Agentic Analytics & Data Platform Buildout

Want to chat with your data with an AI data analyst? We'll help your AI agent understand the data in your warehouse and how to respond to your business users' plain English questions. Don't have a data warehouse? We can set that up, too.

Your engagement gets

  1. Architecture

    We'll set up your AI-powered BI tool and data warehouse if you don't already have one.

  2. Context Layer

    Semantic layer + skills for optimal speed and accuracy on analytical questions.

  3. Evals

    Run your custom testing suite to confirm your agent answers questions correctly.

Who is agentic analytics for?

Situations where we can help you with agentic analytics.

  • You're running Claude directly on top of your data

    You have context layer and accuracy problems. We can fix that.

  • You have an existing warehouse but no AI

    Your stakeholders want to query via MCP without the data team. Give it to them.

  • You're just starting out

    It's faster than ever to get off the ground, especially when you're designing with AI agents in mind.

How does an agentic analytics engagement work?

Length of each step will depend on size and scope of engagement.

  1. Discovery

    We meet with your team and fully understand the problem.

  2. Set the strategy

    We propose the strategy and get sign off before building.

  3. Implementation

    We build your AI data analyst and quickly get it in front of your team to refine.

  4. Training and handoff

    We train your team on how to maintain the AI data analyst so your internal champions can keep the momentum.

Is agentic analytics right for you?

Cases where we think you should hold off for now.

  • You don't have and don't want a data warehouse.
  • Your data questions are all neatly answered by your current set of dashboards.
  • Your data inaccuracies stem from bad data in business systems and you need to clean that up first.

Case Studies

See how we've delivered results for our clients.

Case study Disco · AdTech

Implementing agentic analytics at Disco

AI agents need context. We provided Disco's Hex AI agents with the right context to power self-service analytics.

AI ImplementationAnalytics Engineering

71 → 158 chats per week, within 6 weeks

"Jacob made key contributions to our dbt project and Hex agentic analytics instance early and often in our engagement. He was agile and unafraid to tackle unfamiliar problems."
Peter Li Peter Li Head of Data & ML at Disco
View all case studies

Your project leader

Jacob Adler

Jacob Adler

Founder and Principal, Riverboat Consulting

Before starting Riverboat, Jacob was the first data hire at Dutchie and later held senior- and staff-level roles at brightwheel and Future. He's presented at the dbt Coalesce conference and written for the Locally Optimistic data blog. He lives in Santa Monica, CA.

LinkedIn

Questions about agentic analytics

What is agentic analytics?

Agentic analytics is the use of AI agents to answer data questions asked in plain English.

Why can't I just give Claude access to my data warehouse?

This is great for a demo but without the right context layer and harness, your agent will confidently spit out the wrong answers.

Why can't I have Claude pull data from each of my business systems when I have a question?

You'll burn more tokens doing this with repetitive calls and get worse accuracy without the right SOP in place.

How will I know if my agent is actually giving correct answers?

We'll build out a suite of "evals" that test how the agent responds to frequently asked or trick questions.

Do we need a data warehouse first?

No. We can help you set up your data warehouse and work with all major options including Snowflake, Databricks, Google BigQuery, and Amazon Redshift.

Do we need a semantic layer?

Yes, the semantic layer is one of the most important parts of a successful AI data analyst. We can help you set it up if you don't have one, and work with all the big players including dbt, Cube, Snowflake, Databricks, and Hex.

Will this replace our data analysts?

No, this frees up your analysts from ad hoc questions so they can work on high-leverage projects for your business.

Related services

Want to learn more? Let's chat.

Or reach out directly at [email protected]

Book a discovery call