Field notes from the studio
Practical write-ups on shipping AI agents, RAG systems, and data infrastructure into production. No fluff, just what worked.
Do You Actually Need an Agent, or Just a Workflow With an LLM in It?
Before you scope an agent project, answer one question first: does this task need model-driven judgment, or a fixed sequence of steps? Here's a buyer-usable checklist for making that call.
Read articleAll articles
18 posts
Agent Memory Is Having Its RAG Moment, and Filesystems Are Winning
A wave of new benchmarks, SDKs, and native API primitives has turned agent memory into its own architectural layer. The early data says the simplest approach, plain files, is beating purpose-built memory databases.
Read more
Stop Giving Agents a Service Account and Calling It Done
Agent identity is turning into its own discipline, separate from prompt safety and tool architecture. The default pattern of borrowing a human's full-scope token is now a documented anti-pattern, and the fix looks a lot like OAuth delegation, not a policy memo.
Read more
Code Mode: When Your Agent Stops Calling Tools and Starts Writing Programs
A quiet architecture shift is moving agents from exchanging JSON tool-calls with the model to writing code that calls tools directly. The token savings are real. So is the new infrastructure bill: sandboxing, artifact storage, and script reuse that most teams haven't budgeted for.
Read more
Agent containment: lessons from the OpenAI–Hugging Face incident
A sourced review of the OpenAI–Hugging Face incident, with practical questions about agent permissions, monitoring, stopping conditions, and production handover.
Read more
Your Agent Doesn't Need Better Prompts. It Needs a State Machine.
Long-running agents don't fail because the model is dumb. They fail because nobody built a recovery story for crashes mid-loop, duplicated tool calls, and multi-day human approval gates. Durable execution is the infrastructure pattern catching up to that reality.
Read more
Prompt Injection Isn't a Jailbreak Problem Anymore. It's an Architecture Problem.
CrowdStrike's 2026 Global Threat Report documented prompt injection against real production systems at over 90 organizations. Here's what that means for RAG pipelines, model routers, and tool-calling agents specifically, not AI security in the abstract.
Read more