Order-to-Schedule Automation for a Secure Logistics Operator
Cash-in-transit operator (client anonymised)
A cash-in-transit operator ran its scheduling on email and spreadsheets: hundreds of order emails a day, hand-built run sheets, and one person's knowledge holding it together. We ran a four-week discovery, mapped the whole process and its 70+ rules, and designed an order-to-schedule automation that runs inside the client's own Microsoft tenant.
Book a Case Walkthrough
The client is a secure logistics operator, a cash-in-transit company that collects and delivers cash across a fleet of armoured vans. We have anonymised them here. Their business runs on scheduling: every working day, hundreds of customer orders arrive by email in every format imaginable, from typed requests and attached spreadsheets to photos of handwritten delivery notes. A small operations team turns all of that into a quarterly master schedule and daily run sheets by hand, then uploads them into their transport management system. The schedule is the business, and the way they built it was fragile.
The Challenge
Scheduling ran on email and Excel, held together by a few people's memory. It worked, but it did not scale and it broke in ways that were hard to recover from.
- Operators read hundreds of order emails a day across several shared mailboxes, in mixed formats: typed text, spreadsheets, and photos of handwritten notes.
- Building the master schedule and daily run sheets by hand cost the team 15 to 30 hours a week, with one person spending several hours a day reconciling versions.
- The whole thing lived in spreadsheets that corrupted a few times a year, needing IT to restore from backup.
- The knowledge sat in one or two people's heads. Onboarding a new scheduler took one to two months, a serious key-person risk.
- Last-minute changes bypassed the spreadsheet and went straight into the routing system, so there was no single source of truth.
Our Solution
We started with a four-week discovery on site. We mapped the as-is process end to end, documented every order source, and captured the 70+ business rules the schedulers apply, most of which had never been written down. Out of that we designed an order-to-schedule automation that runs entirely inside the client's own Microsoft tenant, so their data never leaves their environment, and runs in parallel with the existing Excel process rather than replacing it overnight. An intake agent reads the order mailboxes and turns any format into structured orders, using Claude's vision to read handwritten and photographed notes without a separate OCR engine. A deterministic rules engine, editable by the client, checks each order. A scheduling agent then sorts the work into green (handled automatically), yellow (proposed for a manager to approve) and red (left to a human), so the team manages the exceptions instead of the whole process. Approvals happen in Microsoft Teams, and the finished schedule is written back in the same Excel format and fed to the existing routing system. The discovery is delivered; the pilot is designed and ready to build.
- An intake agent that reads several shared order mailboxes and turns typed text, spreadsheets and photographed notes into structured orders, using Claude vision for the handwriting instead of a separate OCR engine.
- An orders database as the single source of truth, holding each order's state, history and rule checks with a full audit trail.
- A deterministic rules engine encoding 70+ business rules, kept out of the model and editable by the client without code.
- A scheduling agent that classifies each order green, yellow or red, so people approve only the work that needs judgement, in Microsoft Teams.
- Everything runs inside the client's own Microsoft tenant and writes the schedule back in today's Excel format, so nothing downstream has to change.
Built with Enterprise-Grade Technology
Goals and Objectives
The client came to us with clear objectives to transform their operations.
Map the Real Process
Document the as-is scheduling process end to end and capture the rules that only lived in people's heads.
Automate Order Intake
Turn hundreds of mixed-format order emails a day into clean, structured orders automatically.
Encode the Rules
Capture the 70+ scheduling rules as a deterministic, auditable engine the client can edit themselves.
Manage by Exception
Sort work into automatic, approve and human-only, so the team handles exceptions, not transcription.
Keep Data In-House
Run the whole system inside the client's own Microsoft tenant, with no data leaving their environment.
Change Nothing Downstream
Write the schedule back in today's Excel format and feed the existing routing system, so the rest of operations is untouched.
Remove Key-Person Risk
Move tacit knowledge into a system so onboarding takes about a week, not months.
See the Platform in Action
From intake to completion, explore how the solution transforms operations.
The Order-to-Schedule Flow
Order emails arrive in any format. An intake agent structures them, a rules engine checks them, and a scheduling agent sorts each into green (automatic), yellow (approve) or red (human). The finished schedule writes back in the client's existing Excel format.
How It All Works Together
Email Intake Agent
Monitors the shared order mailboxes, extracts structured order data from any format, and uses Claude vision to read handwritten and photographed notes, with a watcher that catches later updates in the same thread.
Orders Database
The single source of truth: every order, its state from received to delivered, its rule checks, history and a full audit trail.
Business Rules Engine
The 70+ scheduling rules encoded as a deterministic, auditable layer, kept out of the model and editable by the client without code.
Scheduling Agent
Checks each order against capacity, time windows and constraints, then classifies it green, yellow or red and builds the master and daily schedules.
Human Approval in Teams
The only path for human overrides. Managers approve, reject or adjust proposed work in Microsoft Teams cards, with every decision logged.
Schedule and Routing Output
Writes the master schedule and run sheets back to SharePoint in the existing Excel format, and feeds the route file to the client's transport management system.
Value and Impact Delivered
Measurable improvements across every dimension of operations.
Hours Back Every Week
The manual scheduling work the design is built to reclaim, freeing the operations team from email parsing and Excel reconciliation.
Every Rule Captured
The 70+ scheduling rules that lived in people's heads are now documented and encoded, removing the key-person risk.
Data Stays In-House
The whole system is designed to run inside the client's own Microsoft tenant, so order and customer data never leaves their environment.
Manage by Exception
Orders are sorted into automatic, approve and human-only, so people spend time on judgement calls, not transcription.
Nothing Downstream Changes
The schedule writes back in today's Excel format and feeds the existing routing system, so the pilot can run in parallel with no big-bang cutover.
Onboarding in a Week
With the process in a system rather than a spreadsheet, a new scheduler can be productive in about a week instead of one to two months.
Frequently Asked Questions
Ready to Transform Your Secure Logistics Operations?
See how AI can help your organisation reduce errors, speed up processing, and improve outcomes. Let's discuss your specific challenges.
Book Discovery CallExplore Other Projects
Discover more AI solutions delivering measurable results across industries