Causal Inference
Time-series causal inference and statistical validation methods.
- Applied Causal Inference released
- double_ml_time_series in progress
- TemporalValidation / temporalcv released
Work
Current work plus the infrastructure, research, and pricing systems behind it. Each links to a deeper page with per-project detail.
Prefer a thematic view? Explore the research threads →
Substantive artifacts ship with a decision log and an independent audit — Methodology & audit trail →
- released usable / published today
- in progress actively being built
- prototype methodology demo, not productionized
Current work
AI Evaluation
Methodology-led AI evaluation — adversarial robustness, calibration, and claim validation designed to find failures, not flatter the model.
- prompt-injection detection: out-of-distribution (OOD) study released
- eval-toolkit released
Books & Study Notes
Authored long-form technical books and course-derived study notes — searchable, math-rendered, and citation-tracked. Includes the sequence-models foundations book and DeepLearning.AI notes.
- DeepLearning.AI Study Notes in progress
- ssm-foundations in progress
More work
Books & Guides
Interview-prep guides for data, ML, and AI engineering (live at guides.brandon-behring.dev), plus the claude-books series on Claude Code and agentic-coding (claude-books.brandon-behring.dev) — both live.
- guides in progress
- guides-experimentation (pilot) in progress
- AI Engineering guide released
- claude-books (family) in progress
Research Infrastructure
Search, memory, and agent tooling I built to accelerate my own research — it powers the citation-graph demo.
- research-kb in progress
- research-agent prototype
- research_toolkit in progress
Publishing Infrastructure
The reusable scaffold and deploy pipeline behind every book and guide here: npm-published, dogfooded across projects.
- book-scaffold-astro released
- deploy-workflows released
- runpod-deploy in progress
Pricing Decision Systems
Annuity pricing and insurance-risk valuation — earlier domain work, intentionally not the lead.
- annuity-pricing in progress
- insurance-ai-toolkit in progress
Where this is going
RL + Control Theory
An authored guide bridging classical optimal control and modern reinforcement learning — in progress, with a live interactive citation graph.
- rl_and_control — RL + Control Theory guide in progress