Dex | Let Your Agent Build Your Analytics
Let your agent build your analytics.
Explore, Transform, Maintain. The agent-native analytics engine.
Point it at your data. Dex learns the landscape, builds your models and metrics, and tells you exactly what to fix when anything drifts.
Any agent Claude Code
npx skills add exmergo/dex
1 /plugin marketplace add exmergo/exmergo-agent-plugins 2 /plugin install dex@exmergo
Run each command in Claude Code, one at a time.
Dex Semantics
Let your agent build analytics with 25% fewer errors.
Dex Semantics · 60 s
The Emperor wants his spice report.
Let your agent build your analytics.
You → your coding agent
“Build analytics for spice production and revenue on Arrakis.”
Build the models & record the meaning
- Production Spice extracted
- Spice sold
- Spice shipped
- Revenue Sold × agreed price
The report says spice production doubled overnight.
The report changed overnight (but the desert didn’t)
- Report: 200 t
- Reality: still 100 t
- Yesterday This morning
The join broke silently!
Same shipment, but the new API sends two rows instead of one.
- S01+S01
- Revenue: 140k → 280k credits.
Dex embeds semantic meaning explicitly.
Declare the rules → Check the results → Keep the context
- The declaration lives with your models
- One row per shipment.
- Production counts harvests.
- Revenue uses the agreed price.
Dex checks the built data
- S01 and S02: expected 1 row, found 2.
- Duplicate shipments flagged.
Without Dex: 200 t
With Dex: 100 t
Proposed fix: tally the lines first, then count harvests separately.
Analytics Engineering is ETM
ETL ends at Load. Dex is built for what comes after.
Explore Make sense of your data.
- Dex intelligently profiles columns, infers relationships, and builds a comprehensive draft map of your tables, cached locally. PII is automatically flagged, never surfaced.
Transform Build models and semantic layers.
- Ask for a metric, and Dex writes the reviewable diffs.
- It authors dependency-aware dbt SQL models, schema tests, and the semantic layer on top, in MetricFlow, Apache Ossie, SLayer, Cube, Snowflake Semantic Views, or Databricks Metric Views.
Maintain Detect drift before it breaks.
- Run /dex:maintain against your .dex/ snapshot to instantly detect schema, grain, and semantic drift. Dex proposes the exact edits needed to keep your project correct.
Your raw data stays where it lives.
Dex is read-only against your data and never routes it through Exmergo.
- Aggregates leave, rows do not.
- Your agent, your keys.
- Credentials never reach the LLM.
Frequently asked questions
Q01. What is Dex?
Dex is an open-source, agent-native analytics engine that lets Claude Code and other coding agents build your analytics. It explores your data, whether it lives in a data warehouse, a lakehouse, or a database; authors dbt models and semantic layers; and detects schema, volume, grain, and semantic drift.
Q04. Does Dex support Apache Ossie?
Yes, natively. Dex reads it as a first-class semantic layer.
Q05. Does Dex support SLayer?
Yes, natively. SLayer by Motley keeps a semantic layer as YAML model files, and Dex reads it as a first-class semantic layer.
Q06. Does Dex support Cube, Snowflake Semantic Views, and Databricks Metric Views?
Yes, natively, each in its own format with no conversion.
Q10. What is free and what is Enterprise?
Dex is free and open source under Apache 2.0, including the full Explore, Transform, Maintain loop with manual drift detection.
Dex Enterprise is the harness that runs that loop for a whole team, deployed on your infrastructure: it scopes analytics goals, builds dbt changes from tickets, and fixes drift on a schedule, in your own CI, with every change opened as a draft pull request.
Ready to turn maintenance into an automated habit?
Install the open-source engine today.