From your data to watch around the clock.
Connect your data and describe the behaviour. The agent builds and proves the detector, then Lucir watches day and night.
590,540rows read
118,107unseen, scored
0.926ROC-AUC
How it works
Four steps. Two of them are yours.
- 01
Connect
Point Lucir at your database. Detectors run there as queries.
No data migration.
- 02
Describe
Say what matters, in plain language or with a policy.
No rule writing.
- 03
Prove
The agent builds a detector, checks it, and scores it on history it never saw.
Evidence before go-live.
- 04
Watch
You approve it. Lucir runs it around the clock, on the cadence you set.
Alerts with their reasons.
What changes
The rulebook, rebuilt around evidence.
| Today | With Lucir | |
|---|---|---|
| A new rule | Weeks of tickets and vendor time | Minutes to hours, built by the agent |
| Who writes it | An engineer translating a request | The agent, from the request itself |
| What it is tested on | Often the data it was tuned on | A locked holdout, never used to tune |
| What runs in production | Whatever was last edited | Frozen at approval, retrained models versioned |
| When an auditor asks | A document describing the rule | The detector, its scores and its history |
Where it runs
Built on your data. Owned by you.
- Queries run in your database. Snowflake, BigQuery and Databricks support is next.
- Least exposure. The agent works from profiles and small samples of your data, with held-out labels masked.
- Your model provider, your keys.
- Any domain. Nothing is hard-coded to one dataset.