Underwriting, claims and capital teams see the portfolio through different reports and different time lags. Management sees loss trends, claim backlogs and solvency headroom together, with fraud and fairness checks built into the flow.
A worked example for a typical Malaysian General & Life Insurer, 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 General & Life Insurer in Malaysia. Profile: A Malaysian composite insurer — motor, health, life and SME lines, agency and bancassurance distribution, 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: Growth vs Loss ratio; Fast claims vs Fraud control; Persistency vs Acquisition; Capital vs Return; Price vs Fairness to customers.
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 General & Life Insurer: Underwriting, Claims, Distribution, Capital, Portfolio.
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:
- Underwriting: loss ratios by segment, rate adequacy, referral queues
- Claims: claim cycle times, leakage signals, fraud indicators, backlog
- Distribution: agent productivity, persistency, partner performance
- Capital: RBC ratio headroom, reserve development, reinsurance cover
- Portfolio: line profitability, product gaps, regulatory change impact
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: Policy admin and claims systems; Agent and partner performance reports; Actuarial and reserving models; Fraud and investigations case 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 rules, Financial Services Act, fair-treatment expectations, PDPA 2010 and sensitive health data rules. Claims and underwriting decisions remain with authorised 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 motor referral rules for the segment with an 82% loss ratio / Fast-track 300 low-risk health claims to clear the backlog / Review the partner with a persistency drop of 9 points.
Stage 5 of 6
Build and automate it
Turn the design into a working automation for our General & Life Insurer.
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 General & Life Insurer 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.
