Customer forecasts change weekly, but materials, labour and machine plans are updated on a slower cycle. Planners see shortages, overtime and machine risks against the latest build plan, and can re-sequence before a delivery is missed.
A worked example for a typical Malaysian Electronics Contract Manufacturer, not a description of any real company. Go through the six stages in order: paste each prompt into Claude, check the answer against how your business really works, then continue. Change the profile at the start to match yours.
Stage 1 of 6
Map how the operation really runs
Act as an operations consultant. I run a Electronics Contract Manufacturer in Malaysia. Profile: A Malaysian electronics contract manufacturer — 3 plants in Penang and Johor, SMT and assembly lines, global OEM customers with volatile forecasts.
Interview me, one question at a time, to map how decisions actually get made today. Cover: the recurring meetings and reports, who decides what, which numbers people trust, and where decisions are late or made on gut feel.
Known friction: Busy lines vs. Room to adapt; Safety stock vs. Part shortages; Overtime vs. Defects; Big customers vs. Spreading risk; Low cost vs. Short lead time.
After 8 to 10 questions, summarise the five decisions that cost us the most when made late, in a table: decision, current owner, current delay, cost of delay.
Stage 2 of 6
Design the specialist agents
Using the decision map above, design 5 specialist AI agents for our Electronics Contract Manufacturer: Order Book, Component Supply, Line Staffing, Machine Health, Site Mix.
For each agent give: the one question it answers every day, the data it reads, what it may recommend, what it must never do alone, and the format of its output.
Starting points for what each should watch:
- Order Book: customer forecast changes, order book, capacity vs. demand
- Component Supply: component lead times, shortages, allocation risk, alternates
- Line Staffing: headcount vs. build plan, skills, overtime, foreign-worker quota
- Machine Health: OEE, machine-health trends, unplanned downtime
- Site Mix: plant margin, utilisation, product-mix fit
Keep every agent narrow. If an agent covers two jobs, split it.
Stage 3 of 6
Wire up data and compliance
For the agents above, list the data feeds needed. Likely systems: ERP and MES; Customer forecast portals; Maintenance system and machine sensors; HR and shift records.
Output a table per agent: field, source, how often it refreshes, data-quality risk, and what the agent should do if the feed is stale or missing. Mark every personal-data field and say how to minimise it.
Rules we operate under: Customer quality standards, export-control and customs rules, labour law on overtime, environmental licences, and customer NDAs on forecasts.
End with a short list of actions that always need human sign-off.
Stage 4 of 6
Design the morning brief
Design the single daily brief that pulls the 5 agents together for the CEO, ready before the first meeting of the day.
Specify how the brief merges overlapping or conflicting recommendations, how it ranks items (impact, urgency, reversibility, confidence), and the exact fields per item: what to decide, recommended action, evidence, owner, deadline, and the cost of doing nothing.
Then write a realistic sample brief of five items. Items might resemble: Expedite the 4,000-piece connector order: allocation risk starts in 9 days / Move Line 4 maintenance to Sunday: vibration trend is worsening / Re-sequence builds to protect the on-time delivery of the top customer.
Stage 5 of 6
Build and automate it
Turn the design into a working automation for our Electronics Contract Manufacturer.
Needs: a scheduled daily run; the 5 agents run in parallel and each saves structured JSON; a final step reads them all and sends the brief by email or chat; every run is logged with inputs, outputs and cost.
Propose the build with Claude plus a workflow tool (for example n8n or the Claude Agent SDK). Give the steps in order, what happens when a data feed fails, and a human-approval step before anything that spends money or makes a customer commitment.
Stage 6 of 6
Roll out and measure
Write a rollout plan for the Electronics Contract Manufacturer agent team that starts small and earns trust.
Stage 1: one agent, advisory only, run alongside the current process. Stage 2: add the other agents. Stage 3: switch on the daily brief. Stage 4: let agents prepare low-risk actions for approval.
For each stage give duration, owners, what "ready to move on" means, and the metrics to track: time to decision, how often recommendations are accepted, hours saved, and errors caught. Close with the three biggest risks and how we contain them.
