ARTICLES
Technology and business,
from hands-on practice.
Articles on AI agents, business systems, financial AI, and e-commerce.
We write from the perspective of designing, building, and operating technology in real business contexts.
CATEGORIES
ALL ARTICLES (PAGE 4 OF 7)
Meta's Muse Code: Worktree Isolation Prevents Editing Collisions, but Integration Risks Remain
A design that prevents concurrent edits and consistency after integration are two different problems. Using Meta's first-party material on Muse Code as a starting point, we set out along three axes what is separated when coding agents run in parallel, and what is not.
Shadow AI and Verizon's 2026 DBIR: Designing the Approved Path
The 45% and the 67% measure different things. Read separately, they point to what actually needs designing: an approved path people choose over the unmanaged alternative.
Cloudflare's Agent Access Model: Permissions Beyond the Prompt
A reference architecture proposal and a private beta, read for what they say about binding, recording, and narrowing agent permissions outside the model.
Mercury Agent Cards: Enforced Spend Limits and Customer Liability
Telling an agent "spend up to this much" in a prompt is not the same as a limit that gets declined at authorization. And setting a limit does not move liability.
What Agent Plugins Standardizes—and What It Does Not: Portability for Agent Skills and MCP Configuration
Conformance to a common format does not guarantee the same behavior on another product. Separating what Agent Plugins 1.0.0 standardizes from what remains product- or organization-specific.
Bedrock Data's Agent DLP: Access Scope and Runtime Control
Permission settings tell you what an identity can reach. Runtime control tells you what a given tool call actually sent and received. Two controls worth keeping apart.
EU AI Act Becomes Generally Applicable: Key Annex III High-Risk Obligations Deferred to 2027
The AI Act became generally applicable on 2 August 2026, and the transparency obligations now apply. With key Annex III high-risk obligations deferred to December 2027, here is how the two timelines separate.
What GhostApproval Reveals About Approval Screens in AI Coding Agents
Having an approval screen and giving the approver a meaningful decision are two different things. A look at the blind spot GhostApproval revealed in AI coding agents' approval design.
73% of AI-Using Small Businesses Report an Impact on Employee Roles — What a U.S. Survey of 750 Owners and Operators Shows
73% reported an impact on roles and responsibilities, 70% on performance expectations — separating what the survey shows from what it does not.