Blog
Thinking in events
Engineering insights, product thinking, and technical deep-dives from the team building the infrastructure layer for the agentic era.
Event sourcing is the backbone of agentic AI
Why append-only event logs are essential for AI agent reliability. Event sourcing gives agents memory, audit trails, and governance — not just state.
Read articleYour AI agent needs an audit trail, not just guardrails
Guardrails prevent bad actions. Audit trails prove good ones. Why every AI agent needs an immutable record of decisions — and how to build one.
Read articleHow to comply with the EU AI Act using immutable event logs
Practical guide: how immutable event logs satisfy Articles 9, 12, 13, 14, and 15 of the EU AI Act. Compliance checklist and code examples included.
Read article7 layers of AI agent memory: a bio-inspired architecture
Deep-dive into how knowledge graphs, vector search, and confidence decay create persistent memory for AI agents. Interactive layer explorer included.
Read articleVector search + event sourcing: why you need both
Event sourcing gives you complete history. Vector search gives you semantic retrieval. Together they create an AI-native data layer.
Read articleTES Agent Memory vs Mem0: choosing an AI agent memory framework
Fair comparison: 7-layer architecture vs single vector store. Knowledge graphs, HybridRAG, confidence decay, and audit trails.
Read articleEdge-native event processing with Cloudflare Workers
How TES achieves sub-50ms event ingestion globally. Architecture deep-dive: Workers, D1, Queues, R2, and multi-tenant isolation.
Read articleFrom Kafka to event stores: when to make the switch
Kafka is a transport layer. Event stores are systems of record. When you need audit trails, AI enrichment, and entity tracking — it's time to add an event store.
Read articleAI bias detection in production: moving beyond static audits
Static audits are snapshots. Production AI needs continuous, self-evolving detection. How evolutionary algorithms find bias patterns humans wouldn't think to test.
Read articleWe gave AI agents a brain. And a conscience. And a perfect memory.
Three systems. One stack. The first complete cognitive architecture for AI agents — persistent memory, self-evolving bias detection, and an immutable event ledger.
Read articleThe immutable ledger for the agentic age
Why enterprise AI needs an append-only event spine — not another database. TES is the system of record for agents, physical goods, and financial transactions.
Read articleStay in the loop
More thinking in events, coming soon
We write about event-sourced architecture, AI enrichment, and building infrastructure for the agentic era.