The agent that checks your agents' data pipelines.

Know your data is right before anyone sees it.

AtEvals checks every change: at ingestion, after each transformation, and on your dashboard KPIs. Then it decides: publish, warn, or hold.

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.

WHY ATEVALS

Your tests passed. The dashboard is still wrong.

Your tests

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

AtEvals

  • Checks the data your pipeline actually produced
  • Catches issues nobody wrote a test for
  • Flags wrong KPIs, even when the source system is at fault
  • Traces the cause and says what to do next

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

UNDER THE HOOD

Your agent calls AtEvals. AtEvals checks the data.

MCP client

Your coding agent

Any MCP-compatible agent

MCP server

AtEvals

  • check_model
  • check_kpis
  • explain

①Warehouse

sources & tables

②dbt project

the PR diff & models

③BI tool

KPI definitions

agent → atevals.check_model("orders_enriched")← HOLD  customer_id renamed · 2 joins affectedagent → fixes join in revenue_by_customeragent → atevals.check_model("orders_enriched")← PASS  14 checks passed · ready for review

AtEvals ships as an MCP server, so your agent checks its own work before handing off, or as a step in your CI.

How it works

Three checkpoints, raw data to dashboard

01 · INGESTION

When new data lands

Schema changes and stale sources

  • Columns added, dropped or retyped
  • Late or missing loads
  • Unusual row counts
  • Null spikes on key columns

02 · TRANSFORMATION

On every PR, after your tests

Broken logic your tests missed

  • Diff against production
  • Joins that drop or duplicate rows
  • New duplicates or nulls
  • Totals that don't match upstream

03 · KPIs

Before dashboards refresh

Wrong numbers, healthy pipeline

  • KPIs read from your BI tool
  • Out-of-range values and spikes
  • Root cause: pipeline or source (ERP)

When it runs

Two moments. Same checks.

On a PR

Before the merge

Catch it while it's still a diff.

Runs on the pull request. Shows which models the change touches and what would break downstream.

Verdict
A comment on the pull request: pass, warn, or block the merge.

In prod

Every pipeline run

Catch it when the data changes underneath you.

Runs on every scheduled pipeline run. The only place a source-system problem shows up, like an ERP that exported the same orders twice.

Verdict
Hold publication and name the cause.

The merge catches what your change broke. The pipeline run catches what the world changed.

Example finding

Not just a report. A verdict.

BLOCK MERGEatevals · PR #212
Caught
In CI, before the merge. Verdict posted as a PR comment.
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

Get early access.

What AtEvals can see

  • Read-only access to the schemas and models you choose
  • Your raw data never reaches the AI model: only metadata and check statistics do
  • AI models and processing hosted in Canada
  • Stores check results and aggregate metrics, not your raw rows
AI agents you use

0/500

FAQ

No. AtEvals reviews every change, whoever made it. It's built for the pace and volume of agent-written code, but human changes go through the same checks.

No. Keep them. AtEvals catches what they don't cover.

AtEvals works without them. It compares each run against your data's normal baseline (schemas, row counts, freshness and KPI ranges) and flags what changed. If you add tests later, it runs after them.

On every pull request, and on every scheduled pipeline run in production. It checks at ingestion, after each transformation, and on your dashboard KPIs before anything is published.

Early access starts with dbt projects on ClickHouse, Snowflake, BigQuery or Postgres. The AtEvals MCP server is public, so any coding agent that supports MCP can use it, like Claude Code or Cursor. The CI integration for GitHub rolls out with early-access users. Tell us your stack in the waitlist form.

Free during early access. Pricing will be usage-based, not per seat, and announced before launch.

Early access opens in early December 2026. Join the waitlist to get in first.