Skip to content
This repository was archived by the owner on Mar 7, 2026. It is now read-only.

Commit 4ed08ff

Browse files
mosiddiCopilot
andcommitted
feat: add trust scoring exploration notebook
Interactive Jupyter notebook demonstrating trust scoring, decay, violations, and threshold gates with visualizations. Closes #168 Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
1 parent ab2a0c3 commit 4ed08ff

2 files changed

Lines changed: 421 additions & 0 deletions

File tree

notebooks/README.md

Lines changed: 34 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,34 @@
1+
# Agent Mesh Notebooks
2+
3+
Interactive Jupyter notebooks for exploring agent-mesh concepts.
4+
5+
## Available Notebooks
6+
7+
| Notebook | Description |
8+
|----------|-------------|
9+
| [trust-scoring-exploration.ipynb](trust-scoring-exploration.ipynb) | Explore the 5-dimension trust scoring system, decay, violations, and threshold gates |
10+
11+
## Getting Started
12+
13+
1. Install dependencies:
14+
15+
```bash
16+
pip install -e ".[dev]"
17+
pip install jupyter matplotlib
18+
```
19+
20+
2. Launch Jupyter:
21+
22+
```bash
23+
jupyter notebook notebooks/
24+
```
25+
26+
3. Open `trust-scoring-exploration.ipynb` and run cells sequentially.
27+
28+
## What You'll Learn
29+
30+
- How the **RewardEngine** scores agents across 5 dimensions
31+
- How **trust decay** reduces scores without positive activity
32+
- How **policy violations** and security events impact trust
33+
- How **trust threshold gates** allow or deny actions
34+
- How to **visualize** trust score trends over time

0 commit comments

Comments
 (0)