Track 2: Agentic Analytics
Day 2 breakout track · For analysts and data practitioners
This track is all about using agentic systems to build, verify, and operationalize data products. You'll start by building a data set from live data sources. Then you'll learn to verify and refine what the agent produces, build visualizations, and finish by turning the analysis into a production-ready workflow that delivers fresh recommendations every morning.
Throughout the labs, you'll work to help GreenTech Manufacturing tackle a critical sustainability challenge facing their five UK production facilities. The company consumes over 42 million kWh annually running energy-intensive operations, and with UK carbon offset costs at £50/ton CO2, their environmental impact is becoming a significant financial burden. The key insight: the UK's electricity grid carbon intensity swings dramatically throughout the day. Your mission is to build an intelligent system that learns from 30 days of historical weather and carbon data to predict these low-carbon windows up to 7 days in advance, then identifies which flexible operations can be strategically shifted from high-carbon hours to clean-energy windows.
Prerequisites
- Complete Hands-On Lab: Getting Agentic on Day 1.
Labs
Lab 1: Agentic Analysis
Build a carbon + operations optimization pipeline from scratch — connecting live weather and carbon data with your manufacturing operations to find optimal scheduling windows.
Lab 2: Verifying Agent Output
Explore the optimization results, verify the scheduling logic respects constraints, and build visualizations that quantify savings by facility and machine.
Lab 3: Repeatable Workflows
Make the pipeline production-ready — fix hardcoded dates, schedule daily runs, and set up alerts for carbon intensity spikes during scheduled operations.
Questions?
Reach out to your bootcamp instructors or support@ascend.io.