
The engine room
The workflow engine that runs it all
Retries, error handling, self-hosting and the reliability work that keeps automations running when an API has a bad day. Open → The wiringCustom AI integrations
Connecting the tools you already pay for: CRM, Gmail, WhatsApp, Slack, Drive, databases and internal APIs. Open → The knowledge layerGrounded knowledge systems
Answers drawn only from your own documents and policies, with sources shown and out-of-scope questions refused. Open → The practiceBusiness process automation
The harder work of redesigning a process before you automate it, so you are not paving over a broken path. Open →RUN 04 How an engagement runs
First workflow live in weeks, not quarters.
-
01 · Listen
We watch the actual work
A few days sitting with the team, seeing where information gets copied between apps and where the same judgement call gets made over and over. The best first workflow is almost always already there, in plain sight.
-
02 · Map
We pick one and draw its checkpoints
One workflow, chosen because it repeats and has visible cost. We agree the trigger, the steps, and exactly where a human has to approve before anything leaves the building.
-
03 · Build
We ship something real, early
The first workflow goes live in weeks, running on real data with the approval gate switched on from day one. You watch it work before we widen the scope, not after months of quiet building.
-
04 · Run
We keep it honest
Monitoring on the runs, alerts to the person who can actually fix a problem, and a monthly review of failures and missed cases. A workflow that fails quietly is worse than no workflow at all.
RUN 05 Real cases
Workflows we have put into production.
UK clinic, professional services · anonymised
Invoice triage that handed back four hours a week
A clinic team spent hours each week reading supplier invoices and filing them by hand. We built a workflow that polls the inbox, classifies each message, reads the fields, files into two document stores and writes an audit log. Exceptions wait for a person. It replaced roughly four hours a week of bookkeeping admin.
Read the finance operations case →Four UK businesses · anonymised
A content pipeline that publishes weekly with no writer on payroll
Research, outline, draft, quality check, image and publish, handled by an orchestrated set of AI workflows that produce a finished article in a fraction of the usual time. Four UK businesses now publish on a weekly cadence without keeping a writer on staff, and a human still signs off before anything goes live.
Read the growth engine case →Healthcare group · anonymised
Enquiries from the website and WhatsApp into one queue
Messages arrived from a website widget and WhatsApp with inconsistent handoff. We built routing that standardises the message, works out the intent, records the conversation and sends the right summary to the right team. One operational view across two front doors, with logging throughout.
Read the routing case →Names redacted out of respect for our clients. We can share full details on a call.
RUN 06 How we quote
Three shapes of work, quoted to your process.
First workflow
Two to four weeks
- One workflow, live.
- Real data and a visible result.
- Human approval gate built in.
- Fixed quote before we start.
Production system
Six to ten weeks
- Several linked workflows.
- Monitoring, retries and alerts.
- Documentation and staff handover.
- Quoted fixed after discovery.
Managed & monitored
Rolling monthly
- We watch the runs, not you.
- Monthly review of failures.
- Fixes and dependency changes.
- One named point of contact.
A number on a website is priced to the website, not to your process. We quote each build as a fixed figure after a discovery call, once we know how many systems we are connecting and how much judgement the workflow carries. Model usage, hosting and third-party platform fees are itemised separately and shown before anything goes live.
RUN 07 The quieter cost
What it costs to leave the busywork where it is.
A single recurring task that takes one person four hours a week is not really four hours. Over a year it is more than 180 hours, the better part of a working month, spent on something a system could do the same way every time.
We saw exactly that with a UK clinic. Invoice triage, roughly four hours a week of a bookkeeper's time, replaced by a workflow that files everything and keeps the audit log. The point of the number is not the money it frees up. It is what those hours were being pulled away from.
RUN 08 Questions
Answers before the call.
What is AI workflow automation, and how is it different from normal automation?
Normal automation follows fixed rules: if this exact thing happens, do that exact thing. It breaks the moment reality is phrased differently. AI workflow automation adds a reading step. The system understands a messy email, a scanned invoice or an oddly worded enquiry, decides what it is, then runs the right next action and logs it. Same plumbing, far fewer broken rules.
Is AI automation worth it for a small business?
Often yes, but not always, and we will tell you when it is not. The test is simple: is there a repeated task, done the same rough way each week, that eats real hours and follows a pattern a person could describe? If the volume is tiny, we will say so and save you the spend. If it is a few hours every week, automation usually pays for itself quickly.
How much does AI workflow automation cost in the UK?
The honest answer is that it depends: on how many systems we connect, how much judgement the workflow needs and how much of the process wants rebuilding first. A figure produced before we have seen any of that would be a guess dressed up as a price, so we do not publish a rate card. Instead, a thirty-minute discovery call gets you a fixed quote for your actual process, with model usage and hosting itemised separately. Our guide to AI workflow automation costs breaks down what moves the number.
How long does implementation take?
A focused first workflow is usually live in two to four weeks, not two to four quarters. A larger production system with several linked workflows, monitoring and documentation tends to take six to ten weeks. We build in stages so you see something real early, rather than waiting months for a single big reveal that may have drifted from what you needed.
Do you replace our existing tools?
No. We build around the systems you already run: your CRM, your inbox, your document store, your phones. The automation reads from and writes to those tools rather than asking your team to learn a new platform. If a tool genuinely cannot support a reliable connection, we will say so early, before any budget is committed, rather than forcing an awkward workaround.
Who owns the system after delivery?
You do. The workflows, the accounts, the credentials and the documentation are yours. We run our own infrastructure and can host and monitor the system for you, but that is a service you choose, not a lock-in you are trapped by. If you ever want to bring it fully in-house or move it elsewhere, the handover pack is written so another competent team can pick it up.
Is it GDPR-compliant for UK data?
It can be, and that starts at design, not as an afterthought. We map what personal data the workflow touches, keep it to the minimum, decide what is logged and set retention and access rules. For higher-risk uses we recommend a DPIA before go-live. The ICO guidance on AI and data protection is the standard we design against for UK work.
Does it replace staff?
Mostly it replaces tasks, not people. The work we automate is the repetitive reading, sorting, filing and chasing that few people enjoy and that keeps them from the judgement work only they can do. In small teams that usually means the same people getting their week back. We have not been asked to help a client cut headcount, and it is not what we sell.
Form · 02 · AI Workflow Automation enquiry
Tell us what eats your team's week.
30 minutes. We'll tell you honestly whether automation pays for itself in your case.