Cached at:
10/01/26, 05:07 AM
# One-shot anomaly detection on the command line¶
Source: [https://cmungall.github.io/jevotron/](https://cmungall.github.io/jevotron/)
jevotron / airports\.csv
```
$ jevotron scan airports.csv --guidance "Check airport locations."
```
01 / PREVIEW
### See what goes in[¶](https://cmungall.github.io/jevotron/#see-what-goes-in)
Inspect chunks, field paths, and exact model requests before making an API call\.
[Preview a file →](https://cmungall.github.io/jevotron/quickstart/#preview-the-input)
02 / SCAN
### Assess every entry[¶](https://cmungall.github.io/jevotron/#assess-every-entry)
Jev scores selected fields together\. Each entry gets the same guidance and optional examples\.
[Choose your fields →](https://cmungall.github.io/jevotron/guides/files/)
03 / REVIEW
### Start with the warnings[¶](https://cmungall.github.io/jevotron/#start-with-the-warnings)
Sort suspicious entries, export CSV, or pipe JSONL into your existing shell workflow\.
[Build a review queue →](https://cmungall.github.io/jevotron/guides/reports/)
## Small setup\. Useful defaults\.[¶](https://cmungall.github.io/jevotron/#small-setup-useful-defaults)
**CSV, YAML, JSON, TOML, text, OBO, and more**work out of the box, including gzip files\. The[format reference](https://cmungall.github.io/jevotron/reference/formats/)covers defaults and format\-specific options\. Select fields with`\-\-field`, add a sentence with`\-\-guidance`, and run\. Longer instructions can come from`\-\-guidance\-file`\. A local Python config is available when a project needs custom parsing or reusable settings\.
**Unchanged input reuses its assessment\.**SQLite saves each successful result as it arrives\. Reorder a file, change a reporting threshold, or resume a failed run without reassessing unchanged entries\.
**A review aid with visible evidence\.**Reports retain each field's probabilities, the entry score, source location, and assessment date\. The warning score is the highest field anomaly probability; you choose the threshold\.
## Try a complete example[¶](https://cmungall.github.io/jevotron/#try-a-complete-example)
ExampleWhat you'll do[Airports / CSV](https://cmungall.github.io/jevotron/examples/airports/)Find two injected country errors in public data, then compare versions\.[Inventory / YAML](https://cmungall.github.io/jevotron/examples/inventory/)Apply written rules and a chosen exemplar to stock records\.[Measurement units / OBO](https://cmungall.github.io/jevotron/examples/obo/)Score definitions and repeated synonyms within independent stanzas\.[Agent traces / JSONL](https://cmungall.github.io/jevotron/examples/agent-traces/)Classify public agent traces and individual steps, then compare with published labels\.### Agent traces: a measured pilot[¶](https://cmungall.github.io/jevotron/#agent-traces-a-measured-pilot)
On a small, length\-filtered sample of**24 public traces**, jt matched**130 of 163 step\-quality labels \(79\.8%\)**\. Harmful\-step precision was**89\.7%**, with**70\.3% recall**\. The example uses original messages and tool definitions, with human labels withheld from the model\.
[Try the trace example →](https://cmungall.github.io/jevotron/examples/agent-traces/)·[Read the full analysis and limitations →](https://cmungall.github.io/jevotron/analysis/agent-traces/)