Skip to content

docs: clarify AgentControl quickstart example #3650

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.

Sign up for GitHub

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
Poshith (Poshith-git) wants to merge 1 commit into
base: main
Choose a base branch
from
Open

docs: clarify AgentControl quickstart example #3650

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
27 changes: 25 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -127,7 +127,7 @@ Or use the full `AgentControl` API for programmatic control:
```python
from agent_control_specification import AgentControl

runtime = AgentControl.from_path(str("manifest.yaml"))
runtime = AgentControl.from_path("manifest.yaml")
result = runtime.evaluate(
"input",
{
Expand All @@ -139,6 +139,30 @@ print(result.verdict)
runtime.close()
```

```yaml
# manifest.yaml (minimal, illustrative shape — matches the schema used in
# examples/acs-email-tool/manifest.yaml). Running this requires a matching
# policy adapter; see the linked example below for the full working version.
agent_control_specification_version: "0.3.0-alpha-agt"
metadata:
name: example-agent
version: "0.1.0"
extends: []
policies:
example_policy:
type: custom
adapter: example_policy
intervention_points:
input:
policy_target: $.input.body
policy_target_kind: input_body
policy:
id: example_policy
tools:
web_search:
clearance: internal
```

[Run the complete ACS email-tool example](examples/acs-email-tool).

</details>
Expand Down Expand Up @@ -226,7 +250,6 @@ Agent ──► Policy Engine ──► Identity ──► Audit Log
▼
Decision Record
```

Every layer is optional. Start with `govern()` and add layers as your risk profile grows. Most teams run policy enforcement + audit logging and never need the full stack.

---
Expand Down
Loading