Demand, fuel, crews and asset condition are managed by separate teams on separate rhythms. Planners get a joined-up daily view of load, supply and equipment health, while grid control stays with licensed operators.
A worked example for a typical Malaysian National Utility, 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 National Utility in Malaysia. Profile: A Malaysian national electricity utility — generation, transmission and distribution, millions of customers, a mix of gas, coal, hydro and growing solar.
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: Always-on supply vs. Cost; Cheapest fuel vs. Cleaner fuel; Fix-before-fail vs. Fix-when-fail; Tariffs vs. Upgrades; Peak readiness vs. Idle plant.
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 National Utility: Demand, Fuel Supply, Repair Crew, Equipment Health, Investment.
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:
- Demand: load forecast by region, weather, industrial demand, tariff effects
- Fuel Supply: gas and coal stock, delivery schedules, price exposure
- Repair Crew: outage tickets, crew locations, restoration times
- Equipment Health: sensor trends on transformers, turbines and lines
- Investment: asset age and risk, renewals vs. new build, return on capex
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: SCADA and grid telemetry; Fuel contracts and stock; Outage management system; Asset register and maintenance 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: Energy Commission requirements, Grid Code, Electricity Supply Act, and tariff rules. Agents never issue control commands to the grid; dispatch stays with licensed operators.
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: Pre-position two crews in Johor ahead of the forecast storm / Bring forward the transformer T-14 inspection: temperature trend is outside tolerance / Delay the coal purchase by one week: spot price is falling.
Stage 5 of 6
Build and automate it
Turn the design into a working automation for our National Utility.
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 National Utility 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.
