All projects

La Caisse (CDPQ) · 2026 · In production

Hybrid conversational agent over a Databricks lakehouse

[One-sentence summary: what it is, who it is for, and the main result.]

Role
[Your role]
Period
[Start and end dates]
Team
[Team size, or solo]
Status
[In production, in progress, finished]
[00][What this figure measures]
[00][What this figure measures]
[00][What this figure measures]
[Main image: screenshot, diagram or photo. 1600 × 900 px]

Context

[Where and why the project started: employer, course or competition, and the people involved.]

[The constraints: deadline, data available, tools imposed, confidentiality.]

Problem

Investment teams relied on manual SQL work to answer recurring questions about financial data.

Approach

A deterministic SQL engine for the known question families, with an automatic Databricks Genie fallback for the rest. Every answer is traceable to its query. Evaluated in MLflow with deterministic scorers and LLM judges.

  • [Design decision 1, and why you chose it over the alternative]
  • [Design decision 2, and why]
  • [Design decision 3, and why]
[Architecture diagram or pipeline schematic]

Results

About 80% of queries answered in about 1 s, against 30 to 45 s before.

[How it was evaluated: data, baseline, protocol, and who validated it.]

[Results table or chart]

Limits and next steps

  • [What does not work yet, or the known limits of the result]
  • [What you would do differently]
  • [The next step, if the project continues]

Stack

  • Databricks
  • LangGraph
  • MLflow
  • SQL
  • Azure DevOps
  • [Add a tool]

Links

Gallery

Next project Systematic equity research pipeline