AtEvals

The agent that checks your agents' data pipelines.

AI agents build pipelines fast. People miss things too. AtEvals reviews every change at ingestion and after every transformation, and tells you whether the data is safe to publish.

Join the waitlistSee how it works

Scenario 1 of 3: All clear

Sources are checked at ingestion, each transformation's output is re-checked after your own tests, KPIs are checked against their normal range, then a publish gate decides pass, warn or hold before the BI dashboard, whose KPI definitions the KPI check reads.SourcesERP · CRM · IoTPublish gateCHECK: INGESTIONCHECK OUTPUTCHECK: KPIsfrom your BI dashboardPass→ publishWarn→ publish + notifyHold→ block and explain

Hover or tap a check to see what it looks at.

Example finding

Not just a report. A verdict.

HOLD PUBLICATIONatevals · report
Check
After transformation: orders_enriched
Finding
Column customer_id was renamed to client_id. 2 downstream joins now drop 18% of rows.
Why it matters
Revenue by customer on the dashboard will be understated by ~18%.
Suggested fix
Alias client_id AS customer_id in orders_enriched, or update the joins in revenue_by_customer and churn_daily.
Changed by
AI agent (session #4821)
Affected models: 2Rows impacted: 41,290
WARN

Source shopify_orders last updated 26h ago (expected: hourly)

PASS

14 checks passed on stg_customers

How it works

What each check looks at

Check: ingestion

Schema changes and stale sources

  • Schema vs. last run (added, dropped, renamed, retyped columns)
  • Freshness vs. expected schedule
  • Row count vs. baseline
  • Null rate on key columns

Check output (after every transformation)

Broken logic your tests missed

Runs after your own tests pass

  • Join cardinality (rows dropped or duplicated)
  • Duplicate keys
  • Null rates
  • Numbers that should reconcile with upstream

Check: KPIs

Dashboard numbers that look wrong, even when the pipeline is fine

  • Reads the KPI definitions from your BI tool
  • Computes them on the new data before it's published
  • Flags values outside their normal range, sudden spikes or drops
  • Traces the cause: pipeline or source system (e.g. ERP)

Whether an agent wrote the change or a person did, every finding comes with why it matters and what to do next.

VS. YOUR TESTS

Your tests

  • Written ahead of time, for cases you predicted
  • Check your transformation logic, not the source system
  • Pass even when the ERP or CRM sends bad data
  • Pass/fail with no context

AtEvals

  • Checks the data your pipeline actually produced
  • Catches issues nobody wrote a test for
  • Flags KPIs that look wrong, even when the error comes from the source system
  • Traces the cause and says what to do next

Keep your tests. AtEvals checks what they can't see.

Works with your agent

AtEvals ships as an MCP server, so your coding agent can call it to check its own work before handing off.

dbtClickHouseSnowflakeBigQueryPostgresClaude CodeCursor
agent → atevals.check(model="orders_enriched")
← HOLD  column customer_id renamed
        2 downstream joins affected

Get early access.

AI agents you use

0/500

Who's behind it

Built by Fouad A. Djebbar: 10+ years building data platforms end to end, with a software engineering background. Based in Montréal.

LinkedIn

AtEvals is the agent of AtiMati, a hosted data services company based in Québec.

FAQ