Blog
Articles on agentic control planes, AI governance, and building trust infrastructure for AI systems.
Seven agent frameworks, one backend, governance diverges on 9 of 48 tests
architecture
governance
benchmark
agentgovbench
sequence-diagrams
Seven frameworks, one backend, 48 governance scenarios. Scores ranged 37-46. Variance is architectural: where a framework lets you observe tool calls.
April 21, 2026
What our benchmark told us about our own product — six fixes we're shipping
roadmap
governance
agentgovbench
accountability
Benchmarking seven frameworks against ACP broke three things. Two get SDK fixes in two weeks; the third is a structural MCP limit no SDK fix can close.
April 20, 2026
Reproduce AgentGovBench on your stack — full setup guide
tutorial
benchmark
reproducibility
agentgovbench
Step-by-step guide to running the AgentGovBench scorecard against your own ACP deployment: required env, Firebase setup, common issues, reading results.
April 20, 2026
Recommended governance deployment patterns — pick the one that scores highest for your stack
governance
deployment
recommendation
agentgovbench
architecture
AgentGovBench scores across seven frameworks, translated into a customer-facing recommendation for deploying governed AI agents by stack, score, and reach.
April 20, 2026
OpenAI Agents SDK scores 13/48 on AgentGovBench. With ACP, 45/48.
openai
openai-agents-sdk
benchmark
governance
proxy
agentgovbench
Fourth framework, first proxy-pattern integration. OpenAI Agents SDK scores 45/48 with ACP — closest to pure ACP because the proxy sees the full payload.
April 20, 2026
LangGraph's StateGraph checkpoints don't replay through governance
langgraph
governance
stategraph
checkpoint
agentgovbench
LangGraph checkpoint replays skip the governance pipeline — policy changes between original run and replay are silently ignored. The failure mode and fix.
April 20, 2026
LangGraph scores 13/48 on AgentGovBench. With ACP, 40/48.
langchain
langgraph
benchmark
governance
agentgovbench
LangChain/LangGraph run through 48 governance scenarios, twice. Same as CrewAI: vanilla floor, jumps once wrapped in @governed. Per-category breakdown.
April 20, 2026
How we think about testing AI agent governance
testing
benchmark
governance
AgentGovBench is an open, NIST-mapped benchmark for AI agent governance. We ran it against ACP. What broke, what shipped, how to run it on your deployment.
April 20, 2026
Governed OpenAI Agents SDK in 3 Minutes
openai
openai-agents-sdk
proxy
OpenAI Agents SDK is built for multi-agent systems. Point the client at ACP's proxy — every LLM and tool call is audited and policy-checked in four lines.
April 20, 2026
Governed Cursor in 3 Minutes
cursor
mcp
ide
Cursor writes a lot of AI-assisted code, with zero visibility into what its agents did. Route Cursor through ACP so every MCP tool call is audited.
April 20, 2026
Governed Codex CLI in 3 Minutes
codex
openai
cli
OpenAI Codex CLI's auto-approve mode keeps ACP's governance hook firing in unattended runs. 60-second install, what it buys you that Claude Code doesn't.
April 20, 2026
Full scorecard: seven frameworks, 48 scenarios, one open benchmark
benchmark
governance
scorecard
agentgovbench
comparison
Seven frameworks benchmarked: CrewAI, LangGraph, Claude Code, OpenAI Agents SDK, Anthropic Agent SDK, Cursor, Codex CLI. Native vs ACP. Three score tiers.
April 20, 2026
Decorator, proxy, hook — three patterns for agent governance, three different scorecards
governance
architecture
decorator
proxy
hook
agentgovbench
Why CrewAI + ACP scores 40/48 but Claude Code + ACP scores 43/48 on the same backend. Three integration patterns, three scorecards — where each wins.
April 20, 2026
Cursor scores 13/48 on AgentGovBench. With ACP MCP server, 37/48 — and that gap is structural.
cursor
mcp
benchmark
governance
ide
agentgovbench
Seventh framework. Cursor's MCP integration only governs MCP-exposed tools — internal Edit/Read/Bash bypass entirely. A structural 37/48 ceiling.
April 20, 2026
CrewAI's task handoffs lose the audit trail — here's the gap and the fix
crewai
governance
audit
agent-delegation
agentgovbench
CrewAI's Hierarchical Process delegates manager-to-worker without carrying the chain. Even with @governed, audit logs show worker as top-level. The fix.
April 20, 2026
CrewAI scores 13/48 on AgentGovBench. With ACP, 40/48.
crewai
benchmark
governance
agentgovbench
CrewAI run through 48 governance scenarios, twice. Vanilla: floor. Wrapped in @governed: 40/48. Where the gap sits and what it means in production.
April 20, 2026
Codex CLI scores 13/48 on AgentGovBench. With ACP, 43/48 — same as Claude Code.
openai
codex
codex-cli
benchmark
governance
hook
agentgovbench
Sixth framework. OpenAI's Codex CLI shares Claude Code's hook protocol, scores 43/48 with ACP. Differentiator: auto mode keeps hooks firing.
April 20, 2026
Claude Code scores 13/48 on AgentGovBench. With ACP, 43/48.
claude-code
anthropic
benchmark
governance
agentgovbench
Third framework. Claude Code sits at the vanilla floor with no PreToolUse hook; with ACP installed, every Bash, Edit, and MCP call is governed.
April 20, 2026
Claude Code's --dangerously-skip-permissions disables every governance hook
claude-code
anthropic
governance
security
agentgovbench
Claude Code's --dangerously-skip-permissions silently disables every PreToolUse and PostToolUse hook, including ACP's. How to detect it server-side.
April 20, 2026
Anthropic Agent SDK scores 13/48 on AgentGovBench. With ACP, 46/48 — best of any framework.
anthropic
anthropic-agent-sdk
benchmark
governance
agentgovbench
Fifth framework, highest ACP-paired score yet. Anthropic Agent SDK's TypeScript governHandlers wrapper hits 46/48 — above proxy and decorator patterns.
April 20, 2026
How AgentGovBench's 48 scenarios map to NIST AI RMF 1.0
nist
ai-rmf
governance
compliance
agentgovbench
methodology
AgentGovBench scenarios cite specific NIST AI RMF 1.0 controls — MAP, MEASURE, MANAGE, GOVERN. The full mapping for procurement teams citing controls.
April 20, 2026
What 28,000 agent tool calls look like
observability
replay
governance
agents
28,256 agent tool calls across ChatGPT, Claude Code, Claude Desktop, Codex, Cursor, Lovable — 70 days of data. What we found, why Session Replay shipped.
April 17, 2026
How to Rate-Limit an MCP Server (Per-User, Per-Tool, Per-Agent)
mcp
rate-limiting
runaway-agents
per-user
governance
MCP servers are rate-limit-blind — they see the LLM runtime's service account, not the user. How to add per-user, per-tool, per-agent limits in MCP.
April 16, 2026
Introducing ADCS — an open spec for agent-to-agent delegation chains
spec
delegation-chain
a2a
governance
standards
ADCS v0.1: an open JSON spec for agent delegation chains — scope intersection, budget propagation, cycle prevention, identity, audit. Ref impl shipping.
April 16, 2026
EU AI Act Article 14 and AI Agents: Mapping Human Oversight to Delegation Chains
eu-ai-act
article-14
compliance
delegation-chain
adcs
human-oversight
governance
EU AI Act Article 14 requires demonstrable human oversight from Aug 2, 2026. How ADCS delegation chains map to 14(4)(a)-(e) with auditor-ready artifacts.
April 16, 2026
Governing CrewAI A2A Delegation: a production setup guide
crewai
a2a
delegation
governance
tutorial
CrewAI shipped a first-class A2A delegation primitive. Full walkthrough: install, configure, govern, audit CrewAI A2A crews with scope and budget caps.
April 16, 2026
How to Add Per-User Authentication to a LangGraph Agent
langgraph
authentication
auth
oauth
per-user
governance
LangGraph agents run on a shared API key by default — every tool call looks the same. Add per-user auth, identity-attributed audit, and rate limits.
April 16, 2026
Governed CrewAI in 3 Minutes
crewai
a2a
delegation
CrewAI is multi-agent by design, where governance gets hard. Route a crew through ACP so every tool call, across every agent, is scoped and budget-capped.
April 15, 2026
Governed LangGraph in 3 Minutes
langgraph
a2a
delegation
LangGraph's supervisor pattern is a delegation chain waiting for governance. Route a supervisor-and-workers graph through ACP so every hop is auditable.
April 12, 2026
Governing the Anthropic Agent SDK
anthropic
agent-sdk
a2a
delegation
Anthropic's Agent SDK makes multi-skill agents easy to ship. Route them through ACP so every skill, tool call, and sub-agent hop is scoped and auditable.
April 10, 2026
Governance for Claude Code in 60 seconds
claude-code
governance
tutorial
hooks
One command installs a governance hook on every Claude Code tool call. Bash, Read, Write, Edit, WebFetch — logged, policy-enforced, dashboard-visible.
April 6, 2026
Your AI agents need a control plane, not another gateway
architecture
governance
control-plane
mcp
API gateways proxy traffic. LLM gateways proxy prompts. Neither governs what an autonomous agent does with your tools. Why the control plane is different.
April 6, 2026
4 Security Vulnerabilities Hiding in Your MCP Server's Tool Schema
security-research
mcp
schemas
cve
Real CVEs trace back to unconstrained tool schemas. From 8,216 MCP servers: the JSON patterns behind path traversal, SSRF, injection, and how to fix each.
April 2, 2026
MCP Gateway Comparison: ACP vs Composio vs Self-Hosted
architecture
mcp
An honest comparison of MCP gateway options. When to use ACP Cloud, Composio, or build your own with open-source tools.
April 1, 2026
MCP Servers Proxy Paid APIs With No Rate Limits. I Calculated the Blast Radius.
security-research
mcp
180 MCP servers proxy calls to paid APIs like OpenAI and Stripe. 85% document no rate limits. An agent retry loop can cost $1,080/hour.
March 31, 2026
Can You Prove What Your AI Agent Did? I Checked 8,216 MCP Servers.
security-research
compliance
mcp
74.9% of MCP servers have no mention of audit logging. The MCP spec defines zero audit primitives. Here's why that's a compliance problem.
March 30, 2026
4,500 MCP Servers, 7,840 Tools, Zero Input Validation. Here's the Attack Surface.
security-research
mcp
supply-chain
Analysis of 8,216 MCP servers: 2,432 expose high-risk inputs — SQL, file paths, shell commands — with zero validation constraints in the tool schema.
March 29, 2026
I Classified 8,000+ MCP Servers by Auth Appropriateness. Most Get It Wrong.
security-research
identity
mcp
A static analysis of 8,216 MCP servers across 4 registries. 50.6% have no auth. But the real question is: do they have the right auth for what they do?
March 28, 2026
Why Not Just Use OPA and a Service Mesh?
architecture
identity
Do OPA, Istio, API gateways, and IAM already solve AI agent governance? Where existing infrastructure fits, where it breaks, and what's still missing.
March 25, 2026
I Audited 7,522 AI Agent Skills. Here's What I Found.
supply-chain
mcp
A first-hand static analysis of every skill on ClawHub — the real numbers on credential leaks, prompt injection, and what registry moderation actually catches.
March 25, 2026
How an Agentic Control Plane Addresses Every OWASP Agentic Top 10 Risk
standards
compliance
A risk-by-risk mapping of OWASP's Agentic Top 10 to specific control plane capabilities — from the governance layer, not the model or app layer.
March 25, 2026
How to Trigger a Governed AI Agent from n8n, Zapier, or Any Webhook
agent-triggers
Step-by-step guide to invoking AI agents via HTTP from workflow automation tools. Every tool call is identity-verified, rate-limited, and audit-logged.
March 24, 2026
CSA Defines the Agentic Control Plane. Here's What We Built.
standards
architecture
Cloud Security Alliance just published the Agentic Control Plane framework. We've been building the infrastructure. What's real vs. still theoretical.
March 23, 2026
The MCP Security Checklist for Enterprise Teams
security-research
mcp
compliance
A 10-point security checklist for teams deploying MCP servers in production. Covers identity, auth, PII, rate limits, audit trails, and more.
March 22, 2026
How to Connect Salesforce to Claude Desktop in 5 Minutes
mcp
architecture
Step-by-step guide to connecting Salesforce CRM data to Claude Desktop using ACP's MCP gateway. Query contacts, deals, and reports from your AI assistant.
March 21, 2026
Runtime Authorization for AI Agents: Why Static Policies Break
authorization
Traditional authorization was built for humans clicking buttons. AI agents make thousands of decisions a minute. Runtime authz for autonomous callers.
March 20, 2026
WebMCP Ships Without Agent Identity. Here's Why That Matters.
standards
mcp
identity
W3C WebMCP gives browsers a native API for AI agents to call site tools — but ships with no agent identity, scoped permissions, or delegation context.
March 19, 2026
Continuous Trust Validation for AI Agents
compliance
authorization
Point-in-time audits break when agents make 10,000 decisions an hour. Continuous trust means verifying identity, policy, and behavior on every action.
March 18, 2026
MCP Is the Data Plane. You Still Need a Control Plane.
architecture
mcp
MCP defines how agents call tools — the data plane. It doesn't define who can call what, when, or with what audit trail. That's the control plane.
March 17, 2026
MCP Re-Auth: What ChatGPT Actually Needs When Tokens Expire
architecture
mcp
oauth
ChatGPT won't re-trigger OAuth on HTTP 401 or JSON-RPC errors — it needs a JSON-RPC success envelope with _meta. The signal, and how a gateway emits it.
March 16, 2026
NIST Just Defined Identity for AI Agents. Here's What Changes.
standards
identity
NIST's AI Agent Standards Initiative is the first federal move on identity and authorization for autonomous agents. The architectural asks are clear.
March 15, 2026
Your API Keys Already Give Agents Production Access
identity
supply-chain
Every API key in your env vars lets an agent act with full access and no user identity. Most teams don't notice until something breaks in production.
March 14, 2026
Authentication Is Broken in AI Systems
identity
mcp
AI agents call your backend APIs on behalf of users. Your backend has no idea who's asking. This isn't a bug — it's how every major agent framework works today.
March 10, 2026
AI Agent Identity: The Problem No One Has Solved Yet
identity
Your IAM stack handles human identity. AI agent identity — proving who an agent acts for across every tool call — requires a fundamentally different layer.
March 4, 2026
AI Agent Audit Trails: What CISOs Actually Need to Know
compliance
AI agent audit trails need identity-attributed logging — not generic API logs. Here's what CISOs actually need to know for compliance-ready governance.
March 1, 2026
What Is an MCP Control Plane?
architecture
mcp
An MCP control plane adds identity verification, policy enforcement, and audit logging to Model Context Protocol servers — the missing governance layer.
February 26, 2026
Agentic Data Plane vs Agentic Control Plane
architecture
mcp
Agentic data plane vs agentic control plane — what each layer does, why you need both, and how they work together to govern AI agents in production.
February 23, 2026
The Governance Controls Existed
authorization
Microsoft 365 Copilot bypassed its own DLP policies because every governance control lived inside the same vendor pipeline that failed.
February 20, 2026
Your AI Agents Are Acting on Behalf of Your Users
identity
AI agent identity is broken: agents call your backend on behalf of users, but your systems can't verify who initiated the request. Here's the real risk.
February 18, 2026
What Tools Is Your OpenClaw Agent Using?
supply-chain
mcp
Your OpenClaw agent can read .env files and bypass permission skills. Here's what an MCP server security audit revealed — and how to lock it down.
February 15, 2026
OpenAI Frontier Proves AI Governance Can't Live Inside the Model Provider
architecture
Frontier names the real bottleneck: agent identity, permissions, audit. But baking governance into the model provider creates a problem it can't solve.
February 12, 2026
Compliance-Ready AI Governance
compliance
AI agents are accessing protected data on behalf of users — but HIPAA, SOC 2, and GDPR weren't built for this. Compliance-ready AI governance starts here.
January 22, 2026
The Cost of Running Agents Without Budget Controls
authorization
One runaway agent loop can burn through your entire monthly LLM budget in minutes. Here's how to prevent it.
January 2, 2026
Why API Gateways Don't Solve AI Governance
architecture
Traditional gateways handle routing and rate limits. But AI needs identity binding, PII detection, and policy enforcement they were never built for.
December 10, 2025
PII in Prompts: What You're Probably Leaking
compliance
Users paste PII into your AI app. It goes straight to the LLM. That's a compliance problem.
November 19, 2025
Identity in the Three-Party Trust Model
identity
The core problem in AI governance isn't authorization or audit — it's identity. If you can't identify who a request is for, nothing else works.
November 5, 2025
Why Agentic Control Planes Will Matter
architecture
AI is moving from chatbots to agents that take real actions. Without a governance layer, every tool call is a liability.
October 15, 2025