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.
More from coding & agent
- An MCP server signs every AI agent tool call into a verifiable Merkle chain — Funky_Chicken_22 · 2026-07-22
- Claude Code skill uses 10 Markdown rules to make outputs ADHD-friendly — alex_verem · 2026-07-22
- A Firecracker-based platform says it can host 6,000 AI agents on one 256 GB server — maritime_sh · 2026-07-22
- A better path to agent autonomy is running waves, finding friction, and iterating — JnBrymn · 2026-07-22
- AI agent designers map the visual and tonal cues behind companionship products — Unlikely-Platform-47 · 2026-07-22
- Coding agents are heading toward an AI-writes, AI-reviews, human-approves workflow — aftahi_ai · 2026-07-22