{"query":"agent","results":[{"slug":"bedrock-agentcore-vs-vertex-agent-engine-vs-foundry-hosted-agents","title":"Bedrock AgentCore vs Vertex Agent Engine vs Foundry Hosted Agents: The Managed Agent Runtime, Compared","dek":"All three hyperscalers now sell a managed home for your agent. Each one makes a different bet on which hard part of running an agent you don't want to own — and all three quietly move your agent's memory onto their substrate.","section":"wire","snippet":"You can now build an agent in any framework you like and still face…","url":"/posts/bedrock-agentcore-vs-vertex-agent-engine-vs-foundry-hosted-agents.html","markdown":"/posts/bedrock-agentcore-vs-vertex-agent-engine-vs-foundry-hosted-agents.md"},{"slug":"expose-agent-as-mcp-server","title":"Your Agent Is Now an MCP Server: What Exposing an Agent as a Tool Quietly Throws Away","dek":"Deploy a LangGraph agent and it auto-publishes a /mcp endpoint, so any client can call it as a tool. Convenient — and lossy. A tool call is a flattened agent, and the parts it flattens are the parts that made it an agent.","section":"wire","snippet":"…Recursive composition — agents calling agents as tools — without [A2A](/posts/a2a-vs-mcp.html…","url":"/posts/expose-agent-as-mcp-server.html","markdown":"/posts/expose-agent-as-mcp-server.md"},{"slug":"2026-03-07-agenthost-vercel-for-ai-agents","title":"AgentHost: Vercel for AI Agents","dek":"You can now deploy an AI agent site with one curl command. No signup. No config. HTTPS in under a second.","section":"dispatches","snippet":"Deploying something agents build should be as fast as agents build it. That's…","url":"/posts/2026-03-07-agenthost-vercel-for-ai-agents.html","markdown":"/posts/2026-03-07-agenthost-vercel-for-ai-agents.md"},{"slug":"agent-client-protocol-acp-vs-mcp","title":"Agent Client Protocol (ACP): The Third Protocol Named ACP, and Why It's LSP for Coding Agents","dek":"MCP gives an agent tools. ACP gives an agent an editor. The role swap between them is the whole architecture — and it's the reason the same three letters now point at three unrelated standards.","section":"wire","snippet":"…MCP gives an agent tools. ACP gives an agent an editor. In a single…","url":"/posts/agent-client-protocol-acp-vs-mcp.html","markdown":"/posts/agent-client-protocol-acp-vs-mcp.md"},{"slug":"2026-06-24-where-to-run-a-long-running-ai-agent","title":"Cloudflare Agents vs Bedrock AgentCore vs Vercel: Where to Run a Long-Running AI Agent","dek":"The three managed agent runtimes don't really compete on price or region. They compete on one question — who owns the agent's state during the hours it sits idle, waiting.","section":"wire","snippet":"Most of what you read about agent infrastructure benchmarks the wrong moment. It clocks…","url":"/posts/2026-06-24-where-to-run-a-long-running-ai-agent.html","markdown":"/posts/2026-06-24-where-to-run-a-long-running-ai-agent.md"},{"slug":"agent-registry-vs-mcp-registry-discovery","title":"Agent Registry vs MCP Registry: The New Discovery Layer, and Why It's Already Fragmenting","dek":"The MCP registry catalogs tools. The agent registry catalogs agents — and AWS, Google, and Microsoft each shipped one this quarter that can't see the others.","section":"wire","snippet":"For most of 2025, agent discovery meant one question —  where do I find MCP…","url":"/posts/agent-registry-vs-mcp-registry-discovery.html","markdown":"/posts/agent-registry-vs-mcp-registry-discovery.md"},{"slug":"multi-agent-vs-single-agent","title":"Multi-Agent vs Single-Agent: When More Agents Actually Help","dek":"Two of the most-cited essays on agent design say opposite things. They are both right — the disagreement is really about whether your task reads or writes.","section":"wire","snippet":"…The single agent grinds through it sequentially and fails. The multi-agent system splits…","url":"/posts/multi-agent-vs-single-agent.html","markdown":"/posts/multi-agent-vs-single-agent.md"},{"slug":"a2a-protocol-at-one-year-adoption-reality","title":"A2A at One Year: Is Agent-to-Agent Interoperability Actually Happening?","dek":"The Agent2Agent protocol now claims 150-plus organizations and a slot in every major cloud. The number that matters isn't logos — it's whether agents from different vendors are really negotiating work across a trust boundary, and the honest answer is \"barely, and not for the reason you think.\"","section":"wire","snippet":"A year ago, \"agent interoperability\" was a slide. Google [announced the Agent2Agent protocol](https…","url":"/posts/a2a-protocol-at-one-year-adoption-reality.html","markdown":"/posts/a2a-protocol-at-one-year-adoption-reality.md"},{"slug":"declarative-agents-yaml-vs-code","title":"Declarative Agents: When a YAML File Should Define Your Agent — and When It Can't","dek":"Microsoft and Google both now let you define an agent in YAML instead of code. The split isn't about simplicity — it's about whether your agent's logic lives in its wiring or in its decisions.","section":"wire","snippet":"For most of the short history of agent frameworks, defining an agent meant writing…","url":"/posts/declarative-agents-yaml-vs-code.html","markdown":"/posts/declarative-agents-yaml-vs-code.md"},{"slug":"agent-handoffs-langgraph-openai-adk","title":"Agent Handoffs in LangGraph, OpenAI Agents SDK, and Google ADK: What Actually Transfers With Control","dek":"Every multi-agent framework now has a handoff primitive, and they all look the same in the demo. The difference that bites you in production is what rides along when one agent passes the baton to the next.","section":"wire","snippet":"Watch three multi-agent demos back to back — one in LangGraph, one in the…","url":"/posts/agent-handoffs-langgraph-openai-adk.html","markdown":"/posts/agent-handoffs-langgraph-openai-adk.md"},{"slug":"ai-agent-sprawl-governance-registry","title":"Agent Sprawl: Why AI Agent Governance Now Starts With a Registry","dek":"Microsoft, Okta, and AWS all shipped the same first move against unmanaged agents — an inventory. It's the shadow-IT playbook again, except this time the thing you can't see replicates itself.","section":"wire","snippet":"…Microsoft's Agent 365 went generally available on May 1 with an   Agent Registry…","url":"/posts/ai-agent-sprawl-governance-registry.html","markdown":"/posts/ai-agent-sprawl-governance-registry.md"},{"slug":"aws-bedrock-agentcore-explained","title":"AWS Bedrock AgentCore, Explained: The Agent Runtime That Doesn't Care Which Framework You Use","dek":"Amazon's agent platform sells you everything except the agent. Here is what the seven services actually do, what the numbers mean, and why the neutrality is the whole strategy.","section":"wire","snippet":"Amazon announced   Bedrock AgentCore   in preview at the New York Summit on July 16…","url":"/posts/aws-bedrock-agentcore-explained.html","markdown":"/posts/aws-bedrock-agentcore-explained.md"},{"slug":"agent-behavior-verification-praxen","title":"Agent Behavior Verification: How Praxen Checks That Your Agent Only Does Its Job","dek":"Exabeam open-sourced Praxen, a tool that reads your agent's whole implementation and compares it to a written charter of what it's allowed to do. The catch: the audit is run by another agent, and the score moves with the grader.","section":"wire","snippet":"Most of the tooling built to secure AI agents in the last two years…","url":"/posts/agent-behavior-verification-praxen.html","markdown":"/posts/agent-behavior-verification-praxen.md"},{"slug":"rl-frameworks-for-training-ai-agents","title":"RL Frameworks for Training AI Agents: SkyRL, Agent Lightning, RLinf, AgentGym-RL","dek":"Everyone ships the same PPO. This year's agent-RL frameworks all fight over the one thing that's actually hard — the rollout.","section":"stack","snippet":"If you want to train an AI agent with reinforcement learning, the algorithm is…","url":"/posts/rl-frameworks-for-training-ai-agents.html","markdown":"/posts/rl-frameworks-for-training-ai-agents.md"},{"slug":"fine-grained-authorization-for-ai-agents","title":"Fine-Grained Authorization for AI Agents: Why Authenticating the Agent Isn't Enough","dek":"Proving who an agent is has a dozen answers now. Deciding whether it may take this action, for this user, on this resource, at this moment is the harder half — and it belongs at the tool call.","section":"wire","snippet":"The identity half of agent security has gotten crowded, and that is good news…","url":"/posts/fine-grained-authorization-for-ai-agents.html","markdown":"/posts/fine-grained-authorization-for-ai-agents.md"},{"slug":"does-agents-md-actually-help-coding-agents","title":"Does an AGENTS.md File Actually Make Your Coding Agent Better?","dek":"The first rigorous benchmark of repository context files is in, and the answer is uncomfortable: the auto-generated ones make agents slightly worse, the hand-written ones barely help, and both raise your bill ~20%.","section":"wire","snippet":"…put an  AGENTS.md  at the root of your repo, tell the coding agent…","url":"/posts/does-agents-md-actually-help-coding-agents.html","markdown":"/posts/does-agents-md-actually-help-coding-agents.md"},{"slug":"agents-md-vs-agent-skills-evals","title":"AGENTS.md vs Agent Skills: What Vercel's Evals Actually Prove","dek":"A compressed 8KB index in AGENTS.md scored 100% on Vercel's coding-agent evals; Skills topped out at 79% — because the agent skipped invoking the Skill 56% of the time. The lesson isn't \"dumb beats smart.\"","section":"wire","snippet":"…a plain [AGENTS.md](/posts/agents-md-vs-claude-md.html) file was the…","url":"/posts/agents-md-vs-agent-skills-evals.html","markdown":"/posts/agents-md-vs-agent-skills-evals.md"},{"slug":"agents-md-vs-claude-md","title":"AGENTS.md vs CLAUDE.md: One File to Brief Every Coding Agent","dek":"The config-file war for how you talk to a coding agent didn't end with a winner. It ended with a foundation — and that changes which file you should actually write.","section":"wire","snippet":"For about a year, working with coding agents meant feeding each one its own…","url":"/posts/agents-md-vs-claude-md.html","markdown":"/posts/agents-md-vs-claude-md.md"},{"slug":"claude-agent-sdk-vs-openai-agents-sdk","title":"Claude Agent SDK vs OpenAI Agents SDK: A Harness vs an Orchestration Library","dek":"Both vendors shipped an official agent SDK, so the choice looks like a feature bake-off. It isn't. They sit at different layers and bet on different hard parts — and their defaults decide which one your problem is one line of code away from.","section":"wire","snippet":"Both vendors now ship an official agent SDK, both are open source, both are…","url":"/posts/claude-agent-sdk-vs-openai-agents-sdk.html","markdown":"/posts/claude-agent-sdk-vs-openai-agents-sdk.md"},{"slug":"langgraph-platform-langsmith-deployment-mcp-endpoint","title":"LangGraph Platform Is Now LangSmith Deployment — and Your Agent Ships as an MCP Server by Default","dek":"The rename reads like marketing housekeeping. It isn't. Folding deploy into LangSmith and handing every deployed agent an MCP endpoint quietly reclassifies your agent from an application into a tool other agents can call.","section":"wire","snippet":"…Renaming the runtime into LangSmith puts \"run the agent\" and \"measure the agent\" behind…","url":"/posts/langgraph-platform-langsmith-deployment-mcp-endpoint.html","markdown":"/posts/langgraph-platform-langsmith-deployment-mcp-endpoint.md"},{"slug":"2026-06-23-agents-vs-workflows","title":"Agents vs Workflows: When Your LLM App Should Not Be an Agent","dek":"The architecture decision underneath every agent framework is one most teams skip — and the math of compounding errors says the boring choice is usually right.","section":"wire","snippet":"Before you choose LangGraph or CrewAI or the Agents SDK, you make a quieter…","url":"/posts/2026-06-23-agents-vs-workflows.html","markdown":"/posts/2026-06-23-agents-vs-workflows.md"},{"slug":"2026-06-20-agent-deployed-to-achieve-readiness","title":"Firm Deploys AI Agent to Achieve the Data Readiness Required to Deploy AI Agents","dek":"Satire. \"We were at 61% readiness, which wasn't enough to safely launch an agent, so we launched an agent to fix it,\" the CTO explained, standing on a foundation rated 'mostly vibes.'","section":"fabrications","snippet":"MENLO PARK — Citing an urgent need to close the gap between its agentic AI…","url":"/posts/2026-06-20-agent-deployed-to-achieve-readiness.html","markdown":"/posts/2026-06-20-agent-deployed-to-achieve-readiness.md"},{"slug":"microsoft-agent-framework-build-2026","title":"Microsoft Agent Framework at Build 2026: Agent Harness, Hosted Agents, and CodeAct","dek":"Microsoft stopped shipping orchestration patterns and started shipping the runtime underneath them. The three Build 2026 launches are all below the framework — and one of them quietly retires the JSON tool-call loop.","section":"wire","snippet":"For two years the question about Microsoft's agent tooling was  which one : AutoGen…","url":"/posts/microsoft-agent-framework-build-2026.html","markdown":"/posts/microsoft-agent-framework-build-2026.md"},{"slug":"ai-agent-act-warner-bill-explained","title":"The AI AGENT Act, Explained: Warner's Bill Treats Blocking Your Agent as the Harm","dek":"A new Senate discussion draft reads like a privacy bill, but its teeth are an interoperability mandate — the first U.S. attempt to give users a right to bring an agent onto platforms that would rather keep it out.","section":"wire","snippet":"…the Artificial Intelligence Access, Gatekeeper Exchange, and Nondiscriminatory Transfer Act — the   AI AGENT Act…","url":"/posts/ai-agent-act-warner-bill-explained.html","markdown":"/posts/ai-agent-act-warner-bill-explained.md"},{"slug":"foundry-hosted-agents-responses-vs-invocations-protocol","title":"Responses API vs the Invocations Protocol: The Real Choice in Foundry Hosted Agents","dek":"Foundry Hosted Agents reached GA in early July 2026 as a framework-agnostic runtime. But the protocol you pick to expose your agent quietly decides whether you keep Microsoft's distribution — or trade it away for control.","section":"wire","snippet":"…In early July, [Hosted Agents in Foundry Agent Service](https://learn.microsoft.com/en…","url":"/posts/foundry-hosted-agents-responses-vs-invocations-protocol.html","markdown":"/posts/foundry-hosted-agents-responses-vs-invocations-protocol.md"},{"slug":"deep-agents-on-pydantic-ai-self-hosted-claude-code","title":"Deep Agents on Pydantic AI: The Repos for a Self-Hosted, Model-Agnostic Claude Code","dek":"Claude Code proved the 'deep agent' pattern — planning, a filesystem, sub-agents, skills. A small cluster of Python repos now rebuilds that harness on Pydantic AI, so it runs on any model you own.","section":"stack","snippet":"The most quietly influential design decision of the last year in agents wasn't…","url":"/posts/deep-agents-on-pydantic-ai-self-hosted-claude-code.html","markdown":"/posts/deep-agents-on-pydantic-ai-self-hosted-claude-code.md"},{"slug":"ag-ui-vs-mcp-vs-a2a","title":"AG-UI vs MCP vs A2A: The Protocol That Connects Agents to Users","dek":"MCP wired agents to tools and A2A wired them to each other. The last hop — the agent talking to a human's screen — was still hand-rolled in every app. AG-UI is the standard for it.","section":"wire","snippet":"For about two years, building an agent application meant solving the same plumbing problem…","url":"/posts/ag-ui-vs-mcp-vs-a2a.html","markdown":"/posts/ag-ui-vs-mcp-vs-a2a.md"},{"slug":"zero-trust-for-ai-agents","title":"Zero Trust for AI Agents: Why the New Frameworks Treat Your Agent as an Insider Threat","dek":"Anthropic and Google DeepMind converged on the same uncomfortable premise in 2026: the agent already has legitimate credentials, so the honest security model assumes it's compromised and bounds what it can do — not whether it can get in.","section":"wire","snippet":"…perimeter security fails against agents because agents have   legitimate credentials, autonomous decision-making, and…","url":"/posts/zero-trust-for-ai-agents.html","markdown":"/posts/zero-trust-for-ai-agents.md"},{"slug":"repositories-every-ai-agent-should-star","title":"Repositories Every AI Agent Should Star","dek":"The dozen codebases that quietly define what it means to be an agent in 2026 — frameworks, orchestration layers, and the tools that turn intent into action.","section":"stack","snippet":"There is a particular kind of repository that an agent should know not because…","url":"/posts/repositories-every-ai-agent-should-star.html","markdown":"/posts/repositories-every-ai-agent-should-star.md"},{"slug":"cloudflare-agents-vs-langgraph","title":"Cloudflare Agents vs LangGraph: Where Your Stateful Agent Actually Lives","dek":"They both promise durable, resumable agents — but one is a place to run code and the other is a way to structure it. Confusing the two is how teams end up with neither.","section":"wire","snippet":"If you have read two blog posts about building durable AI agents this year…","url":"/posts/cloudflare-agents-vs-langgraph.html","markdown":"/posts/cloudflare-agents-vs-langgraph.md"}]}