Workshop contents
Session 1 · Layer 4
Agentic AI
Running without being asked
Until now, every action required someone to type a prompt. Now the AI operates on its own schedule.
Step 4.1 — The autonomous agent scenario
Name: Supply Chain Monitor Trigger: Runs daily at 6:00 AM INSTRUCTIONS: 1. Pull yesterday's delivery data 2. Calculate late delivery rate by region and shipping mode 3. Compare to the 30% target KPI 4. IF any region exceeds 50% late delivery rate: - Analyse contributing factors (carrier, product mix, volume spike) - Generate alert with supporting evidence - Draft recommended action - Send summary to VP Logistics 5. IF all regions are below 30%: - Log "All clear" and update weekly trend tracker 6. Every Friday: generate weekly performance summary with trend analysis
Show the output. Walk through a bad day and a good day. In the historical data, most regions sit between 53% and 58% — so the alert is today’s reality and the all-clear is the target state.
This agent runs every morning without being asked. But it depends on clean data, reliable execution, and well-defined exceptions. Who monitors the monitor?
Lesson. Agentic AI operates across time without being prompted. The executive question is not how many agents you deploy, but what each one may access, recommend, and execute.
Step 4.2 — Beyond a single agent
Organisations rarely run one agent. What they run is a small set of specialised agents in a hub-and-spoke arrangement, not a peer-to-peer network negotiating with itself.
| Specialised roles | Each agent handles one distinct task: demand forecasting, delivery monitoring, carrier optimisation, cost control. |
| Centralised output | The agents do not message each other. Each feeds its findings and alerts into one executive summary, which is the only thing a person reads. |
| Governing boundaries | Organisational guardrails bound every agent. The defining question for each is what it may access, decide, and escalate. |
The structure is what keeps this manageable. Several agents contribute to one unified picture for leadership, without unchecked interaction between the agents themselves.
If four agents disagree, who reconciles them — and does that person see the disagreement, or only the summary?