— Published work
All our writing, in one place.
24 posts from the AGF open work supported by INTREXA — engineering guides, executive briefings, and ideas on agent authorization.
agf-sdk 0.7.0: LangGraph, OpenAI Agents SDK, and a Warm-Container Fix
Two new framework adapters, plus a real correctness fix for a broken sync/async bridge that crashed anything reusing an AGF client across repeated calls.
Read article ↗ENGINEERING · AUG 27, 2026How to Add Authorization Gates to AWS Lambda Agent Functions
A Lambda handler running an AI agent is just a function — but it's a function reused across warm invocations, and that changes what 'safe to guard' requires.
Read article ↗ENGINEERING · AUG 27, 2026How to Add Authorization Gates to LangGraph Agents
LangGraph gives you two different places to put an agent's logic, and they need two different authorization patterns. Here's both, plus the one shape that needs a third.
Read article ↗ENGINEERING · AUG 27, 2026How to Add Authorization Gates to OpenAI Agents SDK Tools
OpenAI's Agents SDK ships its own tool guardrail hook. Here's why we didn't build on top of it, and what we built instead.
Read article ↗IDEAS · JUL 29, 2026Explainability Tells You Why. Authority Tells You Whether.
As AI agents move from answering questions to taking actions, explainability stops being enough. Did the agent actually have the authority to act?
Read article ↗ENGINEERING · JUL 12, 2026A2A Needs an Authorization Layer, Too
The Agent2Agent protocol standardizes how one agent delegates work to another. It doesn't standardize whether that delegation should be allowed.
Read article ↗ENGINEERING · JUL 12, 2026Governing Agents That Drive a Browser, Not Just Ones That Call APIs
A browser-automation agent has no downstream server to front as a gateway. Here's how AGF governs that case instead.
Read article ↗ENGINEERING · JUL 12, 2026Not Every Agent Speaks MCP or A2A — the HTTP Gateway Covers the Rest
Plenty of agents still just call a plain REST API. The AGF HTTP Gateway fronts those too, without requiring the downstream API to change.
Read article ↗STANDARDS · JUL 12, 2026The AGF Specifications Are Now Public: 27 Open Standards for Agent Governance
Every AGF specification is now published under Apache 2.0, with an open RFC process and a conformance path for independent implementations.
Read article ↗ENGINEERING · JUL 11, 2026MCP Needs an Authorization Layer, Too
The Model Context Protocol standardizes how agents discover and call tools. It doesn't standardize whether they should be allowed to.
Read article ↗IDEAS · JUL 5, 2026Identity Gets Agents in the Door. Authorization Decides What Happens Next.
On Okta's Oktane 2026 positioning, and why the industry conversation is splitting into two layers: who an agent is, and what it's allowed to do.
Read article ↗EXECUTIVE · JUL 8, 2026CISO Brief: The Actual Attack Surface of Deployed Agents
Four attack patterns that actually show up in agent deployments, and the controls that address each one.
Read article ↗EXECUTIVE · JUL 7, 2026CISO Brief: Mapping Agent Governance to NIST, ISO 42001, and the EU AI Act
How AGF's audit artifacts map to the three compliance frameworks security teams are actually being asked about.
Read article ↗EXECUTIVE · JUL 6, 2026CISO Brief: What 'Securing AI Agents' Actually Means
Most 'AI security' conversations are about model safety. That's not the same problem as securing what an agent is authorized to do once deployed.
Read article ↗ENGINEERING · JUL 2, 2026Introducing agf-sdk: the AGF Python SDK Is on PyPI
One package, three ways to call it: a synchronous facade, an async client, and framework adapters for LangChain and CrewAI.
Read article ↗ENGINEERING · JUL 4, 2026Authorizing Tool Calls in AutoGen Multi-Agent Systems
AutoGen's function_map has no authorization concept. Here's how to gate it with the AGF Python SDK.
Read article ↗ENGINEERING · JUL 3, 2026Adding Authorization Gates to CrewAI Crews
CrewAI's Agent/Task/Crew model has no built-in concept of policy enforcement. Here's how to gate CrewAI tool calls with AGF.
Read article ↗IDEAS · JUN 18, 2026The Delegation Problem: When Agents Spawn Other Agents
Multi-agent systems inherit a centuries-old problem: how do you ensure the subordinate does what the principal actually authorized?
Read article ↗IDEAS · JUN 16, 2026Three Trust Zones: A Practical Model for Agent Authorization
Why there's no single revocation state, and why that's okay.
Read article ↗ENGINEERING · JUN 17, 2026How to Add Authorization Gates to LangChain Agents
LangChain makes it easy to build capable agents. Here's how to add policy enforcement in under 10 minutes.
Read article ↗IDEAS · JUN 10, 2026What Is AI Agent Governance? A Practical Introduction
Agent governance is a specific discipline most organizations aren't ready for yet. Here's what it actually means.
Read article ↗IDEAS · JUN 9, 2026Authentication Scales. Revocation Doesn't.
Why agent governance needs a new model for revocation.
Read article ↗IDEAS · OCT 28, 2025The Audit Problem: Why Agent Actions Are Hard to Trace
Most organizations deploying AI agents cannot answer a simple question: what did the agent do, and why?
Read article ↗IDEAS · SEP 12, 2025Why Autonomous Agents Need Their Own Identity Infrastructure
The API keys and service accounts we use for human-facing systems don't translate cleanly to agent systems.
Read article ↗