Recent Posts
-
The Identity Map I Wish I Had
I built a map of identity engineering, for engineers who lose track of what to read next and for developers who want a way into the field. If you do not write code, hand the address to your agent and let it read on your behalf.
-
XAA and EMA: Field Notes and Insights
Updated:Field notes from running Cross-App Access end to end: everything you need is optional, and there is no playbook yet.
-
DPoP, HTTP Signatures, and mTLS, and Why a Key Pair Is So Cool
Tying a token to a private key the client holds is a good idea, and not only for MCP. There are three places to do it, and each one stops something different.
-
Agents Need Their Own Accounts
Why AI agents fit neither human accounts nor service accounts: they execute work long after authorization was granted, alternating between delegated and independent authority. Makes the case for first-class agent identities that keep principal, actor, and delegation chain explicit.
-
Six Small Fixes That Make MCP Authorization Less Weird
An identity practitioner's read of the six authorization SEPs in the MCP 2026-07-28 release candidate. Small, unglamorous fixes are exactly what mature protocol work looks like: by converging on proven OAuth and OIDC patterns, this release brings MCP authorization a big step closer to stability and enterprise readiness.
-
My Development Workflow 2026-Q1 Edition
A tour of my agentic development workflow in five phases: brainstorm, design, plan, code, and review plus improve. Covers Cursor and Claude Code with Superpowers skills, AGENTS.md files, parallel worktrees, the MCP servers I rely on daily, and what a good day of mostly-autonomous software delivery actually looks like.
-
Authorization in a Shifting Maze
Why authorization tooling is straining in the AI era: OPA policies that grow slow and unexplainable past a few dozen rules, ReBAC systems like SpiceDB that trade flexibility for a queryable graph, and AI agents that sit inside the perimeter with no gateway in the loop, pushing us toward dynamic, function-level, context-aware authorization through protocols like MCP and A2A.
-
Next-Gen Languages, Compilers, and IRs for AI
How MLIR, TVM, and SPIR-V are replacing hand-tuned CUDA kernels in the AI stack: MLIR's reusable compiler dialects, TVM's auto-tuned kernel search that beat handwritten code on Apple M1 at launch, and SPIR-V's vendor-neutral GPU bytecode, and how the three cooperate so one model can run fast on any accelerator, from PyTorch 2.0 to WebGPU.
-
O Dia em que Construí uma IA para Prever Preços de Personagens de Tibia
A história completa do TCAQS, um modelo XGBoost que prevê preços de leilões de personagens de Tibia: raspando 650.000 páginas de leilão a três requisições por segundo, convertendo tudo em SQLite, e três rodadas de engenharia de features e limpeza de dados que levaram o modelo de um baseline de 0,89 até 0,935 de R² em teste, com demo ao vivo no Hugging Face Spaces.
-
The Day I Built an AI to Predict Tibia Character Prices
The full story of TCAQS, an XGBoost model that predicts Tibia character auction prices: scraping 650,000 auction pages at three requests per second, parsing them into SQLite, and three rounds of feature engineering and label cleaning that took the model from a 0.89 baseline to 0.935 test R², plus a live demo on Hugging Face Spaces.