Personalizing AI Agents with Snowplow

Al_Grigor · x · 2026-07-14

This is a workshop on tracking and personalizing AI agents using Snowplow + Vercel AI SDK, aiming to enable agents to perceive real-time user behavior within a product, rather than just seeing chat history.

Using a Next.js travel chatbot as an example, the workshop covers the entire pipeline: collecting client-side behaviors (page views, clicks, filters), capturing server-side events (purchases, bookings), logging agent decisions (tool calls and results), and using Snowplow Signals to calculate session attributes in real-time. These attributes are then injected into the system prompt to influence the agent's replies.

It will also demonstrate how to validate event schemas in real-time and set up a tracking pipeline, with a live stream scheduled for July 21 on YouTube.

Original post →

More from coding & agent

coding & agent channel →