---
url: https://hanria.ai/blogs/
canonical: https://hanria.ai/blogs/
site: HANRIA
---

# Essays and explainers on accountable agents.

Notes from HANRIA on what it takes for an AI agent to be trusted with real work.

## Essays

### [Agents can act. They cannot yet prove.](https://hanria.ai/blogs/principals/)

Why the missing piece in the AI economy is accountability, and how HANRIA is designed to build it. A response to the essay Principals.

### [Governed Habitats: What the Agent-Habitat Literature Asks of a Harness, and Where HANRIA Stands](https://hanria.ai/blogs/governed-habitats/)

An assessment of the HANRIA harness against the agent-habitat literature: what aligns, what does not yet, and what external validation would take.

## Explainers

One page at a time, in the order they were written. Each page keeps its own URL.

### [A skill can check an agent action. Only a runtime can stop one.](https://hanria.ai/blogs/skill-checks-runtime-enforces/)

A skill can check a proposed agent action against a written mandate and record permit, deny, or escalate. Stopping the action requires exclusive control of its credential or tool.

### [What is an agent mandate, and why a permission system will not catch authority drift?](https://hanria.ai/blogs/what-is-an-agent-mandate/)

An agent mandate is a written grant of which operations, targets, counterparties, and amounts an agent may attempt, when it expires, and which kinds always need a person. A permission system will not catch authority drift.

### [How to write an agent mandate: denials first, expiry, requires_human](https://hanria.ai/blogs/how-to-write-a-mandate/)

How to write an agent mandate: denials first, expiry, requires_human.

### [What is authority drift when every individual agent check still passes?](https://hanria.ai/blogs/authority-drift/)

What is authority drift when every individual agent check still passes?

### [What should an agent do on permit, deny, escalate, or error?](https://hanria.ai/blogs/permit-deny-escalate/)

What should an agent do on permit, deny, escalate, or error?

### [Worked mandate templates: ticket read, file prefix, refund ceiling](https://hanria.ai/blogs/mandate-templates/)

Worked mandate templates: ticket read, file prefix, refund ceiling.

### [What a hash-chained local decision log is, and is not](https://hanria.ai/blogs/decision-log-is-not-evidence/)

What a hash-chained local decision log is, and is not.

### [What is the difference between an agent skill and an enforcement runtime?](https://hanria.ai/blogs/skill-vs-runtime-in-one-page/)

What is the difference between an agent skill and an enforcement runtime?

### [What does fail-closed mean for an agent mandate?](https://hanria.ai/blogs/fail-closed-mandates/)

What does fail-closed mean for an agent mandate?

### [When must an agent escalate instead of acting?](https://hanria.ai/blogs/requires-human/)

When must an agent escalate instead of acting?

## Developer guides

### [Developer guides for pre-action checks and agent mandates](https://hanria.ai/guides/)

LangGraph, OpenAI Agents SDK and Claude Agent SDK pre-action checks, plus writing and validating a mandate.