Specialised Track · Operations & Supply Chain

Re-engineer operations and the supply chain with AI.

A three-day, hands-on programme for operations directors, supply chain and procurement managers, and logistics, quality and maintenance leads. Apply AI to demand forecasting, supplier management, inventory and logistics, quality management and predictive maintenance, then build and evaluate a working reconciliation agent in a pre-configured lab. Every delegate leaves with a working operations agent, an AI opportunity map for their function and a ninety-day plan.

3 days 17 modules 60%+ hands-on Codespaces lab included STOA certified
Daniel Sto
Why this programme exists
"Orders, shipments, stock, suppliers. Every reconciliation in the supply chain is an agent waiting to be built, and a person still signs off the exception."
Daniel Sto · Director of Faculty, STOA Institute
Duration
3 days
Format
Live online or on site
Next open date
Private cohorts
Fee
On request
per delegate
For teams
Private cohort from 8 delegates
Schedule a TNA call
Programme overview

Built around the operations value chain, from plan to deliver.

This three-day programme is built for operations, supply chain, procurement, logistics, quality and maintenance leaders who now have to decide where AI belongs in their operation. Operations produces a heavy load of documents and data: standard operating procedures, shift reports, work orders, supplier correspondence, forecasts, exception lists and quality records. Generative AI drafts, summarises and cross-checks that work well. Machine learning and optimisation handle the forecasting, scheduling and routing questions behind it. An AI agent goes one step further: given a goal, such as reconciling the order book against the shipment log, it works out the steps, reads the data, applies the rules and hands the result to a person for approval. The programme supplies the AI method, which work to hand over, how to ground it in the organisation's own documents and systems, and how to verify a result before it is acted on, while the operations expertise stays with the participants.

Day one establishes how generative AI works, places each type of AI where it belongs across the operation, takes every participant through structured prompting on their own operational documents, and closes with an AI opportunity map for their function. Day two applies AI across the supply chain: process thinking for automation, demand forecasting and planning, procurement and supplier management, inventory, warehousing and logistics, quality management, and production and maintenance. Day three moves from assistants to agents. Participants design and build an order and shipment reconciliation agent on a wholesale distribution case carrying realistic ambiguity and planted edge cases, instrument it and read its traces, metrics and costs, then set the governance and data controls for AI in their own operation. Emerging methods and the ninety-day plan close the programme.

Every lab runs in a pre-configured cloud environment opened from a browser, with no software to install. Participants choose a visual build track or a coding-agent track, and each lab is verified against fixed acceptance criteria. Participants leave with a working reconciliation agent, an operations prompt library, an AI opportunity map for their function, an evidence pack of traces and metrics, governance starting points, and a ninety-day plan. The programme finishes on where the field is heading: agentic AI, where an operations agent is given a goal and plans and executes the work under human supervision, with context engineering, agentic retrieval-augmented generation, the Model Context Protocol and multi-agent orchestration across the supply chain.

Who should attend

This programme is designed for the leaders, managers and analysts of operations, supply chain, procurement, logistics, quality and maintenance functions in manufacturing, distribution, retail, logistics and service businesses:

  • Chief Operating Officers and Operations Directors
  • Heads of Supply Chain and Supply Chain Managers
  • Demand Planners, Supply Planners and S&OP Managers
  • Procurement, Purchasing and Category Managers
  • Logistics, Transport and Distribution Managers
  • Warehouse and Inventory Managers
  • Production and Plant Managers
  • Quality Managers and Quality Assurance Leads
  • Maintenance and Reliability Managers
  • Operational Excellence, Lean and Continuous Improvement Leads
  • Operations Analysts and Supply Chain Analysts

Learning outcomes

By the end of this programme, participants will be able to:

  • Explain how generative AI works and where its output needs verification
  • Place generative AI, machine learning, optimisation and agentic AI where each belongs in operations
  • Apply the C.L.E.A.R. framework and K-shot prompting to operational work
  • Draft and check SOPs, handover notes and incident reports with AI
  • Map AI opportunities across planning, procurement, logistics, quality and maintenance
  • Map a process to the agent loop and mark where the human stays
  • Produce forecast commentary and demand and capacity scenarios with AI
  • Apply AI to supplier comparison, shortage-risk monitoring and disruption briefings
  • Apply AI to quality investigations, CAPA drafting and maintenance planning
  • Design an operations agent's goal, inputs, outputs and guardrails
  • Build a working order and shipment reconciliation agent
  • Evaluate an agent's traces, metrics, costs and failure modes
  • Apply governance and data controls to AI in operations
  • Build a ninety-day AI plan for their function
Programme outline

Seventeen modules. Three days. One working operations agent.

Each module follows the TEA™ framework, twenty percent theory, twenty percent examples, sixty percent hands-on application on your own operational scenarios. Day one builds fluency and the opportunity map; day two applies AI across the supply chain; day three builds, evaluates and governs an operations agent.

Day 1: Generative AI Foundations and the Operations Opportunity Map

01
Day 1 · Module

Generative AI Essentials for Operations

  • What is generative AI?
  • Large language models and enterprise assistants (ChatGPT, Claude, Microsoft Copilot, Gemini)
  • Tokens, context windows and memory
  • Chat models and reasoning models
  • Hallucination and non-determinism
  • Verification of AI output
  • Operational, supplier and customer data and what may be put into a tool
Live walkthrough the calculator test
02
Day 1 · Module

The Types of AI Across Operations and the Supply Chain

  • Generative AI
  • Machine learning and predictive analytics
  • Optimisation solvers (routing, scheduling, network design)
  • Automation and robotic process automation (RPA)
  • Agentic AI
  • Computer vision and document AI
  • Sensor data and the industrial internet of things (IIoT)
  • Where each type belongs:
    • Planning and forecasting
    • Procurement
    • Production
    • Warehousing and inventory
    • Transport and logistics
    • Quality
    • Maintenance
  • Deterministic and probabilistic work
Gamified task matching operations problems to the right type of AI
03
Day 1 · Module

Prompting for Operations Work

  • The anatomy of a prompt (role, context, task, format, constraints)
  • The C.L.E.A.R. prompt engineering framework
  • K-shot prompting (zero-shot, one-shot, few-shot, multi-shot)
  • Chain-of-thought and reasoning prompts
  • Structured outputs (procedures, shift reports, exception lists, comparison tables)
  • Common prompting errors in operational work
  • The operations prompt library and reusable agent skills
Hands-on exercise applying C.L.E.A.R. to participants' own operational documents
04
Day 1 · Module

Working With Operational Documents and Data

  • Standard operating procedure drafting from a spoken procedure
  • Decision points and exceptions in a procedure
  • SOP summarisation and comparison
  • Shift handover notes
  • Incident, near-miss and health and safety write-ups
  • Long-document work (contracts, tenders, specifications, supplier manuals)
  • Tables, spreadsheets and operational data questions
  • Document search grounded in the organisation's own manuals and contracts
  • Grounded answers and source citation
  • Abstention when the answer is not in the source
  • Confidentiality when uploading documents
Individual and pair work turning a spoken procedure into a numbered SOP with decision points and exceptions
05
Day 1 · Module

Mapping AI Opportunities Across Operations

  • High-value work types (documentation, reconciliation, investigation, reporting, scenario analysis, correspondence, triage)
  • The function-level opportunity scan (planning, procurement, production, warehousing, transport and logistics, quality, maintenance, health and safety)
  • Opportunity discovery methods:
    • Pain-point inventories
    • Process reviews
    • Time and effort mapping
  • Value, feasibility and risk assessment
  • Build, buy or configure
  • Candidates and non-candidates for AI
  • Where the human stays in each workflow
Hands-on exercise building the AI opportunity map for participants' own operation

Day 2: Applied AI Across Operations and the Supply Chain

06
Day 2 · Module

Process Thinking for Automation

  • What is a process?
  • Process documentation as source material (SOPs, SIPOC, value stream maps, swim-lane diagrams)
  • Steps, decisions, exceptions and hand-offs
  • Deterministic and probabilistic steps
  • The agent loop (goal, observe, reason, act, evaluate, repeat)
  • Mapping a process to the agent loop
  • Inputs, processing steps and outputs
  • Approval, exception and escalation points
  • The automation spectrum (scripts, RPA, workflow tools, AI agents)
Hands-on exercise mapping one of participants' own processes to the agent loop
07
Day 2 · Module

AI in Demand Forecasting and Planning

  • Machine-learning and classical forecasting in the planning system
  • Demand sensing and external signals
  • Demand and capacity scenarios with language models
  • Forecast commentary and exception reporting
  • Sales and operations planning (S&OP) pack preparation
  • Figures that come from the planning system rather than the model
  • Data quality and its effect on AI output
Individual and pair work forecast commentary and demand and capacity scenarios from a sample planning dataset
08
Day 2 · Module

AI in Procurement and Supplier Management

  • Supplier and market research
  • Request for quotation and tender document drafting
  • Quote and bid comparison in a consistent format
  • Contract review support (terms against standard positions)
  • Supplier communications and documentation
  • Supplier performance summaries (on-time in-full, quality, lead time)
  • Shortage-risk monitoring
  • Human sign-off on commercially binding work
Hands-on exercise supplier comparison and supplier correspondence on participants' own procurement scenarios
09
Day 2 · Module

AI in Inventory, Warehousing and Logistics

  • Querying inventory data and reports
  • Stock, restock and ageing reports
  • Order and shipment reconciliation
  • Warehouse SOPs and shift, staffing and capacity scenarios
  • Route, load and network questions that belong to optimisation solvers
  • Carrier and subcontractor correspondence
  • Shipment status and milestone updates for customers
  • Disruption and contingency briefings
Case study analysis a supply disruption handled with and without AI support
10
Day 2 · Module

AI in Quality Management

  • Deviation and non-conformance trend summaries
  • Root cause analysis support (5 Whys, fishbone, 8D)
  • Corrective and preventive action (CAPA) drafting support
  • Inspection and test data trending
  • Audit preparation
  • Customer complaint handling support
  • Computer vision for visual inspection
  • Quality records and where AI may not operate
Hands-on exercise AI support on quality documents from participants' own areas
11
Day 2 · Module

AI in Production, Maintenance and Asset Reliability

  • Production applications:
    • Shift handover support
    • OEE and downtime analysis
    • Production record queries
  • Predictive maintenance:
    • Machine learning on sensor and work-order data
    • Anomaly detection and failure prediction
    • Condition monitoring
  • Language-model applications in maintenance:
    • Work order analysis
    • Troubleshooting support grounded in equipment manuals
    • Maintenance planning scenarios
    • Spare parts and MRO stock questions
  • Questions that belong to a data science team
Individual and pair work work order analysis and maintenance planning on a sample work-order export

Day 3: Building, Evaluating and Governing an Operations Agent

12
Day 3 · Module

AI Agents for Operations

  • What is an AI agent?
  • Agents, assistants and workflow automation
  • Tools and function calling
  • Memory (in-context, session, long-term)
  • Levels of autonomy and human-in-the-loop
  • The build spectrum (no-code, low-code, full-code)
  • Visual agent builders and coding agents (n8n, LangFlow, Claude Code)
  • AI features inside ERP, WMS and planning platforms (SAP, Oracle, Microsoft Dynamics 365, Kinaxis, Blue Yonder)
  • Agent failure modes (wrong tool, wrong data, fabricated result, silent failure)
  • The agent design brief (goal, inputs, tools, outputs, guardrails, success criteria)
Live demonstration an agent completing a multi-step logistics task end to end
13
Day 3 · Module

Building the Order and Shipment Reconciliation Agent

  • The lab environment (GitHub Codespaces, browser-based, pre-configured)
  • The wholesale distribution case (order book, shipment log, inventory file)
  • Exception rules (missing shipment, quantity mismatch, duplicate shipment, orphan shipment)
  • The restock report against reorder points
  • The two build tracks (visual canvas, coding agent)
  • Planted edge cases (recent orders, partial shipments, orphan records)
  • Acceptance criteria and automated checking of results
  • The exception that costs the business most
Lab building the order and shipment reconciliation agent end to end
14
Day 3 · Module

Monitoring and Evaluating the Agent

  • Observability for AI agents
  • Traces, spans and runs (LangSmith)
  • Trace contents (prompt, tool calls, model response, tokens, latency, cost)
  • The metrics baseline (latency, token use, cost per run, success rate)
  • Failure-mode probes
  • Optimisation levers (instruction, model choice, tool set, task decomposition)
  • Measured before-and-after comparison
  • Evidence for a reviewer
Lab instrumenting the reconciliation agent, recording a metrics baseline and running a failure-mode probe
15
Day 3 · Module

Governance, Data and Controls for AI in Operations

  • The AI governance toolkit:
    • The acceptable-use policy
    • Approved tools and access control
    • Human oversight and approval points
    • Vendor and tool due diligence
    • Logging and audit trails
  • Data classes that stay out (customer, supplier, pricing, personal and contract data)
  • Data residency and enterprise agreements
  • The allow, block and escalate pattern
  • Agent permissions (read-only, write, approval)
  • The AI use register and change control
  • Standards and frameworks (ISO/IEC 42001, the NIST AI Risk Management Framework, the EU AI Act)
Controlled group discussion the guardrails participants would set for AI in their own operation
16
Day 3 · Module

Emerging Methods

  • Context engineering
  • Loop engineering and graph engineering
  • Agentic retrieval-augmented generation (RAG)
  • Model Context Protocol (MCP)
  • Multi-agent systems and orchestration
  • Computer use and browser agents
  • Supply chain control towers and digital twins
17
Day 3 · Module

Capstone and the Ninety-Day Plan

  • The capstone build or agent review
  • Peer showcase
  • The pilot definition for the reconciliation agent (scope, owner, success criteria, review points)
  • The agent portfolio and sequencing
  • Team readiness and capability building
  • The ninety-day plan (next steps, priority use case, timeline, owners)
Personal action planning each participant's ninety-day AI plan for their operation
Day 3 · Course closing

Course closing

  • Course debrief and key takeaways
  • Final Q&A
  • Official closing ceremony and award of certificates
  • Group photo
Our training methodology

Three frameworks behind every programme.

Whatever programme you choose, it follows three proven instructional frameworks, from design to delivery to evaluation.

Delivery

TEA™ Delivery Framework

  • T Theory, core concepts & frameworks
  • E Examples, live demos & case studies
  • A Application, hands-on exercises & practice

Our signature approach structures every module into three phases for maximum retention and practical application.

Design

ADDIE Instructional Design

  • A Analyse, assess learner needs
  • D Design, structure the learning path
  • D Develop, build materials & activities
  • I Implement, deliver the programme
  • E Evaluate, measure outcomes & refine

The industry-standard model for course design and learning alignment.

Evaluation

Kirkpatrick Model

  • L1 Reaction, participant satisfaction
  • L2 Learning, knowledge & skills gained
  • L3 Behaviour, on-the-job application
  • L4 Results, business impact & ROI

The globally recognised four-level framework for measuring training effectiveness, from initial reaction to long-lasting post-training effects.

Upcoming sessions

Choose your date.

Private cohorts for operations and supply chain teams, live online or on site. Schedule a TNA call and receive a custom proposal within 48 hours.

Date
Format
Duration
Price
Private cohorts run on request.
Live virtual or On-site
1/2 to 5 days
Custom
What every participant gets

You keep everything.

No vendor lock-in, no paywalled materials. Every delegate leaves with the working files, the templates, and the post-programme support to actually use them.

Personal prompt library

8 – 12 tested prompts built during the session on your actual work scenarios.

Templates & dashboards

Dashboards, workflow templates, and evaluation frameworks ready to use.

Learning materials

Full soft copy of all session materials, handouts, and reference guides.

STOA certificate

Certificate of Completion plus a guided pathway to the Google AI certificate.

30-day support

Post-programme Q&A availability and implementation guidance.

Lifetime updates

Access to updated prompt libraries and resources as AI tools evolve.

Delivery options

Choose how your team learns.

In-Person

Instructor-led on-site

Delivered at your offices or venue. Maximum engagement for teams of 8 – 25 participants. All exercises use your team's actual work scenarios.

Live Online

Virtual instructor-led

Real-time delivery via Zoom, Meet, or Teams. Interactive breakout rooms, same content depth as in-person. Ideal for distributed teams.

Hybrid

Blended approach

Combine in-person and virtual sessions. Flexible scheduling across time zones. Pre-work materials and follow-up resources included.

Training catalogue

104 courses in nine families, overview level, methodology up front.

Download the catalogue
Ready to build

Give your operations team a working agent and the controls to run it.

Book a private programme for your operations and supply chain team. Custom proposal within 48 hours. Delivery live online or on site.