Day 60: From model demos to mission-ready AI systems
A practical map for moving from impressive AI demos to systems people can trust.
Jul 20, 20263 min read25
Pinned
Command Palette
Search for a command to run...
Latest articles
Autonomy is a runtime decision, not a model decision
Agents get more capable by default. They only get bounded on purpose.
Jul 30, 20263 min read9
When MCP earns its overhead, and when a direct API is better
One question settles most of these arguments: will more than one AI application need this capability?
Jul 28, 20263 min read4
A clean connector does not make a reliable agent
Connector correctness and agent behaviour are separate problems. Most teams only test the first one.
Jul 27, 20262 min read
Tools, resources and prompts are not interchangeable
Choosing the wrong primitive hands the model authority a person was supposed to hold.
Jul 25, 20262 min read1
Where your MCP server runs is a production decision
Transport looks like a technical detail during the demo. It is really a choice about ownership, reachability and trust.
Jul 24, 20263 min read77
What the MCP protocol actually standardises
It settles how capabilities are described and discovered. Every decision about whether to trust them is still yours.
Jul 23, 20262 min read6
Day 59: Why production AI is coordinated infrastructure
Why production AI is the coordination of data, models, tools, controls, evaluation, and people.
Jul 19, 20263 min read1
Day 58: Why governance belongs in the architecture
Why governance belongs in the architecture, not in a document after launch.
Jul 19, 20263 min read