Nine Failures, Zero Alerts: I Audited My Own AI Agent Fleet
Most ways of proving you can audit a system are unfalsifiable. A sample report about an invented company shows you can write like an…
Category
Agentic AI
posts
26
Agent APIs Are Becoming Runtime Contracts
For the last year, if you were building anything serious with agents, you spent most of your time building everything that was not the…
Silent Failure: What Running an Agent Fleet on OpenClaw Taught Me
One of my OpenClaw agents spent about ten weeks writing thoughtful weekly summaries of a feed that had gone completely empty. Every week it…
The Buyer Left
I wrote recently that agentic commerce takes the observer out of the buying journey: the human stops being the one watching the path from…
The Model Is Not the Market: The Limits of Synthetic Respondents
Picture the choice a consumer-research team faces this year. On one side, a real panel: weeks of fieldwork, incentive costs, recruiting, the slow grind…
The Observer Left: What Agentic Checkout Does to Attribution
A brand's growth team can usually tell you, close to the decimal, how a customer traveled from an ad to a purchase. Which impression,…
Agent Cost Is a Scheduling Problem, Not a Billing Problem
The bill arrived, and it changed the conversation about agents. EY illustrates the shift with a single line: a chat that cost about four…
When the Description Becomes the Routing Table
Salesforce put Multi-Agent Orchestration into its Summer '26 release. That matters less because Salesforce did it, and more because Salesforce sits inside a very…
Coding Agents Are Runtimes. Evaluate Them Like One
Most teams still evaluate coding agents with one question. Can it write the code? That question made sense when the product was autocomplete. You…
Model Escalation Is a Tool Call
On June 10, 2026, OpenRouter announced Advisor, a server-side tool that lets one model consult another model mid-generation. The obvious reading is cost optimization.…