Pricing, liquidity, branch staffing and control issues each live in their own report, and the picture only comes together in committee. A short daily brief connects them, so a pricing tweak is weighed against funding headroom and branch capacity before it goes out.
A worked example for a typical Malaysian Retail & SME Bank, 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 Retail & SME Bank in Malaysia. Profile: A Malaysian retail and SME bank — ~120 branches, ~6,000 staff, a mix of consumer deposits and SME financing, regulated by Bank Negara Malaysia.
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: Earning more vs. Losing less; Cash on hand vs. Cash at work; Friendly service vs. Lean branches; Selling more vs. Staying compliant; Branches vs. Apps.
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 Retail & SME Bank: Pricing Desk, Funding, Branch Staffing, Controls, Network.
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:
- Pricing Desk: loan and deposit spreads, approval rates, early-delinquency signals
- Funding: LCR/NSFR headroom, funding mix, maturity gaps
- Branch Staffing: queue times, skills coverage, overtime and leave
- Controls: unusual transaction patterns, control breaches, open audit items
- Network: branch profitability, footfall vs. digital shift, consolidation candidates
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: Core banking extracts; Treasury and liquidity reports; Branch queue and roster systems; AML and case-management logs.
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: Bank Negara Malaysia policy documents, PDPA 2010, AMLA reporting duties, and the bank's own model-risk and outsourcing policies. Agents recommend; credit and compliance decisions stay with accountable humans.
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: Tighten SME unsecured pricing by 25bps in the Klang Valley cluster / Rebalance liquidity buffer ahead of month-end settlement / Escalate three branches with repeated KYC-refresh breaches.
Stage 5 of 6
Build and automate it
Turn the design into a working automation for our Retail & SME Bank.
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 Retail & SME Bank 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.
