MongoDB CTO on Database Architecture Evolution and the Unsolved Problem of Agent Memory
The Cognitive Revolution · rss · 2026-09-01
This episode features Pete Johnson, Field CTO of AI at MongoDB, discussing the history of database architecture and the current state of agent memory systems. Pete contrasts SQL and NoSQL for enterprise use, explaining the shift from storage-scarce to compute-centric paradigms. The conversation dives deep into agent memory challenges, including contextualized chunking tradeoffs, retrieval quality thresholds, and designing memory systems. It also covers enterprise AI deployment, Voyage's acquisition strategy, and global AI adoption trends.
More from coding & agent
- Learn multi-hop Cypher with 2026 World Cup data: group tables to Golden Boot in one graph — JeremyCMorgan · 2026-09-01
- Why Document AI Integration Needs 6 SDKs: IDPForge Unifies the Pipeline — infrrd-ai · 2026-09-01
- Dev ships MCP server for sanctions screening and CVE lookups, pay-per-query via x402 — Glittering-Buyer1830 · 2026-09-01
- Agent-Driven Reverse Engineering of Peripherals Using Claude Opus 5 — bibryam · 2026-09-01
- New tool md² handles agent switching when usage limits are reached — JBO_76 · 2026-09-01
- TouchBar Revived by AI Agents: Real-Time Coding Status on Old Hardware — APPSO · 2026-09-01