Agentic AI Use cases

Cancel the lines the plan stopped needing, before the window closes.

Open purchase order lines are compared every morning with current demand, supplier confirmations and lead-time fences.

THE PO CANCELLATION AGENT · MONDAY 21 SEPTEMBER 2026 · SHOWCASE ESTATE0106:00 · theplanning run endsexception messages touch212 open lines02Version 3 runsexcess, window, supplierclass, then value0338 lines match29 under $25,000 drafted;9 to D. Okafor as buyer04D. Okafor approveseach22 minutes for the queueof 2905SAP confirmswrite-back in 9 minutes;one record per decisionevery approve, edit and reject is recorded and used in the next cycle
The Monday run in five steps: the agent’s three in teal, D. Okafor’s approval in purple, the confirmed write-back in green. The figures are the showcase estate’s and follow chapter 5; the agent itself runs in production at a high-tech manufacturer.
38 min
from the question to the confirmed write-back on the showcase Monday, against 2.5 days by hand
showcase estate
203 of 212
drafts approved as written over six weeks, which is 96%; the other 9 were edited
showcase estate
28%
of procurement staff time goes on transactional work such as managing purchase orders (Gartner, in Supply Chain Management Review, 18 February 2026)
dated source
100%
of actions traced to a rule where the agent runs in production, at a high-tech manufacturer
production · anonymised
A moment in the day

Where this use case starts

DO
Monday 21 September 2026 · 08:50 · the buyer’s approval queue

Monday 21 September 2026, 08:50. D. Okafor, buyer, opens his approval queue. The 06:00 run on rule version 3 found 38 open purchase order lines that can still be cancelled this week, worth $412,000, after a customer push-out left them above the need. Twenty-nine sit under the $25,000 threshold and wait as drafts worth $187,300, each with its projected excess, its window and its supplier class.

He reads each row: the action, the three conditions it matched, the value at stake and the confidence. Twenty-eight he approves as drafted; one he edits to a smaller quantity. By 09:12 the queue is done: 22 minutes. The changes go to SAP S/4HANA through its released purchase order interface, and by 09:21 each answer is stored word for word.

The 9 lines at or above the threshold reach D. Okafor as buyer, for his judgement, each with the reason, before the window closes on Thursday 24 September; he is one person in two chairs. L. Tan, who stated the policy on the Friday, finds the 38 lines already found when she opens her 1,240 messages at 07:40. The Monday is the showcase estate; the agent is the one that runs in production.

Why this is a top use case

What the market is doing, with the evidence

Managing purchase orders is the transactional work the analysts count. About 28% of procurement staff time goes on it, work Gartner calls suitable for automation (Gartner, in Supply Chain Management Review, 18 February 2026) 4; planners spend over half their time sorting dashboards and filters for supply issues, and agents could cut that effort by up to 80% (Kinaxis, 2 April 2025) 64.

The market’s agents draft, and the buyer applies. Microsoft’s Procurement Agent for Dynamics 365 reads supplier e-mails, identifies changed quantity, price, date and cancellation, assesses the effect on inventory and orders, and drafts chasers for unconfirmed orders; the buyer reviews and applies each change (Microsoft Learn, 10 and 26 August 2026) 34 35. SAP’s Joule mass update of delivery dates by plain-language command is generally available (SAP, 22 October 2025) 16; Oracle ships a Purchase Order Status Advisor (Oracle, 9 April 2026) 22 24.

The named numbers measure the chase. Molex raised its purchase order confirmation rate from 30% to 90% with Celonis process intelligence (IT Brief UK, 16 April 2026) 38; JBT AeroTech reached 86% of purchase orders acknowledged within 72 hours (SourceDay, 8 July 2026) 58. Lima’s PO cancellation agent runs in production: planners author the policy in plain language, the rules engine executes it on federated ERP data, write-back happens under human approval and 100% of actions trace to a rule production · anonymised.

Governance is the gate, and this use case shows it. 6% of supply chain organisations run autonomous AI at scale today and 41% expect to within two years; 52% cite trust in AI decisions as the top barrier (IDC for Kinaxis, 11 August 2026) 63. Said plainly, the surveys speak of managing purchase orders in general; a survey that names cancellation or reschedule agents as deployed has yet to appear, and the named numbers come from process intelligence and a purchase order collaboration platform.

By hand today

How it is done today

The MRP run posts exception messages overnight: reschedule in, reschedule out, cancel. The buyer filters by MRP controller, opens each purchase order line and checks projected stock and pegged demand in the planning suite, the lead-time fence, the cancellation window, the NCNR flag and the supplier class. That is the 70 minutes of filtering and the four hours of drafting on the showcase Monday.

Then the buyer e-mails the supplier to cancel or reschedule, and the reply takes a day or more. The buyer sets the deletion indicator or changes the delivery date, records the confirmation, tells the planner and logs the line in a spreadsheet: two hours of updating. Unconfirmed orders are chased from a weekly report; confirmations arrive as e-mail or PDF and are keyed by hand.

Four people touch one batch: the buyer, the supply planner, the MRP controller and the supplier. Elapsed in the showcase estate: 2.5 days for one batch of 38 lines, with the cancellation windows closing on the Thursday. Molex started its chase at a 30% confirmation rate (IT Brief UK, 16 April 2026).

Today

The old path

  • Export from two ERPs · Mon · 70 min
  • Match the lines in a spreadsheet · Mon · 4 h
  • E-mail five buyers and wait · Tue · a day
  • Buyers key each cancellation · Wed · 2 h
2.5 dayslist to last cancellation
With the agent

The Monday with the agent

  • Ask the question in plain language · 4.2 s
  • The agent drafts 29 cancellations · 6 min
  • D. Okafor approves the queue · 22 min
  • Write-back, confirmed by the ERP · 9 min
38 minquestion to confirmation

The four rows chapter 1 drew, for one batch of 38 lines. Showcase estate.

Stage by stage

How Juno enables it

This is the one place in the use-case family where the six stages are a record and a design at once. Chapter 5 follows the cancellation agent through the Friday, the Monday and the six weeks; the rows below place that agent in its chain and say which of the neighbouring roles, the reschedules, the chasers and the confirmations, are designed and yet to be built.

01
Register
Purchase orders, lines and schedule lines; supplier confirmations; MRP exception messages; material at plant with projected stock, demand pegging and lead-time fence; the supplier master and class; the cancellation window and NCNR flag; scheduling agreements. In the showcase estate A. Novak registered 23 tables from SAP S/4HANA and Oracle Fusion on the Monday of the first week; the portal, e-mail and EDI 855 and 856 would join for the confirmation roles.
02
Map
Purchase order, line, schedule line, supplier, material at plant and exception message are ontology objects already, and supplier confirmation is one too. On the Tuesday Juno proposed 371 mappings over 412 columns; the team confirmed 338, adjusted 33 and added 41 by hand. The custom field that decides the case, the cancellation window in days, arrived at 62% confidence and was confirmed with D. Okafor, who owns the purchasing data.
03
Ask
“Which open purchase order lines are still inside their cancellation window this week, and what are they worth?” was L. Tan’s first question on the Wednesday, answered across three systems in 4.2 seconds with the query on show: that week’s 31 lines, worth $348,000. The buyer’s follow-up would be “Which of Delta Fasteners’ open lines are unconfirmed after ten days, and which orders do they feed?”
04
Teach
On the Thursday D. Okafor added NCNR, non-cancellable and non-returnable, as a purchasing term; L. Tan added the lead time fence as a planning term; P. Sharma added the “strat supplier” alias and reviewed all three. Each of them appears in the policy sentence or its checks, which is why the agent could read the desk’s own words on the Friday.
05
Act
Trigger: 06:00 each working day, after the planning run. Actions: draft a cancellation, send a change, open a query to the buyer. Level: A2 with D. Okafor as the named approver. On the Monday 38 lines matched: 29 drafts under $25,000 to the queue, 9 at or above it to D. Okafor as buyer, for his judgement, with the reason. SAP confirmed each write-back. Reschedules and chasers would be further actions, designed and yet to be built.
06
Learn
Overrides and edits per 100 drafts is the measure: 9 edits in 212 drafts over six weeks, 203 approved as written, which is 96%. That record carried lines under $25,000 from A2 to A3 at J. Ridley’s level review. Buyers kept every line for one allocation-bound supplier, so Juno proposed an exclusion, and j.park approved it as rule version 4.
PO cancellation policyA2 Supervisedshowcase estate
Cancel open purchase order lines where projected excess is above eight weeks of demand, the line is inside its cancellation window, the line value is under $25,000 and the supplier class is standard. For lines of $25,000 and above, draft the cancellation and ask the buyer.
What it compiles to: the planning table
RowKindWhat it tests or doesData it readsThen
01CheckProjected excess is above 8 weeks of demand edited by L. Tan · 10:10stock on hand, stock on order, forecast, sales orderscarry on
02CheckThe cancellation window is open on the run dateorder date, cancellation window in dayscarry on
03CheckThe supplier class is standardsupplier record, supplier classcarry on
04ActionDraft the cancellation of the open quantityopen quantity, line value, currencyrow 05 decides the route
05LimitLine value against $25,000line valueunder: the queue · at or above: the buyer
Version 3Released Fri 18 Sep 2026 · 13:30 · J. RidleyApprover: D. OkaforSimulated on last quarter

The policy L. Tan stated on Friday 18 September and the five rows the Planner Agent drafted from it; she adopted four and edited one. Chapter 5 holds the full worked example: the Friday hour by hour, the Monday run, the audit record and the level review. Showcase estate.

Who does what

The person and the agent

The agent A2 Supervised
  • Reads version 3 at 06:00 and compares every open line with projected excess, the cancellation window and the supplier class
  • Drafts the cancellation of the open quantity with the three conditions it matched, the value and the confidence
  • Routes lines under $25,000 to the approval queue and lines at or above it to D. Okafor as buyer, for his judgement, with the reason
  • Sends each approved change to the ERP and stores the acknowledgement word for word
a drafted cancellation, with its basis and its confidence; then the go-ahead
The person
  • D. Okafor approves, edits or rejects every draft by name; at A3 he handles the lines the rules route to him
  • L. Tan owns the policy: she stated it, edited the Planner Agent’s rows and approves the exclusions the agent proposes
  • J. Ridley set the level and released version 3; the level review after six weeks was his decision
  • J. Harrison co-owns the $25,000 threshold with L. Tan and audits cancellation value and overrides each month

The market’s usual level is draft-and-approve: Microsoft’s agent proposes changes that purchasers confirm and apply, with automatic chasers as a setting that stays off until a buyer switches it on (Microsoft Learn, 26 August 2026); SAP’s delivery-date update runs on a purchaser’s command (SAP, 22 October 2025). The blueprint lists PO change and cancellation at A3; the showcase estate started it at A2 and, after 212 approvals with 9 edits, moved lines under $25,000 to A3. Designed at A3, started at A2, raised on evidence.

What you would configure

The settings on this agent

Agent settings · Purchase order change, cancellation and confirmation chasing
ElementSettingSet byChanges
ObjectiveCancel purchase order lines that stand above the need, inside their cancellation windowL. Tan, plannerNew version
Data scopePurchase order lines, schedule lines, demand, stock and supplier class at plants 1210 and 1220A. Novak, data leadNew version
RulesThe policy sentence and its planning table, version 3L. Tan with the Planner AgentNew version, simulated first
Trigger06:00 each working day, after the planning runL. Tan, plannerAt once
Actions permittedDraft a cancellation · send a change · open a query to the buyerL. Tan, ownerNew version
LimitsValue threshold $25,000 · daily action budget 60 · confidence floor 0.80L. Tan and J. Harrison, financeNew version
EscalationAbove the threshold, to the buyer with the reason · a failed write-back, to the ownerL. Tan, ownerAt once
LevelA2 Supervised with D. Okafor as the named approver; lines under $25,000 at A3 since the level reviewJ. Ridley, directorUp on evidence, down in one step
FeedbackEvery approve, edit and reject is recorded and used in the next cycleAlways onFixed

The nine settings of chapter 4 with the values chapter 5 shows; the owners follow the ruling on who owns what. Showcase estate.

Built from the blueprint

The roles this use case would draw on

Lima’s agent blueprint is a design of 960 agent roles across five end-to-end chains. It is the map of what Juno can be configured to do, and the first agents are built from it one at a time, the way the PO cancellation agent was.

Blueprint · designed, yet to be builtThese roles are designed on the map, and the production agent runs at a high-tech manufacturer. Each is configured from the same parts.
Buy 7 roles
PO change & cancellation A3
PO acknowledgement (EDI 855) A4
Supplier commit tracking A3
Expediting & shortage escalation A2
Price & term variance detection A3
PO closure & residual clearing A3
Blanket & scheduling-agmt calls A3
Receive 4 roles
Capacity confirmation & rebooking A3
Supplier WIP & schedule visibility A3
Commit-vs-delivery variance A3
In-transit ETA & exceptions A3

Additional capability in Procure-to-Pay lists the rest of the map for this chain.

How it is measured

The measures that show it working

Measure
open purchase order value above need ($412,000 on the showcase Monday)
cancellations executed inside the window
purchase order confirmation rate (30% to 90% at Molex; 86% within 72 hours at JBT)
reschedule acceptance
expedite and premium freight spend
buyer minutes per batch (38 minutes against 2.5 days in the showcase estate)
overrides and edits per 100 drafts (9 edits in 212 in the showcase estate)

Baseline open purchase order value above need first: it is the number the Monday opens on, $412,000 in the showcase estate, and the one the finance lead reads. Buyer minutes per batch and overrides per 100 drafts come next, because they are the evidence a level review needs: 38 minutes against 2.5 days, and 9 edits in 212, are what carried the lines under $25,000 to A3.

Terms on this page
Cancellation windowThe days after order placement in which a line can be cancelled under the supplier’s terms; a custom field in the showcase ERP.
NCNRNon-cancellable, non-returnable: a line the supplier will hold the buyer to; the policy leaves it alone.
Lead time fenceThe period inside the supplier’s lead time where a change comes late; a planning term L. Tan taught on the Thursday.
Deletion indicatorThe flag on a purchase order line that closes it in SAP; the acknowledgement the agent stores.
Exception messageThe planning run’s note that a line needs attention: reschedule in, reschedule out or cancel.
Questions
Which part of this use case runs in production today?

The cancellation agent: planners author the policy in plain language, the rules engine executes it on federated ERP data, write-back happens under human approval and 100% of actions trace to a rule, at a high-tech manufacturer. Reschedules, chasers and confirmation tracking are designed roles, yet to be built.

What did six weeks change?

The agent drafted 212 cancellations; D. Okafor approved 203 as written and edited 9. On that record J. Ridley moved lines under $25,000 to A3, where the agent executes inside version 3 and D. Okafor handles exceptions only. Lines at or above the threshold still reach him as drafts.

What happens when the supplier rejects the change?

The rejection returns the line to the buyer with the supplier’s words attached, the line stays open, and the next run raises it again while its window is open. A line is closed only when the ERP acknowledges the change.

Next in this chain
The question this leaves

The policy checked the supplier class. Who checks the supplier: its finances, the sanctions lists, and the end-of-life notice on the part?

Answered next

Supplier risk, sanctions and end-of-life monitoring

Supplier risk, sanctions and end-of-life monitoring: continuous screening, and the last-time buy drafted before the window closes.

Sources

Dated sources used on this page

  1. [4] Supply Chain Management Review (Meghan O'Doherty, Gartner), AI is automating procurement; it's also creating jobs leaders aren't ready for, 18 February 2026 (checked 23 September 2026) · https://www.scmr.com/article/ai-is-automating-procurement-its-also-creating-jobs-leaders-arent-ready-for
  2. [16] SAP News Center, SAP Business AI: Release Highlights Q3 2025, 22 October 2025 (checked 23 September 2026) · https://news.sap.com/2025/10/sap-business-ai-release-highlights-q3-2025/
  3. [22] Oracle, AI Agents for Oracle Fusion Cloud Applications (agent catalogue), undated (checked 23 September 2026) · https://www.oracle.com/applications/fusion-ai/ai-agents/
  4. [24] Oracle, Oracle Introduces Fusion Agentic Applications for Finance and Supply Chain, 9 April 2026 (checked 23 September 2026) · https://www.oracle.com/news/announcement/oracle-introduces-fusion-agentic-applications-for-finance-and-supply-chain-2026-04-09/
  5. [34] Microsoft Learn, Procurement Agent overview (production-ready preview), 10 August 2026 (checked 23 September 2026) · https://learn.microsoft.com/en-us/dynamics365/supply-chain/procurement/procurement-agent-overview
  6. [35] Microsoft Learn, Follow up on purchase orders using the Procurement Agent (production-ready preview), 26 August 2026 (checked 23 September 2026) · https://learn.microsoft.com/en-us/dynamics365/supply-chain/procurement/procurement-agent-supplier-com-follow-up
  7. [38] IT Brief UK, Molex lifts purchase order confirmations to 90% with Celonis, 16 April 2026 (checked 23 September 2026) · https://itbrief.co.uk/story/molex-lifts-purchase-order-confirmations-to-90-with-celonis
  8. [58] SourceDay, Are Your Buyers Still Chasing Supplier Acknowledgements?, 8 July 2026 (checked 23 September 2026) · https://sourceday.com/blog/automate-supplier-follow-up/
  9. [63] Kinaxis, Kinaxis-Sponsored Study Identifies Supply Chain AI Accountability Gap (IDC, n>2,000), 11 August 2026 (checked 23 September 2026) · https://www.kinaxis.com/en/news/press-releases/2026/kinaxis-sponsored-study-identifies-supply-chain-ai-accountability-gap
  10. [64] Kinaxis blog, AI agents are here and they're a game changer for how we manage supply chains, 2 April 2025 (checked 23 September 2026) · https://www.kinaxis.com/en/blog/ai-agents-are-here-and-theyre-game-changer-how-we-manage-supply-chains

See Juno answer and act on your own data

Bring two systems and one decision your planners make every week. In the first week we register the data, confirm the mapping with your team, answer your questions in ChatLima and run the first agent at the level you choose.