Writing
[agents][agentic-web][protocols][ai-platforms][security][engineering][infrastructure][apis][authorization][governance][observability][pact][testing]
- What Would a Markets Regulator Ask of an Agent?
I tried to file one agent tool call as an order record under the EU trading rules. Of the eighteen fields that apply, six map to something standard and four have no source at all. Those rules have been binding since 2018, and in February the regulator pointed them at GenAI.
- How Long Does a Revoked Agent Keep Working?
I tried to write down the formula for revocation latency and it kept being wrong in instructive ways. The corrections come from validator source code: a five-minute grace on expired tokens in .NET, streams that outlive their token by design, and a 12-hour JWKS refresh on the one lever that actually works. With runnable experiments.
- Agent Accountability Starts With "On Whose Authority"
Only two fields are Required on the OpenTelemetry span that records an agent taking an action. Not who authorized it, not what it was allowed to do, not what it sent. Here's the gap, field by field, and what to do about it.
- Agents Are Speedrunning the History of RPC
When a tool call dies mid-flight, neither MCP nor A2A can tell you whether it executed, and no retry can prove it is the same request. RPC solved this in 1984. Three changes close the gap.
- When Agents Hire Agents: PACT, the Missing Layer 4 of the Agentic Web
A2A moves tasks without prices, x402 moves money unconditionally, AP2 authorizes without verifying. PACT adds the missing object: the Verifiable Task Contract.
- The Agentic Web Is Being Wired Right Now: A Field Guide to MCP, A2A, Skills, and Agent Payments
A field guide to the protocols wiring the agentic web: MCP for tools, A2A for agent-to-agent work, Skills for know-how, and the three-way fight over payments.
- Can You Trust an Autonomous Agent? The Identity and Delegation Layer Behind MCP, A2A, and AP2
Four questions a bearer token cannot answer: agent identity, authorization flows, delegation chains, and accountability, each mapped to its standard.
- The Hardware-Accelerated Mesh: How DPUs and Ambient Topologies Killed the Data Center Tax
How DPUs and ambient mesh topologies remove the sidecar tax from service networking.
- WebMCP: The HTTP of the Agentic AI Age
WebMCP as the missing protocol layer for agents that browse and act on the web.
- The Invisible Revolution: How AI is Rewiring the Data Center Network
Why AI traffic broke the old data center network and what is replacing it.
- The Enterprise AI Gap isn't Model IQ anymore. It’s Execution + Trust
Enterprise AI stopped being limited by model quality; execution and trust are the bottleneck now.
- AI Agents vs. Agentic AI vs. MCP Server–Based AI vs. A2A AI: Technical Angle
The same four terms, this time from the architecture and protocol side.
- AI Agents vs. Agentic AI vs. MCP Server–Based AI vs. A2A AI: Business Angle
Four overloaded terms untangled for decision makers: AI agents, agentic AI, MCP-based AI, and A2A.
- AI x APIs: The new power couple
OpenAPI-described services are becoming agent tools; what AI-first means for API teams.
- Agentic AI in Healthcare: From Monitoring to Meaningful Action
Turning continuous patient monitoring into safe, timely action with agentic AI.
- Automate. Predict. Grow: Why Managed AI Is the Fastest Path to Scale for SMBs
Why managed AI beats both complex tooling and simple tools for small and mid-sized businesses.
- AI-Powered Low-Code Platforms: Reimagining App Development for Everyone
How AI turns low-code platforms into a way for anyone to ship real applications.
- Mocking web services for testing and fault injection
Standing up mock web services to test SOA systems and inject faults on purpose, from 2015.
- Software secure coding standards and analysis
A 2015 walkthrough of Java secure coding standards and the static-analysis toolchain for enforcing them.