AI & ML interests
AI & ML for Actuarial Science
Recent Activity
Intelligent Actuaries
An AI lab for actuarial science.
We build agentic systems where actuarial science meets frontier AI — and ship them as the AI-native actuarial workbench: nine specialist agents that simulate, predict, advise, and explain across reserving, mortality, capital, climate, pricing, pensions, and regulatory. Every output is traceable from data to submission pack, with FSCA, IFRS 17, and SAM citations built in.
The roster
Nine specialist agents, four capabilities each — simulate · predict · advise · explain — orchestrated by a router that hands work to the right specialist and stitches the answer back together.
| # | Agent | Domain |
|---|---|---|
| 01 | Orchestrator | Routing · planning · multi-agent coordination |
| 02 | Reserving | P&C IBNR · chain-ladder · Mack 1993 · bootstrap |
| 03 | Mortality & Life | Lee-Carter · CBD · life contingencies |
| 04 | Capital & ESG | SCR · ESG paths · ALM · Solvency II / SAM |
| 05 | Climate & Cat | CLIMADA · OasisLMF · parametric design · EP curves |
| 06 | Pricing & ML | GLM · GBM · SHAP attribution · fairness |
| 07 | Pensions & Longevity | DB / DC valuation · longevity transfer |
| 08 | Regulatory | FSCA · PA · IFRS 17 · SAM · SARS · TFSA |
| 09 | Documentation | Quarto reports · ADRs · audit-log provenance |
What we've shipped
- 🌍 951m USD CLIMADA AAL anchor — reproducible AAL on a global tropical-cyclone exposure that locks down our climate & cat pipeline.
- ✅ 429 tests in CI —
mypy --strict, ruff, biome, and Bun tests gate every merge to main. - 🧠 9 / 9 specialist agents live — one SSE wire format across all surfaces; the router and the specialists ship together.
- 🖥️ Three surfaces, one workbench — Textual TUI, React + Vite web dashboard, and a published VS Code extension.
- 📜 Regulatory-aware by default — FSCA · IFRS 17 · SAM. Functions whose output lands in submission packs are pinned with
@regulatory; commits to them require an explicit sign-off marker. - 🔬 Foundation-model baselines — TimesFM-style benchmarks against classical actuarial methods, so practitioners can see where AI helps and where it doesn't.
Stack
Polyglot by design. Python is the glue; heavy compute drops to a Rust crate via PyO3, R via rpy2, and Julia via juliacall. Hermes Agent is the primary LLM provider — Ollama and Claude swap in with a single config flip.
FastAPI · Pydantic v2 · Textual · React · Vite · Bun · Apache ECharts · React Flow · xterm.js · PyO3 · Polars · DuckDB · rpy2 · ChainLadder · StMoMo · juliacall · Turing.jl · JuMP · Hermes Agent · Ollama · Claude · CLIMADA · OasisLMF · SHAP · Fairlearn
Where to find us
| 🌐 | Website | intelligentactuaries.com |
 |
GitHub | github.com/intelligentactuaries |
 |
VS Code | Marketplace → Intelligent Actuaries |
 |
linkedin.com/company/intelligentactuaries | |
 |
X | @aiactuaries |
Source-available
The workbench ships under the Intelligent Actuaries License v1.0 (LicenseRef-IA-1.0) — a UE-EULA-style source-available license. Free for any use while the licensee's gross revenue (aggregated across affiliates) is below USD 1,000,000 in any trailing twelve months; at or above that threshold a Commercial License is required.
- Commercial licensing · audit · indemnity · threshold questions: legal@intelligentactuaries.com
- General & partnerships: hello@intelligentactuaries.com
Built in South Africa 🇿🇦, for actuaries everywhere 🌏.