Hamed Taheri
Co-founder & Product Lead, Personize.ai. Building governed memory infrastructure for enterprise AI agents. Vancouver.
Featured
The Multi-Entity Memory Pattern
Most AI systems memorize contacts. The ones that work memorize contacts, their companies, their deals, and the relationships between all of them — then recall across entity boundaries at inference time.
Featured
Encoding Solution Architecture Into an AI Skill
The early stages of AI implementation are mostly discovery — assembling scattered context into a coherent system design. We spent two years encoding that process. Here's what we found.
Recent WritingAll articles →
2026
- Your Agents Know Things. They Just Don't Tell Each Other.
- Dogfooding governed memory: building smart notifications for our own product
- What's Relevant? What Do We Know? What Are the Rules?
- 7 Patterns for Building Governed AI Knowledge Bases
- Amazon, LinkedIn, and the Race to Build Agentic Knowledge Bases (Part 2)
- Amazon, LinkedIn, and the Race to Build Agentic Knowledge Bases (Part 1)
- Who's Actually in Charge of Your AI Agents?
- 3 Shortcomings of RAG as a Memory