Privacy user testing at scale using LLMs and browser agents
active 2024-09-07 → 2024-09-26 (UTC)
Complete coverage26,690 / 26,690 hourly files (100%) · 2 absent upstream2023-08-15 → 2026-08-31 (UTC)
Events
32
Pushes
10
Pull requests
2
Issues
13
Stars
0
Forks
0
Activity over time
Daily event counts in the loaded window
Line chart, 20 days from 2024-09-07 to 2024-09-26. Pushes: 10 total, peak 5 in a day. Pull requests: 2 total, peak 2 in a day. Issues: 13 total, peak 5 in a day. Comments: 3 total, peak 2 in a day. Stars: 0 total, peak 0 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| yashmaurya01 | 28 | 10 | 2 | 3 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#4yashmaurya012024-09-26 17:00Create personas for simulating a user study of different age participants
- Issue#4yashmaurya012024-09-26 16:52Create personas for simulating a user study of different age participants
- Issue#3yashmaurya012024-09-26 04:44Detailed explanation for output explanation - more metrics and reasoning
- Issue#2yashmaurya012024-09-26 04:44Agentic feedback on action output
- Issue#1yashmaurya012024-09-26 04:43Break down the benchmark questions to tool calls
- Issue#10yashmaurya012024-09-08 05:19Test tagged screenshot performance compared to the text ocr for agent chain
- Pull request#9yashmaurya012024-09-08 02:55
- Pull request#9yashmaurya012024-09-08 02:54
- Issue#8yashmaurya012024-09-08 02:45Unable to use search bar in google
- Issue comment#7yashmaurya012024-09-08 01:23Feedback after creating the benchmark to improve the ui
- Issue#7yashmaurya012024-09-08 01:22Feedback after creating the benchmark to improve the ui
- Issue#6yashmaurya012024-09-08 01:17Take into account the ui(like font size, color, timing etc)
- Issue comment#1yashmaurya012024-09-08 00:34Add agentic feedback to enable exploratory tasks and avoid getting stuck in loops
- Issue#5yashmaurya012024-09-08 00:29Privacy policies are way too long and cause the agent to timeout - think something to fix this
- Issue#4yashmaurya012024-09-07 23:15Decompose UsersFirst framework to set of tasks(benchmark creation)
- Issue#3yashmaurya012024-09-07 23:14Add test examples to the readme(3 websites)
- Issue#2yashmaurya012024-09-07 23:13Create user personas for a variety of participant pools
- Issue#1yashmaurya012024-09-07 23:12Add agentic feedback to enable exploratory tasks and avoid getting stuck in loops
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.