Agentic AI Use cases

Safety stock and lead times kept current every cycle, a name on each change.

Safety stock and replenishment parameter tuning keeps safety stock, reorder points, lot sizes, coverage targets and planned lead times current against the service target and the measured variability of demand and supply, and writes the approved values into the ERP and the planning suite each cycle.

SAFETY STOCK AND PARAMETER TUNING, AS DESIGNED · A201Triggermonthly review · lead timedrift · a service miss · aclass change02Recomputefrom measured variabilityand measured lead time03Splitunder the band: write ·above it: draft with thereason04ApproveL. Tan on the drafts · P.Sharma on lead times · J.Harrison on the envelope05Write backchange document from theERP · job status from thesuiteevery approve, edit and reject moves the next proposal
The mechanism in five steps: the split between the band and the drafts is the setting a manager signs. Showcase estate; a designed role, yet to be built.
59%
of supply chain organisations have inventory optimisation initiatives for 2026 (The Hackett Group, 14 May 2026)
dated source
$1.73 trillion
a year of retail inventory distortion, out-of-stocks plus overstocks, 6.5% of sales (IHL Group, 10 September 2025)
dated source
19%
less inventory at Bell Flight with automated parameter changes, a vendor-published result (GAINS, page modified 11 September 2026)
dated source
312
item-locations at plant 1210 more than 25% away from their policy value on the showcase estate’s quarterly review
showcase estate
A moment in the day

Where this use case starts

LT
First Monday of the quarter · 10:00 · Penang

First Monday of the quarter, 10:00. L. Tan opens the safety stock review for plant 1210, a role built from the blueprint. Juno lists 312 item-locations where the current safety stock sits more than 25% away from the value the policy gives, each with the reason: lead time drift, a change of class, a service miss, a variability that moved.

For material 7741-X the measured lead time from Acme Components GmbH has drifted from 21 to 29 days over six months, and the policy, 95% service on a class Y item, gives 640 pieces where the material master holds 420. For 188 C-class items where the stock change is under $5,000, version 2 of the policy lets Juno write the value to SAP S/4HANA on its own decision, and the change documents are back by 10:20.

The 124 larger changes wait for L. Tan, who approves 117 and edits 7. P. Sharma approves the planned delivery time change for Acme as a master-data change. J. Harrison sees the quarter’s inventory envelope move by $310,000 inside the agreed band, and the audit trail holds each change with its rule version and its approver.

Why this is a top use case

What the market is doing, with the evidence

Gartner names automated replenishment parameter changes, with touchless forecasting, as the place to focus early agentic efforts, because the actions are many and the cost of one wrong change is low (Gartner, 20 May 2026) 1. 59% of supply chain organisations have inventory optimisation initiatives for 2026, and 72% report AI in advanced planning and scheduling (The Hackett Group, 14 May 2026) 8.

Deloitte describes inventory optimisation agents as continuous service-level and safety stock adjustment and reports more than half of surveyed supply chain executives deploying agents, with the sample size unstated (Deloitte, 31 March 2026) 10. The named results are the most in the chain, most of them vendor-published: GAINS claims automation of up to 90% of buying decisions, 19% less inventory and 30% lower handling cost at Bell Flight, and Border States automated across 250,000 SKUs (GAINS, page modified 11 September 2026) 43.

ToolsGroup’s planning agent executes within human-controlled guardrails for 400 customers (ToolsGroup, 27 May 2026) 42. Oracle moved replenishment from periodic manual review to exception-based optimisation inside guardrails, SAP explains safety stock calculations in plain language for maintenance inventory, and the RELEX inventory control agent runs safety stock scenarios inside its rules engine (Oracle, 29 June 2026; SAP, 14 April 2026; RELEX, 2 July 2026) 31 27 44.

The money at stake is the largest in the chain. Inventory distortion, out-of-stocks plus overstocks, costs retailers $1.73 trillion a year, 6.5% of sales (IHL Group, 10 September 2025) 61; autonomous planning cuts inventory by up to 20% (McKinsey, 2 March 2022) 12; and Sainsbury’s reports 98% availability on about 30,000 SKUs and 150,000 fewer disposals in the 2025 peak (diginomica, 18 May 2026; Forbes, 5 June 2026) 38 37.

By hand today

How it is done today

Quarterly, or when service slips, the inventory planner exports the planning parameters for a plant to a spreadsheet: MRP type (how the planning run treats the item), safety stock, reorder point, lot size, coverage profile, planned delivery time. Demand history and receipt history follow, and the planner computes variability and actual lead time per item and applies a service-level formula, or a weeks-of-cover rule of thumb, by ABC and XYZ class.

The proposed values are reviewed with the inventory manager and with finance for the working-capital effect, then keyed into the material master one item at a time or through a mass-change upload, with the master-data steward checking the fields. Two to four weeks per plant review is a fair estimate.

Most item-locations are reviewed once or twice a year. Between reviews the parameters drift as lead times and variability change, and planned delivery times are often years old. The result is the distortion IHL measures: too much of some items and too little of others, at the same time, in the same plant.

Today

A quarterly review, by hand

  • Export the parameters for one plant to a spreadsheet: MRP type, safety stock, reorder point, lot size, planned delivery time
  • Pull demand and receipt history; compute variability and actual lead time per item
  • Apply the formula, or the weeks-of-cover rule of thumb, by ABC and XYZ class
  • Review with the inventory manager and with finance for the working-capital effect
  • Key the values into the material master; the steward checks the fields
2 to 4 weeksper plant review, an estimate; once or twice a year
With Juno, as designed

Each cycle, as designed

  • The agent recomputes every parameter against the service target and the measured variability
  • Changes inside the band execute; the change documents come back within minutes
  • Larger changes reach L. Tan with the reason; lead time changes reach P. Sharma
  • J. Harrison sees the envelope move inside the agreed band, with a record per change
20 minto the first 188 change documents, showcase estate

The manual path from the note, and the designed path from the scene. Showcase estate; the designed role is yet to be built.

Stage by stage

How Juno enables it

The material master and the planning run at plant 1210 were registered in the first week for the PO cancellation agent, and the ontology already holds material at plant with its planning parameters. This use case would add the receipt history that gives measured lead times, the service targets by segment and the planning suite’s inventory module, and would give the agent a policy and an envelope to run inside.

01
Register
You would register the planning parameters on the material master (safety stock, reorder point, lot size, coverage profile, MRP type, planned delivery time) and the planning run from SAP S/4HANA; item attributes and supply planning from Oracle Fusion for the acquired division; the planning suite’s inventory module; stock from the warehouse system; and the demand and receipt history that sits in the lake.
02
Map
Material at plant is the ontology object, and the parameters are its attributes; the service-level target by segment, the ABC and XYZ class, the carrying cost rate and the die bank and hub targets sit beside it. Measured lead time and demand variability are measures computed from receipts and orders, and forecast error joins from the forecast object, so one policy can read all of them for one item.
03
Ask
L. Tan would ask “Which items at plant 1210 have a planned delivery time more than five days away from the measured lead time of the last six months?” and “What would 95% service on class Y items cost in safety stock, against 92%?” ChatLima answers from the mapped parameters and history, with the query on show.
04
Teach
The team would add the desk’s segment names, the “strat supplier” alias it taught in the first week, “DOI” for days of inventory, and the policy itself as a named grounding register (95% service on A and B items, 90% on C, class Y variability), so a question about the policy is answered from the policy.
05
Act
The trigger is the monthly review, drift in lead time or forecast error, a service miss or a class change. At A2 the agent would recompute each parameter and draft the change; inside version 2’s low-value band it executes on the agent’s decision, above it L. Tan approves each, and a planned delivery time change waits for P. Sharma. The ERP returns the change document, the suite the job status.
06
Learn
Service level and fill rate against target by segment improve, with days of inventory and inventory value beside them. Each approved, edited and rejected change is recorded with the facts at that moment, so the proposed values move towards the ones the planner keeps, the band for direct execution can widen on evidence, and drift in a supplier’s lead time is flagged as it happens.
Safety stock policy · plant 1210 · illustrativeA2 Supervisedblueprint · designed, yet to be built
Set safety stock for each item at plant 1210 to the value that gives 95% service on A and B items and 90% on C items, from the measured variability of the last six months of demand and the measured lead time of the last six months of receipts. Where the item is C class and the stock change is under $5,000, write the value. Otherwise draft it for the planner. A planned delivery time change goes to the master-data steward.
What it compiles to: the planning table
RowKindWhat it tests or doesData it readsThen
01CheckThe item’s service target, from its ABC classmaterial master, segmentcarry on
02CheckVariability and lead time measured over six monthsorder history, receipt historycarry on
03ActionCompute safety stock and reorder point; compare with the mastercurrent parameters, stock, forecast errorrow 04 decides the route
04LimitC class and stock change under $5,000stock change at standard costunder: write · otherwise: L. Tan
05RouteA planned delivery time changeplanned delivery time, measured lead timeto P. Sharma as master data
Version 2 · illustrativeOwner: L. TanEnvelope: J. Ridley and J. HarrisonSimulated on last year first

A plausible policy sentence for the role, and the planning table it would compile to. Illustrative values; the mechanics are the product’s.

Who does what

The person and the agent

The agent A2 Supervised
  • Recomputes safety stock, reorder point, lot size and planned delivery time for every item each cycle, from measured variability and lead time
  • Writes the changes inside the low-value band and drafts the rest, each with the reason
  • Checks the envelope: the change in inventory value against the band finance agreed
  • Raises a review task where the service target and the cost conflict
124 drafted changes, each with its reason; the approvals and the edits come back
The person
  • L. Tan approves, edits or rejects each change above the band, with a reason
  • J. Ridley sets the service target per segment and the working-capital envelope the policy runs inside
  • J. Harrison approves changes that move the envelope beyond the agreed band
  • P. Sharma validates planned delivery time and lot size changes as master-data changes

The market runs parameter tuning at draft-and-approve, with execute within rules for low-value items: the vendors cited above run changes inside guardrails with review, or by exception, and the Gartner note of 20 May 2026 names replenishment parameter changes as a low-risk place to start. The blueprint designs safety-stock policy optimisation and replenishment policy setting at A2, coverage and buffer placement at A3, and parameter self-tuning at A4 once the record supports it. The showcase runs the low-value band at A3 inside an A2 agent, the split the PO cancellation agent reached after six weeks.

What you would configure

The settings on this agent

Agent settings · Safety stock and replenishment parameter tuning
ElementSettingSet byChanges
ObjectiveHold 95% service on A and B items and 90% on C at plant 1210, at the lowest inventory value that achieves itL. Tan, plannerNew version
Data scopeMaterial master parameters, planning run, demand and receipt history, forecast error, segments and targets; plants 1210 and 1220A. Novak, data leadNew version
RulesThe safety stock policy and its planning table, version 2, with the formula by classL. Tan with the Planner AgentNew version, simulated first
TriggerThe monthly parameter review, a lead time or forecast error beyond its band, a service miss, a class change, a confirmed supplier lead-time changeL. Tan, plannerAt once
Actions permittedUpdate safety stock, reorder point and lot size · update planned delivery time · assign the coverage profile · write the safety stock key figure · raise a review taskL. Tan, ownerNew version
LimitsDirect write only on C items under $5,000 of stock change · inventory envelope ±$500,000 a quarter · 400 changes a day · confidence floor 0.80J. Ridley and J. Harrison, financeNew version
EscalationChanges above the band to L. Tan · planned delivery time and lot size to P. Sharma · the envelope beyond its band to J. HarrisonL. Tan, ownerAt once
LevelA2 Supervised with L. Tan as the named approver; the low-value band at A3J. Ridley, directorUp on evidence, down in one step
FeedbackEvery approve, edit and reject is recorded and used in the next cycleAlways onFixed

Every row is a setting or a versioned rule; the level and the limits are the ones a manager signs.

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. Each is configured from the same parts.
Plan 9 roles
Safety-stock policy optimisation A2
Die bank target setting A2
Finished-goods coverage policy A3
Buffer placement optimisation A3
Inventory turns & DOI analytics A3
Replenishment policy setting A2
Consignment & hub stock policy A2
Distribution requirements planning A3
Inventory write-down triggers A2
Commit 1 role
Planning parameter self-tuning A4
Quality and Inventory 1 role
Die bank replenishment triggers A3

Additional capability in Plan-to-Produce lists the rest of the map for this chain.

How it is measured

The measures that show it working

Measure
Service level and fill rate against target by segment
Days of inventory and inventory value (case baselines: inventory down 19% at Bell Flight, GAINS; up to 20% with autonomous planning, McKinsey)
Stock-outs and excess value
Share of item-locations with parameters reviewed in the last 90 days
Share of parameter changes executed within rules, approved, edited or rejected
Working capital released

Baseline service level and fill rate against target by segment first, because the policy is written in those terms and a change of parameters shows there within a cycle or two. Days of inventory and inventory value are the finance measures and the envelope the agent runs inside, so J. Harrison sees them move from the first cycle. The share of item-locations with parameters reviewed in the last 90 days is the measure that moves fastest: from once or twice a year to every cycle.

Terms on this page
Safety stockThe quantity held against variability in demand and supply so the service target is met.
Planned delivery timeThe lead time the planning run assumes for a purchased item, held on the material master.
ABC and XYZ classValue class and variability class; together they set an item’s service target and formula.
Inventory envelopeThe agreed band of inventory value the policy may move within a period before finance approves.
Change documentThe ERP’s own record of a field change, returned and kept with the decision.
Questions
Why does a planned delivery time change go to the master-data steward?

Because it is a master-data field, and a wrong lead time moves every order date the planning run creates. P. Sharma validates it the way she validates any master-data change, and the change document carries her name.

What keeps the agent from cutting stock on an item about to spike?

The forecast is in scope: a launch, a design win or a moved customer forecast changes the segment before the parameter is recomputed, and a conflict goes to L. Tan as a review task. A service miss is a trigger.

How would this reach A4, the self-tuning role?

On evidence: a passing test on the recorded changes, J. Ridley’s approval and a live route to L. Tan for the exceptions, band by band. The envelope and the steward’s approval stay in place at every level.

Next in this chain
The question this leaves

The plan is right and the parameters are current. Then a placement machine stops on a Tuesday afternoon. Who re-plans the week, and how fast?

Answered next

Production schedule repair from shop-floor signals

The agent would read the event, re-check material and capacity, propose the re-sequence that protects every committed date and release only the orders that are ready.

Sources

Dated sources used on this page

  1. [1] Gartner, Gartner Warns of Agent Washing Risks in Supply Chain Planning Technology Market, 20 May 2026 (checked 23 September 2026) · https://www.gartner.com/en/newsroom/press-releases/2026-05-20-gartner-warns-of-agent-washing-risks-in-supply-chain-planning-technology-market
  2. [8] The Hackett Group, Supply Chain AI Adoption Becomes Pervasive as Cost and Modernization Pressures Intensify (2026 Supply Chain Key Issues Study), 14 May 2026 (checked 23 September 2026) · https://www.thehackettgroup.com/the-hackett-group-supply-chain-ai-adoption-becomes-pervasive-as-cost-and-modernization-pressures-intensify/
  3. [10] Deloitte Insights, Agentic AI in the manufacturing supply chain (article indexed as agentic-supply-chain-artificial-intelligence-manufacturing), 31 March 2026 (checked 23 September 2026) · https://www.deloitte.com/us/en/insights/industry/manufacturing-industrial-products/agentic-supply-chain-artificial-intelligence-manufacturing.html
  4. [12] McKinsey, Autonomous supply chain planning for consumer goods companies, 2 March 2022 (checked 23 September 2026) · https://www.mckinsey.com/capabilities/operations/our-insights/autonomous-supply-chain-planning-for-consumer-goods-companies
  5. [27] SAP News Center, SAP Business AI: Release Highlights Q1 2026, 14 April 2026 (checked 23 September 2026) · https://news.sap.com/2026/04/sap-business-ai-release-highlights-q1-2026/
  6. [31] Oracle (PR Newswire), Oracle Adds New Fusion Agentic Applications to Help Customers Improve Supply Chain Performance, 29 June 2026 (checked 23 September 2026) · https://www.prnewswire.com/news-releases/oracle-adds-new-fusion-agentic-applications-to-help-customers-improve-supply-chain-performance-302812443.html
  7. [37] Forbes (Steve Banker), Blue Yonder's Supply Chain Agents Are Getting Really Smart, 5 June 2026 (checked 23 September 2026) · https://www.forbes.com/sites/stevebanker/2026/06/05/blue-yonders-supply-chain-agents-are-getting-really-smart/
  8. [38] diginomica, ICON 2026: Blue Yonder bets everything on cognitive, the agent as the app and a new operating model, 18 May 2026 (checked 23 September 2026) · https://diginomica.com/icon-2026-blue-yonder-bets-everything-cognitive-agent-app-and-new-operating-model-product
  9. [42] ToolsGroup, ToolsGroup introduces Decion and the Planning Agent (press release on self-steering supply chains), 27 May 2026 (checked 23 September 2026) · https://www.toolsgroup.com/news/toolsgroup-introduces-new-era-of-ai-powered-self-steering-supply-chains/
  10. [43] GAINS, GAINS home page: DEO platform, agentic orchestration and customer results, page modified 11 September 2026 (checked 23 September 2026) · https://gainsystems.com/
  11. [44] RELEX Solutions, Agentic AI in retail planning: the RELEX agents (resource page), 2 July 2026 (checked 23 September 2026) · https://www.relexsolutions.com/resources/agentic-ai-retail-planning/
  12. [61] IHL Group, Retail Inventory Crisis Persists Despite $172 Billion in Improvements, 10 September 2025 (checked 23 September 2026) · https://www.ihlservices.com/news/analyst-corner/2025/09/retail-inventory-crisis-persists-despite-172-billion-in-improvements/

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.