Refs
A tree of the external references I follow — scientific papers, strategic consulting reports and open-source frameworks, organized by theme.
Agentic AI & Multi-Agent Orchestration
Frameworks and patterns for systems that plan, reason and use tools autonomously.
RAG, Memory & Context Engineering
Retrieval augmentation, long context and persistent memory for grounding LLMs.
Evaluation, Reliability & Guardrails
How to measure, compare and safeguard LLM systems in production.
AI Governance
Frameworks and standards to manage risk, accountability and the AI lifecycle.
AI Regulation (Brazil & global)
Legal frameworks in the making — from the EU AI Act to Brazil's PL 2338.
AI in Regulated Sectors
Health, insurance and finance: guidances, principles and systemic implications.
Organizational Design & Operating for AI
How to structure teams, platform teams and operating models for AI.
AI Product Management
Discovery, architecture and product practice in the generative-AI context.
AI Strategy & Economics
Consulting reports and analysis on the economic impact of AI.
AI Safety & Alignment
Safety, interpretability and the risks of increasingly capable AI systems.
LLMOps, Platforms & Open Source
Infrastructure, serving, observability and tooling to run AI at scale.
Maturity, Adoption & Future of Work
Maturity benchmarks, adoption surveys and AI's impact on work.