Skip to content

Fix broken Watchdog docs links #106

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
PerceiveWorld wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix broken Watchdog docs links #106

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
4 changes: 2 additions & 2 deletions docs/docs/index.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@ Cupcake sits in the agent hook path. When an agent proposes an action (e.g., run

**Allow** · **Deny** · **Halt** · **Modify** · etc

A core pillar of Cupcake is **deterministic guarantees**—policies that always behave the same way given the same input. However, the nature of AI and where it's headed requires more dynamic policy gating. Agents can be prompted, confused, or manipulated in ways that static rules can't anticipate. That's why we developed [**Cupcake Watchdog**](/watchdog/getting-started.md), a built-in feature that uses LLM-as-a-judge to evaluate your rules and context and make intelligent determinations on the fly.
A core pillar of Cupcake is **deterministic guarantees**—policies that always behave the same way given the same input. However, the nature of AI and where it's headed requires more dynamic policy gating. Agents can be prompted, confused, or manipulated in ways that static rules can't anticipate. That's why we developed [**Cupcake Watchdog**](/reference/watchdog.md), a built-in feature that uses LLM-as-a-judge to evaluate your rules and context and make intelligent determinations on the fly.

## Getting Started

Expand Down Expand Up @@ -80,7 +80,7 @@ Modern AI agents are powerful but inconsistent at following operational and secu
Cupcake supports two evaluation models:

1. **Deterministic Policies**: Policies are written in **OPA/Rego** and **compiled to WebAssembly (Wasm)** for fast, sandboxed evaluation. [Writing Policies](https://cupcake.eqtylab.io/reference/policies/custom/) guide for implementation details.
2. **LLM‑as‑Judge**: For simpler, yet more advanced, oversight of your rules, Cucpake can interject via a secondary LLM or agent to evaluate how an action should proceed. [Cupcake Watchdog](https://cupcake.eqtylab.io/watchdog/getting-started/) guide for implementation details.
2. **LLM‑as‑Judge**: For simpler, yet more advanced, oversight of your rules, Cucpake can interject via a secondary LLM or agent to evaluate how an action should proceed. See the [Cupcake Watchdog](reference/watchdog.md) guide for implementation details.

### Decisions & Feedback

Expand Down