Compare the new release against the pattern
You deployed and now the log changed. What's new? The radar weighs the release's pattern and separates what appears for the first time.
No configuration: paste the new deploy's log and see which lines drift from the pattern. Those are the new warnings and the release's errors.
Ideal for reviewing a deploy output before calling it good.
Frequently asked questions
Does it compare two versions against each other?+
It doesn't diff files. It weighs the internal pattern of the log you paste and highlights what doesn't fit.
Does it work with CI output?+
Yes. Any plain-text build or pipeline output can be analyzed the same way.
How do I know what's new?+
New lines tend to be infrequent and different from the dominant pattern: they rise to the top of the ranking.
Related
Features
- Unsupervised
- No labels, no training. The normal pattern emerges from frequency alone.
- 100% local
- The model runs in your browser. Zero data transfer, zero servers.
- Fast
- 22M quantized parameters. Hundreds of lines in milliseconds after the initial load.
- Free and unlimited
- No accounts, no quotas, no usage limits.
- Stack-agnostic
- Works on any text: logs, build output, CSV, whatever you paste.