Writing
I write about the practical side of AI: what it takes to move from interesting demos to useful systems inside real organizations.
The themes I keep coming back to are enterprise adoption, agentic workflows, AI productization, evaluation, observability, operating models, and the infrastructure reality behind AI delivery.
Less “AI will change everything.”
More “Here is what breaks when you try to make it work.”
A detailed write-up on Agents With Brakes, a reference architecture for enterprise agent platforms built around policy, identity, tool access, evals, observability, approvals, cost control, memory, and failure management.
GuardianLLM is my open-source experiment in age-aware AI safety middleware for child-facing LLM applications.
PromptShield is my open-source, local-first privacy firewall for generative AI prompts.
KnowledgeOS is my open-source lab for the architecture enterprise AI needs after the chatbot demo: meaning, evidence, policy, evaluation, and traces.
AgentDesk is my exploration of the policy, observability, evaluation, and cost-control layers computer-use agents need before they belong in real workflows.
A small simulator for understanding agent workflow cost, routing, reliability, guardrails, and observability tradeoffs before production teaches the lesson with a bill.
A policy-driven gateway for secure AI agent tool execution with scopes, approvals, sandboxing, risk checks, budgets, and audit logs.
A field guide to prompt injection, tool overreach, infinite loops, context poisoning, and hallucinated tool calls in agentic AI systems.
A small Python project showing how planner, executor, reviewer, and orchestrator roles make multi-agent workflows easier to understand.
A beginner-friendly A2A project showing how specialized agents discover each other, exchange tasks, and collaborate through protocol boundaries.
A beginner-friendly MCP project showing how AI assistants can safely read, search, and update local notes through controlled tool access.