Plain-English questions, answered with real SQL
Agentic analytics bot
Built an agentic analytics bot: 14 typed DuckDB-backed tools querying 2,400+ outlets via AWS Bedrock, helping drive personalised outlet improvements.
(Python · AWS Bedrock · Claude · DuckDB · SQL)
# Problem
Operators needed answers from outlet-level data without writing SQL. A free-form LLM over the warehouse would make up filters, tables, and numbers.
# Approach
Shipped an agent on AWS Bedrock (Claude) with 14 typed tools, each backed by a parameterised DuckDB query. A tool-use loop of up to 5 rounds lets the model gather what it needs, and routing guards keep questions on supported paths, so every answer comes from a real query rather than model memory.
# Result
Plain-English analytics across 2,400+ outlets, used to steer outlet-specific improvements, with every number traceable to a query.