Skip to content

Core concepts rephrasing and agent_env diagram updated. Fixes #33 #61

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 4 commits into
base: dev
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions .gitignore
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
.idea/
.git/
book/
**/*.DS_Store
Binary file added docs/.DS_Store
Binary file not shown.
Binary file added docs/assets/.DS_Store
Binary file not shown.
Binary file modified docs/assets/agent_env.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
35 changes: 24 additions & 11 deletions docs/topics/core_concepts.md
Original file line number Diff line number Diff line change
Expand Up @@ -33,20 +33,33 @@ A trustworthy agent is an Observed Agent that transparently exposes its interact

## Agent Instrumentation

### Observed Agent Responsibilities:
An Observed Agent should ensure inspectability, traceability, and observability by:
### Observed Agent Responsibilities

- Emitting Standard Events: Every interaction with the environment must be exposed through standardized event formats.
- Standardized Tracing: Maintain a standardized trace of all interactions to support improved observability, enable a holistic multi-agent view, and facilitate historical interaction analysis.
- Instrumentation: Events should trigger hooks that allow the Guardian Agent to enforce policies. Example policies may include restricting external communication, redacting sensitive data, or enforcing compliance constraints. Based on these policies, the Guardian Agent can permit, deny, or modify the content of the interaction.
- Reactive Capabilities: The agent must be capable of responding to Guardian Agent directives, including action denials or content mutations.
An **Observed Agent** is responsible for ensuring environmental visibility and policy responsiveness through the following capabilities:

### Guardian Agent Responsibilities:
The Guardian Agent enforces policies and enables tracing through the following:
- **Support BOM Requests**
Provide up-to-date information about components and dependencies relevant to the agent’s operational context.
- **Emit Events**
Generate standardized events that reflect all interactions with the environment to ensure traceability and observability.
- **Support Hooks**
Integrate with lifecycle hooks that allow external entities (e.g., Guardian Agent) to inspect or control operations.
- **Comply with Hook Responses**
React appropriately to directives from hooks, such as permitting, denying, or modifying actions based on policy enforcement.

- Event Instrumentation Utilization: Leverage standard event hooks to evaluate and enforce policies, responding with permit, deny, or modify instructions.
- Standardized Tracing: Maintain a consistent trace of all interactions to enhance observability, support a comprehensive view across agents, and enable detailed analysis of interaction history.
- Provide comprehensive and dynamic AgBOM: Maintain and notify an up to date list of components and dependencies for the agent environment changes such as new or updated tools, models and other components
---

### Guardian Agent Responsibilities

The **Guardian Agent** enhances control, compliance, and dynamic environment awareness via the following responsibilities:

- **Observe and Emit Events in Multiple Standards**
Capture and emit observed interactions using various standardized formats to support interoperability and broader system integration.
- **Subscribe to Hooks**
Register for and listen to hooks emitted by Observed Agents to enable active intervention in agent behavior.
- **Apply Policy**
Enforce operational policies by evaluating hook-triggered events and issuing corresponding decisions (permit, deny, modify).
- **Dynamically Maintain AgBOM**
Monitor agent lifecycle events to update and maintain the Agent BOM (Bill of Materials) in real-time, reflecting current tools, models, and components.

## A2A and MCP

Expand Down