
Case study · Packaging manufacturing · India
How BBF Packaging clears delayed sales orders faster with an AI agent
BBF Packaging's team chased late sales orders by hand every Friday, and lost last week's answers by the next. Our agent gets a reason for every order from Production, sends it to the team that has to act, and remembers every decision. Orders no longer sit unchanged for weeks.
- The problem
- Comments and decisions were lost every week, so the same questions came back.
- What we built
- An agent that gets a reason for every late order, routes it and keeps its history.
- Business outcome
- Lower sales order age. Delayed orders clear faster.
- Status
- Live for about three months.
The same problem shows up in
- Packaging and printing manufacturers
- Make-to-order factories on SAP
- Any business that chases late orders by email
If the reason an order is late lives in an inbox, you will ask again next week.
Before and after.
Before
The same chase, every Friday
A weekly routine run by hand, with nothing carried over.
- 1Download the delayed order report from SAP
- 2Email each salesperson and ask why orders are late
- 3Collect and analyse the replies
- 4Take serious cases to management, then repeat next Friday
Last week's decisions were lost in email, and some weeks the analysis wasn't done at all.
After
Every order keeps its story
Still a Friday routine. The chasing and sorting are the agent's.
- 1The team uploads the SAP report to the agent
- 2Production get an email, and one button opens their queue
- 3They pick a reason for each order
- 4The agent sends it to the team that has to act
No longer done by hand
- Emailing for comments by hand
- Reading and sorting every reply
- Digging through old emails
~120
Delayed sales orders
In the weekly report.
5
Salespeople
Asked only when Sales is needed.
0
Emails written by hand
The agent does the chasing.
5
Teams an order can reach
Production, Purchase, Sales, SAP, Management.
The problem
Why the chase kept failing.
Every week started from zero
Last week's comments and decisions weren't kept anywhere searchable.
Answers lived in email
Finding one order's decision meant digging through old threads.
The analysis took the time
Reading every reply and deciding who should act was slow, so it wasn't done properly every week.
Management saw it late
The team had to spot the orders that needed management by hand.
Why not just a better report?
SAP knows which orders are late. It doesn't know why.
So we kept SAP as the source and put the agent on the other side of the report.
- 01
A report shows late, not why
The reason sits with the people who know the order.
- 02
Comments are in people's own words
“Board received late, dispatching on the 28th.” A column can't read that. An agent can.
- 03
A report forgets
Next week's report doesn't know what was said this week. The agent does.
What they asked for
Stop repeating the Friday chase, and never lose what anyone said about an order.
One more: send each order to the team that can move it, and bring in management only when the rules say so.
So the goal was to clear delayed orders faster, not to send more emails.
The agent
What it does.
Starts from the SAP report
The team uploads the delayed order report. The agent loads every line.
Production comments first
They know why an order is late. An email button opens their queue, and they pick a reason and save.
Reads the comment
It works out what the comment says about the delay.
Routes by the comment
To Purchase, Sales, SAP or management. Sales and Purchase clarify as a second step.
Remembers every week
Every comment and decision stays with the order, so you can see why it was late.
A dashboard on request
Orders by team, the oldest orders, critical reasons and orders with no action.
It never connects to SAP, never invents a dispatch date, and never adds management just because an order is old.
The comment queue
What Production sees.
SO Comment Queue
Week of 23 Oct · 4 visible
Select a reason, fill any required fields and save.
| Order | Item | Age | Balance | Comment for this week |
|---|---|---|---|---|
| SO-B201 | FG-1042 | 112 d | 5,700 | Select a reason…Save SALES04 SepWaiting for dispatch clearanceShow history (6) |
| SO-B207 | FG-1058 | 64 d | 1,800 | Select a reason…Save PROD16 OctDispatching on 30 OctShow history (3) |
| SO-B214 | FG-1077 | 38 d | 3,000 | Select a reason…Save |
Production pick from a short list of reasons, or write their own. Earlier comments sit under each order. Sales and Purchase see the same queue when the agent needs their clarification.
The dashboard
What management sees.
SO Analysis Report — Management Dashboard
Team records
Management can comment on any order.
- Production (12)
- Purchase (6)
- Sales (2)
- SAP (1)
- Management (5)
| Order | Age | Team | Reason | Status |
|---|---|---|---|---|
| SO-A101 | 92 d | Production + Management | Promised date passed, not dispatched. | Escalated |
| SO-A105 | 57 d | Production + Management | Cause changed from material to QC hold. | Moving target |
| SO-A103 | 66 d | Purchase | Material due beyond 20 days. | Open |
| SO-A102 | 41 d | Production | Dispatch promised within 15 days. | Promise pending |
| SO-A104 | 35 d | Sales | No dispatch clearance. | Open |
| SO-A106 | 48 d | SAP | Dispatched, but still open. | Check SAP |
Each order sits under the team that has to act. Management sees what is oldest, what is critical and what has no action.
One order, three Fridays
How an order's story builds up.
- Week 1 · SO-A105
Production said
“No board. Expected on 12 Nov.”
Purchase
Material pending.
- Week 2 · SO-A105
Production said
“Board received late. Dispatching on 28 Nov.”
Production + Purchase
Date logged as a promise.
- Week 3 · SO-A105
Production said
“Order is on a QC hold.”
Production + Management
New cause, and the promised date passed. Management is added.
A recreation. The order and its comments are constructed.
Without last week's comments, week 3 looks new. With them, the agent sees a reason that keeps moving.
Trust and data
Safe to run.
An agent that routes orders can send one to the wrong team if it's careless. So it follows written rules, one order at a time.
No SAP access needed
It works from the uploaded report and can't change anything in SAP.
Only what was said
A dispatch date comes from this week's comment, never an estimate.
One order at a time
A comment on one order can't change where another goes.
Management by rule
Added only through set triggers, never for age alone.
The process
How we worked.
- 01First
Their judgement became the rules
Each kind of delay, who owns it and when management steps in, written down as the agent's instructions.
- 02Build
One order at a time
The agent analyses one order line per run, so one odd comment can't affect another.
- 03Connection
An upload, not an API
SAP's API wasn't opened up, so the team uploads the report. The agent starts from there.
- 04Live
In use every Friday
BBF's team has used it for about three months.
The hard part
Judging a reason the same way, every week.
The obvious build: a model that reads each comment and decides who should act, with nothing written down.
Why that fails
One sentence can point three ways
“Awaiting clearance” is Sales. “Board received late” is Production and Purchase. “Will update” needs management. A model left to decide would drift, and no one could say why.
What we did instead
Rules first, in strict order
Each kind of delay has a written rule, checked in priority order. Every result says which rule fired and why.
| The Friday routine did | The agent does |
|---|---|
| Judged each reply by hand | Checks the comment against the rules, in order |
| Remembered what it could from last week | Compares with every earlier comment, and flags a shifting reason |
| Took a date on trust | Logs a date only if stated, and escalates it if it passes |
Where it is better than before
Memory
Every decision stays with the order.
Consistency
The same comment gets the same routing.
Time
Upload a report instead of writing emails.
Visibility
The dashboard is there any day, not just Friday.
How we held that bar
Every result names the rule that fired, so anyone can check it against what Production said.
Faster is easy. The hard part is never sending an order to the wrong team.
Six months from now
How it stays predictable.
The agent's instructions are written, not improvised. For every order it asks the same questions in the same order.
- 1Does the comment end the check, like a clearance hold or an already dispatched order?
- 2Is a stated dispatch date within 15 days, past, or missing?
- 3Has the reason shifted, or does a trigger allow management?
- Goes live
An example from the rules
“Awaiting clearance” on a 600-day-old order still goes to Sales. Age alone never sends it to management.
Find out what your Friday chase is costing you.
A short discovery session about the report your team chases every week. We'll show you what an agent would do with it.
Book an AI KickoffOr email hello@avestalabs.ai