Chapters 9 to 17
The code from Parts III to V of Agentic AI for Actuaries. Nine chapters across pricing, reserving, life, and risk, each one runnable from this page.
Tool scripts run in the page. Edit them and run again.
Agent scripts run against Gemini. You watch the tool calls.
Any chapter, as a notebook, with your own free key.
Your first agents: a minimal Agno agent with a single tool, then a data quality agent that scans the defect-seeded motor India claims triangle and reports what it finds.
Designing actuarial tools: a mortality lookup with a validation gate, a present-value tool with structured error handling, and the term life premium agent that chains them together.
A fixed-path, three-step reserving review: a data quality agent checks the triangle, a reserving agent fits chain ladder and Bornhuetter-Ferguson and reconciles them, and a commentary agent drafts the memo.
Persistent and semantic memory: an agent that remembers the FY2024 Q3 experience adjustment across processes via SQLite, and a vector store over the synthetic experience study archive.
Commercial property underwriting for Meridian Re: COPE extraction from a broker submission PDF, GLM-vs-comparables premium reconciliation, and the three-agent underwriting workflow.
Reserving with reflexion: a Cape Cod tool that derives its expected loss ratio from the data, movement commentary that cites its sources, and the full reflexion workflow that reconciles against the prior cycle.
A multi-scheme pension pipeline for closed UK DB schemes: a quality gate on member data, a funding valuation with a six-way sensitivity panel, and member statements whose every figure carries a citation.
Regulatory monitoring, capital impact, and ORSA drafting: a source-of-truth registry guards authority, capital snapshots are read-only, and every quantitative claim in the draft carries a supervisor-grade citation.
Governance in production: a monitoring dashboard that scores each agent against the firm's threshold registry, and a governance agent that reads the dashboard and escalates.
Browser demos run on Pyodide, which is CPython compiled to WebAssembly. The first run downloads about 10 MB; after that it is quick, and nothing leaves your machine. The demo scripts follow the book code line for line.
Live agents run on our server with Gemini and Agno, and the tool calls stream back as they happen. There is a shared daily limit. If you hit it, the Colab notebook for the chapter has no limit.