Tag: enforcement layer
-
Agentic AI Agent-to-Agent: A2A Settles Handoff, Not Trust
What is agentic AI agent-to-agent trust? Agentic AI agent-to-agent trust is the decision to let one agent act on what another agent says. The A2A protocol settles how two agents find each other and hand a task across. But it does not settle whether I should believe the agent on the other end. So a…
-
Agentic AI MCP Server Governance: Vet the Server, Not the Call
What is agentic AI MCP server governance? Agentic AI MCP server governance is the set of controls that decides which MCP servers an agent may connect to, who decides that, and what a user can change. It works at the server level, not the tool-call level. So the question moves from “was this call safe?”…
-
Agentic AI Egress Allowlist: Stop It Calling Out
What is an agentic AI egress allowlist? An agentic AI egress allowlist is a short list of outside hosts an agent may call. The network blocks every other host by default. So the list sits outside the agent, and no prompt can talk its way past it. You cannot stop an agent thinking. You can…
-
Agentic AI Governance Controls: 10 Questions, 10 Answers
What are agentic AI governance controls? Agentic AI governance controls are the checks built around an AI agent that decide what it may do. Some only guide the agent. Others can stop it. You cannot govern an agent with a policy document. You can govern it with controls around it. New here? I publish one…
-
Agentic AI Human-in-the-Loop Gate: Gate What Matters
What is an agentic AI human-in-the-loop gate? An agentic AI human-in-the-loop gate is a checkpoint in the harness. It pauses one class of agent action until a named person approves it. The gate sits on the action, not on the prompt. So it fires only when the agent tries to do something that matters. New…
-
Agentic AI Branch Protection: The Agent That Wrote It Cannot Approve It
What is agentic AI branch protection? Agentic AI branch protection is a rule on the repository that stops any pull request from merging until someone other than its author approves it. The agent that wrote the change cannot approve it. That rule lives in GitHub, not in the agent, so the agent cannot talk its…
-
Agentic AI Credential Scoping: One Key, Not Yours
What is Agentic AI credential scoping? Agentic AI credential scoping is the practice of giving an agent its own short-lived, narrow credential instead of the developer’s. The agent gets one key, cut to one job, that expires. It never gets yours. Yesterday’s post was about the rule the developer cannot edit. This one is about…
-
What Is an Agentic AI Managed Setting? A Rule the Developer Cannot Edit
Agentic AI managed settings are the permission rules an administrator sets above the developer. No project file, local file, or command-line flag can loosen them. That is the whole idea. The rest of this post is the how. Last week I wrote about the circuit breaker and prompt injection. Both of those assume the rules…
-
Keeping Agentic AI Systems Safe From Prompt Injection
Agentic AI prompt injection is what happens when an agent reads content that contains instructions and then follows them as if you had given them. The content can be a web page, an email, a PDF, a support ticket, or the result of a tool call. You asked the agent to do one job. Then…