Journal
September 16, 2026
MCP’s stateless core makes agent infrastructure easier to scale, but it moves responsibility for authority, progress, and recovery into the application. Here is the architecture test enterprises should run.
September 7, 2026
Enterprise AI agents should be evaluated against authoritative business state, not merely their execution traces. A practical architecture test for outcomes, authority…
Read article →
September 3, 2026
For much of the generative AI boom, enterprise technology strategy has revolved around one question: Which model should we use? GPT, Claude,…
Read article →
September 3, 2026
The enterprise AI conversation is shifting from model selection to governed execution. Here are the architecture decisions behind identity, MCP, orchestration, semantics…
Read article →