Skip to content

Claude, Copilot or ChatGPT is your most used BI tool. Cassis keeps it reliable at scale.

Cassis builds, maintains and enriches the definitions, rules and business knowledge your agents need to answer data questions. One context MCP, every agent.

Agents call Cassis using current business context. Operations: the orders table is replaced by orders_v2. In Claude, How many orders did we ship this week? 1,284 orders shipped this week, using orders_v2. Finance: a rule is added, net revenue deducts refunds and discounts. In Copilot, Chart our net revenue by month since July. A bar chart of net revenue for July to October, after refunds and discounts. Customers: no rule says whether trial accounts count as active. In ChatGPT, How many active customers do we have? Cassis asks: Do trial accounts count as active? The user picks Exclude. 11,260 active customers, trial accounts excluded. The missing rule is added to your data team’s review.

Trusted in production

Keeping answers reliable for 1,000+ employees

Works with your stack

Snowflake Databricks BigQuery PostgreSQL dbt
GitHub GitLab
Claude OpenAI Copilot Cursor Dust Slack
The problem

“Our accuracy drifted from 95% at launch to 65% over a month.”

Anthropic, on its Claude analytics agent. Read the post

Keeping your data agents accurate is a never-ending job.

  1. You can’t anticipate every question.

    “Do trial accounts count as active?”

  2. A change can break a good answer.

    “Are we using the new refunds table?”

  3. The next team brings more context to maintain.

    “What’s our customer retention rate?”

Product

Cassis is the context engine behind your data agents.

Keep context current at scale.

Questions and data changes keep coming. Cassis groups recurring gaps and prepares fixes. Your team reviews one change for all the questions behind it.

Example: questions from Sales, Finance, Growth and Exec about active customers become one fix, "Active customers exclude trial accounts", assigned to Léa M. A dbt table dropped and a new one created become "refunds renamed to refunds_v2", assigned to Tom R. Two churn questions become "Churn counts accounts, not seats", assigned to Inès K. Each fix passes tests and evals and is ready to publish.

2,418 questions and 37 data changes this week

Reliable answers everywhere.

CassisPublished

Customers

Active customer

Excludes trial accounts.

Tables
customers orders
Metrics
Active customer count
Active customer growth
Claude
Chart active customers, Q2 vs Q3.
Asked Cassis
Copilot
Is our active customer base growing?
Asked Cassis

+8.4% this quarter.

Build from what you already have.

  • SnowflakeSchemas
  • dbt models
  • Dashboards
  • Docs
  • Semantic layer
  • Catalog
CassisContext

Context review

87% auto-documented

  • 10 business domains
  • 155 metrics
  • 532 tables

13% pending review

10,000+

data questions a month

Reliable data answers for Alan’s 1,000+ employees.

Alan expanded self-service without turning its data team into a full-time troubleshooting desk. Cassis investigates errors and gaps, tests fixes and publishes approved context updates.

Why Cassis

Built for scale.
Improves with use.

Capture knowledge when people have a reason to share it.

Cassis proactively asks users for missing context, feeding their answers into the feedback loop.

Keep large context usable.

Cassis gives your agent only the domains and definitions a question needs, so answers stay sharp as context grows.

Focus on decisions.

Cassis manages evals, CI, reviewed publication, permissions, and everything that breaks as you scale.

Where it fits

Augment your data stack.

Keep your agents and warehouse. Put your existing definitions to work.

Your agents send questions to Cassis and receive answers over MCP. Cassis reads existing definitions from your semantic layer. Cassis exchanges queries and results with your warehouse in a separate connection. Cassis opens pull requests on your Git repository, which publishes context back to Cassis.

Your agents

  • Claude
  • ChatGPT
  • Copilot
  • Custom agent
Questions / answers MCP

Cassis

Maintained context
+ answering

Your data stack

Your semantic layer

Your warehouse

  • Snowflake
  • Databricks
  • BigQuery
  • PostgreSQL
Pull requests / published context

Your Git repository

  • GitHub
  • GitLab
Explore the reference stack

Manage your context as code.

  1. Edit your repo

    › Apply Cassis's fix
     active_customers.yml

    Claude Code, Cursor or Codex writes the file.

  2. Test the fix

    $ cassis context test
     11,260, trials excluded

    Check it answers the questions that raised the issue.

  3. Open a pull request

     context check
     eval suite 12/12

    CI runs the evals so nothing else regresses. Your team reviews.

  4. Merge to publish

    #23 merged
    v42 published

    The next answer uses it.

Frequently asked questions

What data does Cassis access?

You choose between two modes.

  • Metadata only, no warehouse connection: Cassis uses your schema, dbt project, documentation and questions to generate SQL. Your existing tools run it in your warehouse. Row data stays in your environment.
  • Read-only warehouse connection: Cassis executes the SQL through a dedicated read-only role, limited to the datasets you authorize. No warehouse writes.

In both modes, Cassis sees the questions your assistant sends it, not the rest of the conversation.

What if we already have a semantic layer?

Keep it. Cassis reads its definitions, Snowflake semantic views included, and runs queries through it when connected to your warehouse. Cassis adds two things:

  • More context: business concepts, rules and exceptions by domain, which table answers which question, and known data limitations.
  • The engine around it: one MCP server for all your agents, and maintenance. Questions surface what’s missing, Cassis proposes the fix, evals test it, and your team reviews it as a pull request in your own Git repository.
Can you build our first context for us?

Yes. We build the context for one business domain from what you already have: schema, dbt models, dashboards and docs.

Your team settles the definitions we can’t infer, and we test the context against real questions from that domain. Then your team maintains it with Cassis, reviewing each fix before it’s published.

What does our team need to review?

The fixes Cassis proposes and the business rules it can’t settle alone. Your team can edit or decline any fix. Cassis groups the questions behind each gap, so one review covers all of them.

Nothing is published without your data team’s approval. Each change is versioned, tested with evals and reviewed in Cassis or as a Git pull request. Edit rights can be scoped per domain.

Our BI tool already connects to agents. Why Cassis?

Your BI tool’s agent only knows your BI tool’s model, and your people already ask Claude, ChatGPT or Copilot too. Cassis gives every agent the same approved context, including the rules your BI model doesn’t hold.

Your BI tool stays. An agent can still build the chart or dashboard there, with Cassis supplying the definitions behind it.

Do we still need Cassis if we have a data catalog?

A catalog records what exists, and it ages fast. Cassis learns from your people’s questions what’s missing and keeps the context current.

It starts from your catalog: Cassis imports its descriptions and glossary, and can stay in sync if you need it. Questions and corrections then reveal gaps and conflicts, and Cassis prepares updates for your team to review.

Why not build this ourselves?

It’s the best way to start, and you can go all the way if you have the resources. What we see is that it gets hard at scale:

  • Analysis: reading thousands of questions consistently to see what fails, then grouping failures by cause and ranking them so your data team isn’t buried in tickets.
  • Learning curve: we see more context gaps, and more ways to fix them, across deployments. Every customer benefits.
  • Plumbing: evals, CI, permissions and governance, all maintained as you grow.

Get your data ready for analytics agents, and keep it that way.

Bring one domain and we'll go through it with you: what your agent would get wrong today, which definitions your team has never settled, and what keeping them current takes.