What I cover
Multi-billion-dollar counterparty exposure to mortgage insurers, reinsurers, property insurers, and title insurers. Director since 2020, leading a team of four.
Matthew McClure
I lead (re)insurance counterparty credit risk covering billions of dollars of exposure — and build the AI systems that do the analysis.
Nineteen years in (re)insurance and capital markets risk. CPA, CFA, FRM, CIA. About a dozen agentic systems in production, on servers I run myself.
CPA CFA FRM CIA
Certified Public Accountant · Chartered Financial Analyst · Financial Risk Manager · Certified Internal Auditor
Director since 2020 · Nineteen years in counterparty credit risk
In every job I’ve had, the instinct has been the same: build the apparatus rather than do the task by hand. In risk, that meant stress-testing frameworks and rating models instead of another memo. With AI, it means about a dozen agents that read, rate, and draft. The book was the same instinct turned on my own work. Different tools, one habit.
Professional
The other side of the contract
Counterparty credit risk is the question of what happens to you when the other side of a contract can’t pay. For nineteen years that has been my job.
Stress testing
Built a stress-testing framework for mortgage insurers on the Federal Reserve’s CCAR scenarios — testing whether critical counterparties keep paying through a severe downturn.
Rating models
Built internal rating models for mortgage insurers and reinsurers with external analytics partners, so counterparty risk is measured consistently rather than case by case.
Capital standards
Contributed to the development of revised regulatory capital standards for U.S. mortgage insurers.
AI
I build the systems that do the analysis
About a dozen systems in production. Not demos — they run on a schedule and produce work I use.
Reads and rates what no one has time to read
Adverse-media research and earnings-call analysis, run against public sources.
Turns filings and calls into a written view
Annual review and industry outlook generators that produce a draft analyst-style view from public disclosure.
Runs a repeatable process end to end
Screening workflows, loss-estimate aggregation, structured multi-step review with checks built in.
Makes the output presentable
Interactive HTML reports, and an infographic generator running against 600 templates.
Worked example
A full earnings-call analysis — my pipeline, a public insurer’s public call, the unedited output — will be published here.
Two self-hosted n8n servers — a Mac mini and a Mac Studio — exposed through Cloudflare tunnels. Built with Claude Code, Codex, and Gemini. Deployed to Google Cloud Run.
The book
Productivity Supercharger: Reach Your Goals Faster by Working More Effectively on the Right Things
I read more than a hundred books on productivity and took dozens of courses, then wrote the one I wanted — what actually survives contact with a real job. Self-published, 2020.