Bed pressure, pharmacy stock and nurse rosters are handled in daily huddles with incomplete information. Operations leaders get an early read on capacity, critical-drug stock and equipment risk, with every clinical decision left to clinicians.
A worked example for a typical Malaysian Private Hospital Group, 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 Private Hospital Group in Malaysia. Profile: A Malaysian private hospital group — 8 hospitals, ~2,500 beds, strong inpatient and day-surgery mix, in-house pharmacies and biomedical engineering.
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 wards vs. Patient comfort; Safe nurse ratios vs. Wage bill; Never running out vs. Expired stock; Speed vs. Bedside time; New centres vs. Clinical oversight.
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 Private Hospital Group: Bed Flow, Medicine Stock, Nursing Cover, Equipment Uptime, Specialty 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:
- Bed Flow: admission forecasts, discharge delays, theatre schedule, bed turnover
- Medicine Stock: critical-drug stock, expiry, cold-chain excursions
- Nursing Cover: nurse-to-patient ratios, agency spend, leave and fatigue
- Equipment Uptime: downtime on critical equipment, calibration due, service contracts
- Specialty Mix: service-line margin, referral patterns, capacity-expansion cases
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: Hospital information system (aggregate operational data); Pharmacy inventory; Nursing roster; Biomed asset register.
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: Private Healthcare Facilities and Services Act, MOH guidelines, PDPA 2010 — agents work on aggregate and de-identified operational data, and make no clinical decisions.
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: Open the 6th-floor overflow ward by 10:00 — admissions forecast is 18% above bed capacity / Reorder the temperature-sensitive biologics ahead of the supplier holiday / Schedule the MRI preventive service for Sunday to avoid peak days.
Stage 5 of 6
Build and automate it
Turn the design into a working automation for our Private Hospital Group.
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 Private Hospital Group 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.
