Answers you can question: Building a verifiable AI analytics agent

​How to build an analytics agent whose answers you can actually verify (Manychat journey) - Alex Litvinov

​We will talk about:

• ​Why pointing an agent straight at your warehouse fails

• ​Context layers: what sits between the agent and the data

• ​Keeping that context fresh as the business evolves

• ​Making answers verifiable, and why a human stays in the loop

• ​Results, limitations, and how you can build your own

​About the speaker:

​Alex Litvinov picked up a Master's in Bioengineering and Bioinformatics, followed by 15+ years as a backend/database engineer in Healthcare and Science domain. Currently a Data Engineer at Manychat, bridging platform data engineering with ML/AI.

​DataTalks.Club is the place to talk about data. Join our Slack community!