Skip to content

Add Interactive Demo Page - Week 1 MVP #124

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

Add Interactive Demo Page - Week 1 MVP #124

Show file tree
Hide file tree
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
10 changes: 8 additions & 2 deletions components/MastHead.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -139,13 +139,19 @@ export default function Home() {
<div id="register">
<div>
<Link
className="btn bg-transparent border-2 border-blue-400 text-blue-400 hover:border-blue-300 hover:text-blue-300 mt-10 mb-6 hover:bg-transparent"
className="btn btn-primary mt-10 mb-6"
href="/demo"
>
Try It Now
</Link>
<Link
className="btn bg-transparent border-2 border-blue-400 text-blue-400 hover:border-blue-300 hover:text-blue-300 mt-10 mb-6 ml-3 hover:bg-transparent"
href="#industries"
>
Learn How
</Link>
<Link
className="btn btn-primary mt-10 mb-6 ml-3"
className="btn btn-outline mt-10 mb-6 ml-3"
href="#start"
>
Get Started
Expand Down
355 changes: 355 additions & 0 deletions pages/demo.js
View file
Open in desktop

Large diffs are not rendered by default.

6 changes: 6 additions & 0 deletions public/benchmark-data/metadata.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,6 @@
{
"benchmark_name": "waa-live",
"run_name": "waa-live_eval_20260116_200004",
"model_id": "unknown",
"created_at": "2026-01-16T20:00:04.964702"
}
20 changes: 20 additions & 0 deletions public/benchmark-data/summary.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,20 @@
{
"benchmark_name": "waa-live",
"run_name": "waa-live_eval_20260116_200004",
"model_id": "unknown",
"num_tasks": 1,
"num_success": 0,
"success_rate": 0.0,
"avg_score": 0.0,
"avg_steps": 5.0,
"avg_time_seconds": 71.88987074999022,
"tasks": [
{
"task_id": "notepad_1",
"success": false,
"score": 0.0,
"num_steps": 5,
"error": null
}
]
}
142 changes: 142 additions & 0 deletions public/benchmark-data/tasks/notepad_1/execution.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,142 @@
{
"task_id": "notepad_1",
"model_id": "unknown",
"success": false,
"score": 0.0,
"num_steps": 5,
"total_time_seconds": 71.88987074999022,
"error": null,
"reason": "Evaluation requires WAA evaluators (not yet implemented)",
"steps": [
{
"step_idx": 0,
"screenshot_path": "screenshots/step_000.png",
"action": {
"type": "click",
"x": 0.6442708333333333,
"y": 0.32666666666666666,
"target_node_id": null,
"target_bbox": null,
"target_role": null,
"target_name": null,
"text": null,
"key": null,
"modifiers": null,
"scroll_direction": null,
"scroll_amount": null,
"end_x": null,
"end_y": null,
"answer": null,
"raw_action": {
"code": "computer.click(1237, 392)"
}
},
"reasoning": null,
"timestamp": 1768611618.802666
},
{
"step_idx": 1,
"screenshot_path": "screenshots/step_001.png",
"action": {
"type": "click",
"x": 0.6072916666666667,
"y": 0.5216666666666666,
"target_node_id": null,
"target_bbox": null,
"target_role": null,
"target_name": null,
"text": null,
"key": null,
"modifiers": null,
"scroll_direction": null,
"scroll_amount": null,
"end_x": null,
"end_y": null,
"answer": null,
"raw_action": {
"code": "computer.click(1166, 626)"
}
},
"reasoning": null,
"timestamp": 1768611631.025159
},
{
"step_idx": 2,
"screenshot_path": "screenshots/step_002.png",
"action": {
"type": "click",
"x": 0.6072916666666667,
"y": 0.5216666666666666,
"target_node_id": null,
"target_bbox": null,
"target_role": null,
"target_name": null,
"text": null,
"key": null,
"modifiers": null,
"scroll_direction": null,
"scroll_amount": null,
"end_x": null,
"end_y": null,
"answer": null,
"raw_action": {
"code": "computer.click(1166, 626)"
}
},
"reasoning": null,
"timestamp": 1768611644.028655
},
{
"step_idx": 3,
"screenshot_path": "screenshots/step_003.png",
"action": {
"type": "click",
"x": 0.6072916666666667,
"y": 0.5216666666666666,
"target_node_id": null,
"target_bbox": null,
"target_role": null,
"target_name": null,
"text": null,
"key": null,
"modifiers": null,
"scroll_direction": null,
"scroll_amount": null,
"end_x": null,
"end_y": null,
"answer": null,
"raw_action": {
"code": "computer.click(1166, 626)"
}
},
"reasoning": null,
"timestamp": 1768611657.31775
},
{
"step_idx": 4,
"screenshot_path": "screenshots/step_004.png",
"action": {
"type": "click",
"x": 0.6442708333333333,
"y": 0.32666666666666666,
"target_node_id": null,
"target_bbox": null,
"target_role": null,
"target_name": null,
"text": null,
"key": null,
"modifiers": null,
"scroll_direction": null,
"scroll_amount": null,
"end_x": null,
"end_y": null,
"answer": null,
"raw_action": {
"code": "computer.click(1237, 392)"
}
},
"reasoning": null,
"timestamp": 1768611670.178712
}
]
}
Binary file added public/benchmark-data/tasks/notepad_1/screenshots/step_000.png
View file
Open in desktop
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 public/benchmark-data/tasks/notepad_1/screenshots/step_001.png
View file
Open in desktop
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 public/benchmark-data/tasks/notepad_1/screenshots/step_002.png
View file
Open in desktop
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 public/benchmark-data/tasks/notepad_1/screenshots/step_003.png
View file
Open in desktop
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 public/benchmark-data/tasks/notepad_1/screenshots/step_004.png
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
9 changes: 9 additions & 0 deletions public/benchmark-data/tasks/notepad_1/task.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,9 @@
{
"task_id": "notepad_1",
"instruction": "Task notepad_1",
"domain": "notepad",
"initial_state_ref": null,
"time_limit_steps": 5,
"raw_config": {},
"evaluation_spec": null
}