How The AA answered routine trading questions in Teams with Databricks Genie
UK roadside assistance provider The AA used the Genie Conversation API to answer trading teams' routine data questions inside Microsoft Teams. Databricks reports faster answers to routine queries.
The problem
Reporting was spread across several tools, with weak accuracy, timeliness and governance. Data specialists were overloaded with routine ad hoc questions, and users had to navigate complex dashboards and ticket queues.
How they did it
- Integrated the Genie Conversation API into Microsoft Teams.
- Trained Genie on 'golden questions' trading teams ask often, such as weekly sales summaries and promotion conversion impact.
- Checked Genie's answers against existing Power BI dashboards before going live.
Results
- Databricks reports a 70% efficiency gain in answering routine queries.
- Routine query resolution times dropped by up to 70%, with 24/7 availability.
As reported by the source (Databricks customer story); AgentGid did not measure these figures.
This suits teams already on Databricks with governed data, a Teams rollout, and someone who can curate the common questions and check answers against existing dashboards. Watch the cost: Genie is billed at standard Databricks usage rates, and the 70% gain is Databricks-reported. For a cheaper way to try natural-language analysis without Databricks, PandasAI is open source (Free).
The agent used here
Similar use cases
Automate a web task in natural language with Stagehand
Stagehand's starter project scripts a browser with plain-English instructions. act, extract and observe handle single steps, and agent runs a multi-step task on its own.
A TypeScript script that clicks, extracts and inspects pages from short instructions.
Run LangChain's Open Deep Research multi-agent pipeline locally
LangChain's open-source deep research agent, built on LangGraph, runs research sub-agents in parallel, compresses what they find and writes a final report. It works with many mode…
On Deep Research Bench, the default GPT-4.1 configuration scored 0.4309 and the GPT-5 configuration 0.4943.
How Spotify migrated about 1,800 data pipelines with its Honk background coding agent
Spotify used Honk, its internal background coding agent built on Claude Code capabilities, to move downstream consumers off two deprecated datasets. The agent opened 240 migration…
As reported by Spotify, the team 'successfully rolled out 240 automated migration PRs using Fleetshift'.
