WebMCP Explained: How AI Works with a Live Web Page
A beginner-friendly explanation of why WebMCP was proposed, its two ways to describe page features, how it differs from adjacent technologies, and how to test it safely.
AI Agents
16 posts with the tag “AI Agents”
What Is AdCP? Governing AI Advertising from Creation to Delivery
A practical reading of AdCP Creative, Governance, and Trust specifications for connecting AI-generated ads to review, approval, and delivery.
Agent Observability Without Centralizing Conversation Content
A design for monitoring long-running agent behavior through minimal safety signals without centralizing conversations and documents.
Verification-First Agents: Validating Answers Through Evidence
A Verification-First design that links claims to evidence as they are produced and independently checks them before action.
What Is OpenMontage? Governing AI Video Production in the Enterprise
An explanation of OpenMontage as a way to organize the stages, responsibilities, approvals, and records of AI video production rather than as a list of code features.
What Is Palantir Ontology? Designing an Operational Layer
A guide to Palantir Ontology covering its origins, Objects, Links, Actions, Functions, permissions, applications, differences from knowledge graphs and RAG, and a practical PoC decision framework.
What Is Hermes Agent? Differences, Use Cases, and Extensions
A research-based overview of Hermes Agent covering framework differences, use cases, extensions, and considerations for organizational use.
What Is SkillOps? How Google Operates Agent Skills
Google revealed how it builds, tests, and scales Agent Skills on August 4, 2026. This article explains the concrete practices and a practical SkillOps adoption path.
Choosing AI Agent Output: HTML or Markdown
Using the Claude Code team's HTML workflow as a starting point, this article separates when to use Markdown, HTML, XML, and JSON for AI agent outputs.
Designing Self-Healing Loops for Coding Agents
A practical guide to coding-agent self-healing loops based on 2026 research and official implementations from OpenAI, Google, and GitHub, covering layered verification, stop conditions, permission boundaries, and human approval.
Claude Dynamic Workflows: Architecture and Parallel Task Design
A plain-language guide to Dynamic Workflows in Claude Code: how multiple AI workers divide a job, which tasks fit, and how to plan outputs, limits, costs, and resumption.
How to Preserve AI Workflow Decisions in lessons.md
How to record an AI workflow problem, cause, resolution, and prevention in lessons.md as a decision history that later work can verify.
Approval Gates for AI Agent Build Commands
A record of how a production build command ran while I was asking AI to make a separate change, and the approval-required rule I put in place afterward.
What Is Harness Engineering? A Three-Layer AI Development System
AI gives different answers to the same question, and it does not remember previous sessions. This article explains how I use the term Harness Engineering for this site's AI operation practices.
How to Detect AI Agent Harness Drift Automatically
How harness drift separates shared rules from tool-specific configuration, and how synchronization checks detect the mismatch earlier.
What Work to Delegate to AI: Three Decision Criteria
A pre-delegation risk check for AI tasks, using reversibility, scope of impact, ease of verification, and the human decisions that should remain under human control.