Insights & Updates
Stories, guides, and updates on AI agents, customer memory, and personalization at scale.
Retrieval, Memory, and Governance Are Three Different Problems
Three questions reveal whether your AI agents have what they need: What's relevant? What do we know about this entity? What are the rules? Each requires different infrastructure — and mixing them up is the most common way enterprise AI quietly fails.
Amazon, LinkedIn, and the Race to Build Agentic Knowledge Bases (Part 2)
In Part 1, we covered LinkedIn and Amazon. Now: how Google, Microsoft, and Salesforce are approaching the same problem — and the gap that no single platform will solve for you.
Amazon, LinkedIn, and the Race to Build Agentic Knowledge Bases (Part 1)
The biggest companies in tech are converging on the same conclusion: AI agents without organizational knowledge are a liability. Here's what LinkedIn and Amazon are each building, and what the pattern reveals.
Without Governance, Your AI Agents Are Just Guessing With Confidence
Same company, same task, three different AI agents, three completely different answers. Your customers notice. Do you? Here's what the governance gap actually looks like — and how to fix it.
3 Shortcomings of RAG as a Memory
RAG solved an important problem, but when the goal shifts from 'find relevant information' to 'maintain persistent understanding of a customer,' retrieval becomes one piece of a larger architecture.
Why Agents Fail Without Memory
If your AI agents forget everything between conversations, they're not agents — they're expensive autocomplete. Here's where memory matters, and what it costs to ignore it.