← Back
Databricks Blog

From Data to Dialogue: How S&P Global Energy Made Its Structured Data Estate Conversational with Databricks Genie Agents and MCP

•6 min read•
#agents#mcp#llm
Level:Advanced
For:AI Engineers
✦TL;DR

S&P Global Energy transformed its structured data estate into a conversational interface by deploying Databricks Genie Agents integrated with the Model Context Protocol (MCP). The solution enables customers to discover and consume data through natural language dialogues, leveraging Databricks’ unified analytics platform. Engineers can adopt the same agent architecture to expose proprietary data assets as chat‑driven services, reducing the need for custom query layers.

⚡ Key Takeaways

  • Databricks Genie Agents were used to power conversational access to structured data.
  • Integration with the Model Context Protocol (MCP) allows the agents to share context and metadata across calls.
  • The approach shifts data consumption from static dashboards to interactive dialogue, improving user experience.
  • Agents are built on Databricks’ platform, so they can be invoked via the platform’s existing APIs and notebooks.
  • Prerequisite: Access to a Databricks workspace with Genie and MCP enabled; without it the agent stack cannot be instantiated.

🔧 Tools & Libraries

Databricks Genie AgentsModel Context Protocol (MCP)
💡 Why It Matters

By converting static data pipelines into chat‑driven interfaces, engineers can deliver faster, more intuitive data access without building bespoke front‑ends, accelerating product rollout and user adoption.

✅ Practical Steps

  1. Enable Genie Agents in your Databricks workspace and configure them to reference your structured data sources.
  2. Activate the Model Context Protocol (MCP) for your agents to allow context sharing across conversational turns.
  3. Deploy the agents via Databricks notebooks or the REST API to expose a chat endpoint for end‑users.

Want the full story? Read the original article.

Read on Databricks Blog ↗

More like this

Censored vs. Truncated Regression in Python, Explained

Towards Data Science•#llm

New in AWS Quick: More capable flows, an updated web experience, and agents that work together

AWS ML Blog•#agents

How Google Duplex evolved to also call businesses for you in Gemini

Google Research•#agents

Q&A: Enabling more human-like interactions and understanding in multimodal foundation models

MIT News AI•#llm

EXPLORE AI NEWS

Daily hand-picked stories on LLMs, RAG, agents and production AI — curated for engineers who ship.

BROWSE NEWS

GET THE WEEKLY DIGEST

Join engineers getting the Monday signal-over-noise AI breakdown. No spam, unsubscribe anytime.

LEARN AI ENGINEERING

Curated courses, research papers, repos and tutorials built for engineers leveling up in AI.

START LEARNING