Wirewalk Instituteof AI
mfg-225 Intermediate Available

Building AI for Production Planning, Scheduling and OEE

For MES engineers, schedulers and CI engineers: analyze OEE and planning evidence, build a fully supplied finite scheduling example, and evaluate industrial solver and agent designs.

Level
Intermediate
Study time
16 hours
Lessons
18 in 6 modules
Exam
20 questions

About this course

Wrenfield Foods (a fictional composite) has signed a private-label contract that its Danville, Illinois plant cannot fill on today's performance, and the owner's investment committee will decide on a $12.4 million fifth line in June. Supervisors say OEE is 79.7%, the corporate dashboard says 63.4%, and the written definition the learner builds says 58.4%. Across six modules the learner computes OEE the plant trusts and attributes its losses, predicts changeover times and each purchase order's chance of shipping by its requested date, and checks their coverage and calibration, builds and verifies a supplied four-order, two-line finite-grid Python scheduler, then analyzes conceptual OR-Tools CP-SAT models with allergen sanitation under 21 CFR 117.135 and lockout time under OSHA 29 CFR 1910.147 as hard constraints, puts a read-only rescheduling agent and number-checked shift briefings around the plan, staffs Saturday crews by the contract's rotation without turning OEE into a people score, and proves the result like for like: a replay is a ceiling, a before-and-after mixes causes, and capacity is not money until a cost line changes. The course ends with a go/no-go package for the committee.

Tools are compared the way plants choose them in October 2026: monitoring subscriptions versus MES modules versus an in-house pipeline; an in-house solver versus Siemens Opcenter APS, SAP PP/DS and sequencing or job scheduling in Dynamics 365; vendor agents versus agents built on model APIs with allow-listed tools and approval before dispatch. Vendors are named to show categories, not as endorsements, and no vendor performance claim is taught as fact. Every module ends in a Decision Lab with business metrics, a cliffhanger and several endings. All data are synthetic, and the course is educational, not legal, food-safety or engineering advice. OT data paths and predictive maintenance are in mfg-210, demand planning in mob-210, quality systems in mfg-235 and pharmaceutical packaging in mfg-270.

Executable build scope: builder/exact_example.py and its complete fixture, expected output and rejection tests use Python standard library only. The larger Wrenfield statistical, CP-SAT and agent outputs are synthetic reading/diagnosis illustrations; their original runtime datasets are not supplied and reproduction is not promised.

What you will be able to do

  • Compute shift and line OEE from machine-state events against a written plant definition within 0.5 points, name the data defects and definition choices behind conflicting numbers, and justify the ideal rate from demonstrated capability
  • Evaluate downtime reason suggestions and micro-stop attribution against an audited sample rather than operator acceptance, and set where a human must confirm
  • Evaluate changeover, run-rate and purchase-order on-time predictions by interval coverage and calibration on held-out weeks, choose the quantile per resource, and route changes so costing standards stay with the controller
  • Build and exhaustively verify a four-order, two-line finite-grid schedule from the complete supplied Python example; evaluate its maintenance, allergen, QA and shared-resource constraints, compare its baseline on identical inputs, and explain how industrial CP-SAT modeling extends beyond this bounded example
  • Evaluate an agent around the plan for least privilege, approval before dispatch, minimal-change repair, injected instructions, stale data and untraceable numbers, and specify controls that do not depend on the prompt
  • Analyze a crew-assignment model for qualification, rest and overtime distribution, and scope it in writing away from pay, discipline and operator ranking, with legal questions routed to HR and counsel
  • Evaluate a scheduling program like for like with fixed KPIs, costed replay and shadow mode, and build a business case that separates projected cash, opportunity cost and realized expenditure evidence
  • Create a go/no-go package with baseline, evidence, constraint register, agent controls, labor scope, staged rollout, tested rollback trigger and a recommendation an investment committee can act on

Syllabus

6 modules · 18 lessons · about 16 hours

Module 1: Nobody Agrees on OEE: Finding Where the Capacity Went

Write the plant's OEE definition, compute it from machine data, and attribute downtime and micro-stops in a way an audit supports.
4 lessons
  1. Three OEE Numbers for One Line: Writing the Plant Definition Before Computing Anything
  2. Computing Shift OEE From Machine States and Counters, and Catching the Data Defects
  3. Suggesting Downtime Reasons Constrained to the Reason Tree, Scored on an Audited Sample
  4. Micro-Stops and Speed Loss From Cycle Signals: Blocked, Starved and Own-Cause Stops
  • Decision Lab · 12 minThree Numbers and a Capex MemoA Wrenfield manufacturing decision with supplied resource limits, source facts and branch-dependent consequences. All mandatory plant controls remain fixed.

Module 2: The Schedule Is Wrong by Tuesday: Durations and Dates You Can Plan On

Replace stale standards with P50/P90 durations whose coverage is checked, keep them out of costing standards, and acknowledge retail purchase orders by calibrated on-time risk.
3 lessons
  1. Predicting Changeover and Run-Rate Durations at P50 and P90 From MES History
  2. Interval Coverage, Drift and the Change Request That Leaves Costing Standards Alone
  3. Promise Dates With Calibrated On-Time Probabilities for the Ridgemark Contract
  • Decision Lab · 12 minThe Standards Nobody UpdatedA Wrenfield manufacturing decision with supplied resource limits, source facts and branch-dependent consequences. All mandatory plant controls remain fixed.

Module 3: Recovering Capacity With a Constraint Solver, Without Trading Away Allergen and Lockout Rules

Model a week on four lines in CP-SAT, hold food-safety, sanitation and lockout rules as signed hard constraints, and decide whether to build, buy an APS or extend the ERP.
4 lessons
  1. Modeling a Week on Four Lines in OR-Tools CP-SAT: Intervals, Sequence-Dependent Changeovers and Weighted Tardiness
  2. Allergen Sequencing and Sanitation as Hard Constraints Under 21 CFR 117.135
  3. Maintenance Windows With Lockout Time and Fixed Due Dates Under OSHA 1910.147
  4. Build, Buy or Extend: CP-SAT, Timefold, Opcenter APS, SAP PP/DS and Dynamics 365, and Why an LLM Must Not Write the Schedule
  • Decision Lab · 14 minThe Allergen ShortcutA Wrenfield manufacturing decision with supplied resource limits, source facts and branch-dependent consequences. All mandatory plant controls remain fixed.

Module 4: Tuesday 10:20: Disruptions, Agents and Numbers Nobody Typed

Put a read-only rescheduling agent with approval before dispatch around the plan, red-team it, and build briefings where every number comes from a query.
3 lessons
  1. A Rescheduling Agent That Calls the Solver as a Tool: Allow-Lists, Minimal-Change Repairs and Approval Before Dispatch
  2. Red-Teaming the Agent: Injected Order Notes, Locked-Out Lines and Stale Data
  3. Shift Briefings and Shortage Triage Where Every Number Comes From a Query
  • Decision Lab · 14 minTuesday, 10:20 a.m.A Wrenfield manufacturing decision with supplied resource limits, source facts and branch-dependent consequences. All mandatory plant controls remain fixed.

Module 5: Saturday Crews for Ridgemark: Qualified, Rested and Inside the Contract

Assign Saturday crews by certification, rest and the seniority rotation, and scope the tool with HR and the local so it never becomes a people score.
2 lessons
  1. Crew Assignment as a Constraint Model: Certifications, Rest Rules and the Seniority Rotation
  2. Scoping the Crew Model With HR and the Local: FLSA, Illinois HB 3773 and Why OEE Is Not a People Score
  • Decision Lab · 12 minThe Crew Optimizer and the StewardA Wrenfield manufacturing decision with supplied resource limits, source facts and branch-dependent consequences. All mandatory plant controls remain fixed.

Module 6: Proof and the Line 5 Decision

Prove the program like for like, turn recovered capacity into a value bridge Finance will book, and build the go/no-go package for the committee.
2 lessons
  1. Proving the Scheduler Like-for-Like: Fixed KPIs, Costed Replay, Shadow Mode and the Value Bridge
  2. Capstone: The Line 5 Go/No-Go Package and the Staged Rollout
  • Decision Lab · 12 minThe $14.8 Million SlideA Wrenfield manufacturing decision with supplied resource limits, source facts and branch-dependent consequences. All mandatory plant controls remain fixed.
  • Capstone simulation · 35 minLine 5 or NotA Wrenfield manufacturing decision with supplied resource limits, source facts and branch-dependent consequences. All mandatory plant controls remain fixed.

Exam and certificate

The exam unlocks once you have completed every lesson and played each Decision Lab to an ending. It draws 20 questions from a larger bank, spread across the modules, with the answer options shuffled for each attempt. You have 40 minutes and need 80% to pass. After a failed attempt you can try again after 24 hours, up to 3 attempts in total. Feedback is given per module, never as the answer key.

Passing earns a certificate of completion and assessment from the Wirewalk Institute of AI with a unique ID that anyone can check at institute.wirewalk.com/verify. It is not an accredited qualification or a vendor certification. How certification works.

The Wirewalk Institute of AI is independent. This course teaches publicly documented products and is not affiliated with or endorsed by Google, Timefold, Siemens, SAP, Microsoft, Tulip, MachineMetrics, Guidewheel, QAD, Vorne, Anthropic, or OpenAI. Product and company names are trademarks of their respective owners.

More in AI in Manufacturing and Industrial Operations

All 16 courses in this track
mfg-001 Free intro Available

AI in Manufacturing and Industrial Operations: The One-Hour Briefing

A free hour built around real plant jobs: a maintenance planner turning overnight vibration alerts into work orders, a technician diagnosing a drive fault with a manual-citing copilot without touching lockout/tagout, a quality engineer setting the threshold on an AI terminal-lock vision check, an OT engineer deciding read-only versus write-back for a vendor's cloud link, a machine-safety engineer classifying ML person detection, and a pharma QA specialist drafting a deviation summary under human review.

1 h · 8 lessons Free intro
mfg-110 Basic Available

AI for Manufacturing and Plant Professionals

Practice with a fictional Ohio components plant using complete inline records. Check AI summaries, quality-review metrics, maintenance evidence, schedule feasibility and controlled-document claims before recommending a bounded next step.

8 h · 18 lessons See price at checkout
mfg-210 Intermediate Available

Building and Deploying AI in Industrial Operations

Evaluate plant AI through a cumulative synthetic US food-manufacturing case: data lineage, alert-to-work-order evidence, causal soft sensors, controlled-document RAG, control-model tests and read-only gateways. Assemble a reviewable decision dossier; no production authority or safety qualification is granted.

22 h · 23 lessons See price at checkout