From Wrangling to Insight: Human-in-the-Loop AI for Analytics
Webinar Speaker: Deanne Larson, Research Fellow
Date: Wednesday, October 29, 2025
Time: 9:00 a.m. PT / 12:00 p.m. ET
Data wrangling and preparation remain some of the most time-consuming steps in enterprise analytics, often slowing down the path from exploration to insight. Emerging AI agents together with human-in-the loop support are changing this dynamic, accelerating many routine preparation tasks, streamlining exploratory analysis, and freeing up experts to focus on delivering value. These tools promise efficiency while still keeping domain experts in control and ensuring trust and governance.
Join TDWI research fellow Deanne Larson, Ph.D., along with experts from AWS and Posit as they discuss how human-in-the-loop assistants can transform analytics workflows. You’ll see a practical demo of Positron Assistant and Databot powered by Amazon Bedrock, followed by a panel discussion on real-world adoption patterns and pitfalls to avoid.
Objectives include:
- Demonstrate how AI assistants streamline EDA (exploratory data analysis) and data prep in Posit with Amazon Bedrock, using a live workflow.
- Understand which tasks provide the highest value when automated and which should remain human-driven.
- Review a reference integration that connects Positron to Bedrock, runs an assisted EDA session, and captures results in a reproducible manner for governance and transparency.
- List three best adoption practices to scale safely.
- Specific prompts - specific questions often yield better results than generic requests
- Close monitoring - Human-in-the-loop AI isn’t effective if the human isn’t actually in the loop. Monitor output and interrupt as necessary to course correct.
- Reproducibility - relying on generated code instead of direct LLM interpretation of data provides a reproducible and auditable trail.
Guest Speakers
James Blair
Senior Product Manager
Posit, PBC
James Blair is a senior product manager at Posit, where he focuses on helping Posit commercial products seamlessly integrate into cloud platforms and environments. He has a background in statistics and data science and finds any excuse he can to write R code and ride his bike, although usually not at the same time.
Shun Mao
Senior Partner Solutions Architect
AWS
Shun Mao is a senior partner solutions architect in the artificial intelligence and machine learning (AI/ML) independent software vendor (ISV) partner team at Amazon Web Services (AWS). He has years of experience in data science, analytics, AI, and cloud computing across different industries, including oil and gas and pharmaceuticals. At AWS, he is helping strategic AI/ML partners to build novel products and solutions to bring business value to customers.
Deanne Larson, Ph.D., DM, CBIP