Skip to content
Merged
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
21 changes: 10 additions & 11 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,16 @@ IBM VIBE is a conversation-centric testing suite for evaluating AI agents throug

Use it to script realistic agent conversations, run them against agent configurations, and inspect the resulting sessions, jobs, token usage, similarity scores, and failures.

## Screenshots

| Dashboard | Conversation detail |
| ----------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------- |
| ![Dashboard showing first-run checklist, summary metrics, job status, and agent performance table](docs/assets/dashboard.png) | ![Conversation detail page showing the script alongside the latest session transcript](docs/assets/conversation.png) |

| Quick execute | Session |
| --------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------- |
| ![Quick execute page with agent and conversation selectors and a conversation preview panel](docs/assets/quick-execute.png) | ![Session page showing turn-by-turn messages with similarity scores and token metadata](docs/assets/session.png) |

## Why VIBE?

- **Test conversations, not just prompts**: model the multi-turn exchanges your users actually have.
Expand Down Expand Up @@ -111,17 +121,6 @@ For multi-instance local setups, use `env.instance1.example` as a template and c
- [`CONTRIBUTING.md`](CONTRIBUTING.md) - contributor workflow
- [`SECURITY.md`](SECURITY.md) - private vulnerability reporting

## Visuals to add before a public push

The repo will read much better on GitHub with a small visual set under `docs/assets/`:

- Dashboard screenshot with first-run guidance visible
- Conversation editor screenshot
- Quick execute screenshot
- Session transcript screenshot

Add those images to this README once captured from a representative local instance.

## License

Apache-2.0. See [`LICENSE`](LICENSE).
Binary file added docs/assets/conversation.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/assets/dashboard.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/assets/quick-execute.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/assets/session.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading