Linear Agent Interaction Guidelines: Design Principles for Agents

Linear has published the Agent Interaction Guidelines (AIG), a set of foundational design principles for AI agent and human-computer interaction. As agents transform how software is planned, built, reviewed, and deployed, a new interaction contract becomes necessary.

Core Principles

1. An agent should always disclose that it’s an agent

When humans and agents work side by side, humans need instant certainty about who they are interacting with. The agent must signal its identity clearly so that it can never be mistaken for a person.

2. An agent should inhabit the platform natively

By default, agents should be able to work through existing UI patterns and standard actions of the platform they operate in, using the same capabilities as human users.

3. An agent should provide instant feedback

Silence leads to uncertainty. When invoked, an agent should provide immediate, but unobtrusive, feedback to reassure the user it has received a request.

4. An agent should be clear and transparent about its internal state

Agents should clearly indicate whether they’re thinking, waiting for input, executing, or finished. Humans should be able to understand what’s happening at a glance and inspect underlying reasoning, tool calls, and decision logic when needed.

5. An agent should respect requests to disengage

When asked to disengage, an agent should step back immediately – and only re-engage once it’s received a clear signal to do so.

6. An agent cannot be held accountable

There should be a clear delegation model between humans and agents. An agent can carry out tasks, but the final responsibility should always remain with a human.

Read the full guidelines: https://linear.app/developers/aig