Posts
Independent essays on AI-native work patterns, agent infrastructure, and what actually works when running agents as real tools.
-
The Enterprise MCP Pattern: Proxy, Aggregate, Host
There are 58 public MCP servers in the awslabs catalog covering cloud infrastructure, databases, AI/ML, and ops tooling. Here's the enterprise pattern: proxy them locally, then host the proxy behind a gateway so every developer in your org gets them without setup.
-
The Website Is Not the Product
AI crawlers are extracting content at 60,000 pages per visitor sent back. The website is becoming a fallback UI. The real distribution layer is structured, machine-readable context — and nobody is building for it yet.
-
The Missing Middle: Why AI Chiefs of Staff Fail Without Calendar Materialization
Every AI Chief of Staff tool tells you what matters. None of them answer 'when will I do it?' The gap between a morning brief and actual execution is calendar materialization — and without it, triage is noise with structure.
-
The Meta-Tool Pattern: Teaching Your Agent to Discover Its Own Tools
The MCP token tax has a fix. The solution isn't fewer tools — it's a smarter way to load them. Here's the pattern.
-
Building the MCP Proxy: What Broke and What I Changed
The proxy pattern from part two, built and debugged. Two things broke: a missing dependency that crashed startup silently, and a response format that made the model do unnecessary work.
-
The MCP Token Tax
MCP won the read path. The token tax is what happened next. And the write path still doesn't have an answer.
-
Memories Fade. Skills Persist.
When an agent makes a mistake, you have two choices: write it down or encode it. One survives the next session. One doesn't.
-
Your Agent Needs Six Voices, Not One
A single system prompt persona doesn't scale. When agents run at speed across contexts, voice consistency requires something more durable.