Every step but one.
Fettler is an AI services company. We build custom agents, skills, automations and integrations for mid-market businesses, then run and monitor them inside your systems, under your approval.
Working with 40+ clients across sizes and industries.
Built for Shift production and downtime capture
Every AI agent we build has the same six parts.
The trigger changes. The approver changes. The six parts don't.
Part 1 of 6
Trigger
Shift ends. It starts.
it starts itself
Part 2 of 6
Read
Reads the shift log, sheet or photo, against the line plan.
ERP, PDFs, portals, mail, sheets, photos
Part 3 of 6
Decide
Output against plan. Every stoppage against a reason code.
your rules, your tolerances, your definitions
Part 4 of 6
Act
Drafts the shift record. Updates the shipment plan.
posts, files, drafts, emails, updates
Part 5 of 6
Escalate
No reason code? Held for the shift supervisor to name.
ambiguity goes to a person, never a guess
Part 6 of 6
Log
Every entry, rule, decision and output. On record.
every input, rule and output, auditable
Six parts. One agent. One person with the pen.
Awaiting release: The plant manager signs off the shift.Signed off. Posted. Logged.
Demonstration data. Not a client system.
Built for manufacturing · Shift production and downtime capture
How this agent is built
- Trigger Shift ends. It starts. Shift clock
- Read Reads the shift log, sheet or photo, against the line plan. Line camera
- Decide Output against plan. Every stoppage against a reason code. Downtime counter
- Act Drafts the shift record. Updates the shipment plan. Record press
- Escalate No reason code? Held for the shift supervisor to name.
- Log Every entry, rule, decision and output. On record.
Released by: The plant manager signs off the shift.
Built for shipping and logistics · Export documentation pack
How this agent is built
- Trigger Shipment confirmed. It starts. Container hoist
- Read Pulls in the invoice, the packing list and the letter of credit. Document feeder
- Decide Every field, checked against the letter of credit. Field rails
- Act Assembles the pack. Drafts the message to the buyer. Pack binder
- Escalate A field mismatch? Held for the export desk, both values shown.
- Log The documents, the checks, the release, the delivery. On record.
Released by: The export desk releases the pack.
Built for hospitality · Purchase to pay matching, across every property
How this agent is built
- Trigger A supplier invoice lands, from any property. It starts. Property key rack
- Read Reads the invoice, the purchase order and the goods receipt. Three-tray intake
- Decide Price and quantity, against the agreed tolerance. Three-way scale
- Act Prepares the matched invoice. Schedules the payment run. Payment spool
- Escalate Outside tolerance? Held for the category buyer, both values shown.
- Log The three records, the matching rules, the release, the payment schedule. On record.
Released by: The category buyer clears any variance.
Built for multi-site consumer operations · Store stock balancing
How this agent is built
- Trigger 06:00. It starts, before the first store opens. Store lamp row
- Read Reads stock, sales and transfer limits at every site. Stock probe
- Decide Which sites run short. Which hold too much. Site map disc
- Act Drafts the transfer list and the replenishment quantities. Transfer arm
- Escalate A transfer outside the limits? Held for retail operations.
- Log Every count, rule and transfer. On record.
Released by: Retail operations approves transfers and replenishment quantities.
Built for business services · Inbound at scale
How this agent is built
- Trigger A message arrives. It starts. Antenna array
- Read Mail, chat or form. Reads it, with the case history. Inbox hopper
- Decide Classifies it. Finds the owner. Sorting fan
- Act Drafts the reply, in your voice. Reply pen
- Escalate Critical language? Straight to a named responder, within minutes.
- Log Every message, route and reply. On record.
Released by: A named responder releases every reply.
“Our agents take the work your team shouldn’t be doing, and stop at the one step that should stay yours: the approval.”
Not a chatbot
A chatbot answers. An agent finishes the task: the document is filed, the entry is posted.
Not recorded clicks
A recorded click sequence breaks the week a screen moves. An agent reads meaning.
Not a dashboard
A dashboard waits to be opened. An agent acts on the number and tells the person who needs to know.
The problem
Most mid-sized businesses do not have a technology problem. They have too much work going through too few hands.
- The hours don't go into making things. They go into re-typing things.
- Buying another module moves the typing, it does not remove it.
- The exceptions never make it into any system.
The usual programme, and ours.
-
Scope
The usual way
A platform rollout that touches every department at once.
With us
One workflow at a time, each paying for itself before the next.
-
Time to real work
The usual way
A programme measured in quarters, with a pilot at the end.
With us
The first agent doing real work by week six.
-
Proof
The usual way
A demo on sample data and a steering committee sign-off.
With us
Parity with your manual process, reconciled to zero difference, before anything is switched off.
-
Pricing
The usual way
Seats, licences and time-and-materials meters.
With us
A fixed price per workflow and a monthly fee to run it.
What we deliver
Custom AI agents, skills, automations and integrations.
You buy one workflow at a time, not a platform to grow into. Our agentic AI services cover the workflow, the connections and the work of keeping it running.
Agents
A digital worker that owns a whole workflow end to end.
builds the full export documentation pack and stops on any mismatch
Skills
One reusable competence that any agent or any person can call.
one "read a supplier invoice" skill, every vendor, every layout
Automations
Scheduled unattended runs, with monitoring and retries.
the daily close pack is on the desk before the desk is occupied
Integrations
Getting data out of systems never meant to share it: a legacy ERP, a supplier portal, bank mail, PDFs.
platform integration where no API was ever published
Find your workflow
The work is different. The approach holds.
Explore 283 workflow ideas across sales, marketing, HR, customer service, procurement and nine industry groups. Each brief sets out the work and the human approval it needs.
Already running
AI workflows already running in business operations.
We describe them by what they do rather than by who they belong to.
Finance
Settlement reconciliation
Reads dense remittance workbooks by meaning rather than cell position and rebuilds every line; anything it cannot account for is held with the reason stated.
trigger: remittance file lands in the mailboxapprover: finance lead
Leadership
An AI colleague on chat
Answers plain-language questions against the live database using one recorded formula per metric, in the chat leadership already uses.
trigger: a question is askedapprover: none, read only
Operations
The watchdog
Sweeps every scheduled process and alerts the owner, not the room, with the fix in the message. Silence means healthy.
trigger: continuousapprover: process owner
Finance
Bank to invoice to filing
Matches credit alerts to open invoices, names every deduction, raises the tax invoice and produces a return-ready workbook.
trigger: bank credit alertapprover: finance controller
Customer service
Inbound at scale
Classifies and routes thousands of messages a week to an owner, escalates critical language within minutes, drafts replies a person releases.
trigger: message receivedapprover: named responder
Integration
The collection layer
Scheduled jobs that sign in to portals with no published interface, with session management, retries and a per-run audit trail.
trigger: scheduleapprover: none, read only
Control
The agent prepares. A person releases.
Anything that leaves your company or moves your money has a named approver.
Scroll sideways to read the table.
| raised | action | approver | state |
|---|---|---|---|
| 09:12 | release tax invoice to customer | finance lead | held for approval |
| 09:31 | post credit note, ledger write | finance controller | held for approval |
| 10:58 | send documentation pack to buyer | export desk | released 11:04 |
nothing in this queue moves without a named human
Data
Your cloud, your network, or your own hardware.
Authority
A human holds the pen.
Evidence
What it read, which rule it applied, what it produced, and who approved it.
Integrity
No fallback logic. If a field is missing it stops and asks.
Continuity
Documented rules and integrations, exportable data, and a handover pack.
Reversibility
Parity is proven before anything is switched off.
We enter your systems only with your written authorisation and your own credentials.
Engagement
Four phases. The first agent is live on real work in six weeks.
| # | Phase | What happens | What you have at the end |
|---|---|---|---|
| Diagnostic, 2 weeks | What happensWe sit beside the people doing the work and map eight to twelve workflows, measuring what each one costs in hours. | What you have at the endA ranked automation backlog with an expected payback against every workflow. | |
| Build, 4 weeks | What happensThe first agent is built against the real process, in your environment, on your data. Weekly demonstrations with the people who will use it, not with a steering committee. | What you have at the endOne agent in production, doing real work. | |
| Prove, 3 weeks | What happensThe agent runs alongside the manual process and the two are reconciled to zero difference. | What you have at the endEvidence, and then the switchover. | |
| Run and extend, ongoing | What happensWe host it, monitor it, maintain it, and absorb the format and portal changes that break automation. The next workflow comes off the backlog every four to six weeks. | What you have at the endCompounding coverage rather than a finished project. |
Numbers are set after the diagnostic, because quoting before we have seen your process goes badly.
Fit
If your work is rules based, repeated and spread across systems that do not talk, we can automate it.
- Skilled people spend more than half their week moving information between systems.
- The number everyone actually trusts lives in one person's spreadsheet.
- The deadline is met by someone staying late.
- The last automation attempt produced a pilot, and the pilot produced a meeting.
Method
Four rules we do not break, and the reason each one exists.
MIT's Project NANDA reported in 2025, in The GenAI Divide, that about 95 per cent of the organisations it studied saw no measurable return from generative AI. We read that as a discipline problem more than a technology problem. These are the four disciplines we hold ourselves to.
No fallback logic
An agent never quietly substitutes one data source for another when a field is missing.
A percentage is not an explanation
A difference is closed when we can say what every unit of it is, not when the percentage looks small. Anything left over is reported as unexplained.
Parity before switchover
The agent runs beside the manual process until the two reconcile to zero difference. If it does not tie out, it does not go live.
The done-ness test
After the agent goes live, does a person still open that file? If yes, we have not finished.
Pick one workflow. We'll have it running in six weeks.
Two weeks beside your team, eight to twelve workflows mapped and costed, and a ranked backlog with an expected payback against each one.
Or write to us and describe the workflow that annoys you most. That is usually the right one.
Questions
Eight questions, answered the way we would answer them on a call.
Where does our data live?
Wherever you tell us: your cloud account, your network, or your own hardware. We do not pool it with anyone else's and we do not use it to train a model.
What do you get access to?
The least we need for the workflow you asked for, granted in writing, using credentials you issue and can revoke. We tell you what an agent touches before it touches it.
Who owns the code?
You do, for everything built specifically for you: the workflow logic, the rules, the integrations and the documentation. This is written down before the first build, not after.
What happens if we stop working with you?
You get a handover pack: documented rules and integrations, credentials returned, data exported in a format you can read, and a walkthrough. We build for that day from the beginning.
How do you price this?
A fixed fee for the diagnostic, credited against the first build. A fixed price per agent and a monthly fee to run it. We do not sell seats or bill by the hour.
What if it gets something wrong?
If it is uncertain it does not proceed: it stops and escalates to the person you named. If it acts wrongly, the log tells you what it read and which rule it applied.
Do our people have to learn a new tool?
No, and we treat that as a design constraint. The work shows up where your people already work: the ERP screen they use, their mailbox, the chat they already have open.
How long before something is live?
Two weeks for the diagnostic, and the first agent is on real work by week six. Parity is proven between weeks six and nine before anything manual is switched off.