Subvolts take Agent memory hinges on database evolution; learn how retrieval drives AI performance. Sep 1, 2026 - Developers
- Understand how database architecture and retrieval strategies directly impact AI agent performance and memory.
- Business
- Learn about the foundational data challenges that influence the development and reliability of AI agents.
This is a solid interview with a key figure from a major database company discussing critical AI agent infrastructure.
Write, Change, Recall, Forget: MongoDB's Pete Johnson on How Retrieval Drives Agent Performance
Audio streams from Erik Torenberg, Nathan Labenz. Your place is remembered on this device.
From Subvolts
Summary and analysis by Subvolts editorial, AI-assisted.
Pete Johnson, MongoDB's Field CTO of AI, joins The Cognitive Revolution to discuss agent memory and database architecture. He traces database evolution from E.F. Codd's relational model, designed for scarce storage, to modern needs. The conversation explores how retrieval systems impact AI agent performance, a key challenge in the field.
This episode explains how storing and finding information, like in computer databases, is crucial for AI agents to remember and act. It connects old database ideas to new AI challenges, showing why efficient data retrieval is key for smarter AI.
This episode offers a deep dive into the technical underpinnings of AI agents, connecting historical database design to current challenges in memory and retrieval. It is for developers and technical leaders building AI systems who need to understand data management's role in agent performance. The discussion on agent memory is directly relevant to frontier labs like OpenAI, Google Gemini, and Anthropic as they strive to create more capable and persistent AI assistants.
- HostNathan Labenz
- GuestPete JohnsonField CTO of AI, MongoDB
- Guest: Pete Johnson, Field CTO of AI at MongoDB
- Show: The Cognitive Revolution
- Length: 97 minutes
- Guest's Birth Year: 1970
- Relational Model Paper: E.F. Codd's original paper published February 1970
Nathan's guest this episode is Pete Johnson, Field CTO of AI at MongoDB, and the conversation is really two conversations woven together: a history of database architecture, and a status report on the still-unsolved problem of agent memory. Pete opens with a framing device that recurs throughout — he was born in February 1970, four months before E.F. Codd's original relational-model paper that gave rise to SQL. The relational model, he explains, was built for a world where storage was the scarce resource, so normalization — splitting data across linked tables to avoid duplication — was the rational design choice.
For full show notes, links, and references, read the episode page:
https://www.cognitiverevolution.ai/write-change-recall-forget-mongodb-s-pete-johnson-on-how-retrieval-drives-agent-performance/
Sponsors:
Mercury: Mercury is the banking platform loved by 300,000+ entrepreneurs, with virtual cards and Spend controls for granular budgets, receipts, and low-risk AI agent purchases. Learn more and apply in minutes at https://mercury.com
Granola: Granola is an AI-powered notepad that securely transcribes meetings and turns rough notes into clean, structured action items. Try it free at https://granola.ai/tcr
Diffusion: Diffusion helps organizations build custom AI software factories that scale business outcomes, not just outputs. Cognitive Revolution listeners get a 25% service credit on their first engagement at https://diffusion.io/tcr
Deepgram Flux TTS: Deepgram Flux TTS brings lifelike AI voices with real personalities that handle interruptions, pauses, and natural conversation. Try all the voices free through September 12 at https://deepgram.com/keep-talking
Claude: Claude is the AI collaborator for problem solvers, helping with writing, coding, financial models, strategy, and more. Get started with Claude and explore Claude Pro at https://claude.ai/tcr
CHAPTERS:
(00:00) About the Episode
(03:15) Sponsor: Mercury
(04:56) SQL versus NoSQL
(11:24) Enterprise database choices (Part 1)
(18:30) Sponsors: Granola | Diffusion
(21:27) Enterprise database choices (Part 2)
(21:27) Schema flexible search
(33:50) Contextualized chunking tradeoffs (Part 1)
(35:12) Sponsors: Deepgram Flux TTS | Claude
(37:17) Contextualized chunking tradeoffs (Part 2)
(46:22) Retrieval quality thresholds
(53:17) Agent memory systems
(01:05:51) Enterprise AI deployment
(01:16:32) Voyage acquisition strategy
(01:23:38) Global AI adoption
(01:30:56) Episode Outro
(01:34:41) Outro
PRODUCED BY:
- relational model
- Pete Johnson
- A way to organize data in databases using tables with rows and columns, linked together.
- normalization
- Pete Johnson
- A database design technique to reduce data duplication by splitting it into separate, linked tables.
- retrieval
- Pete Johnson
- The process of finding and accessing specific information from a larger dataset.
1 h 27AI:AM: Where's the Steering Wheel? My Agent Set the Password, Hidden Valence, Proofs Find Linux Bugs
WithCameron Berg, Everett Hildenbrandt, Grigore Rosu, Phil Maher
2 h 192 h 021 h 28AI:AM: A Level We Shouldn't Pass? Notes from The Curve + Tokens vs. Salaries & Is SaaS Cooked?
WithThomas Sohmers, swyx, Evan Miyazono, Edward Hu
Questions people ask
- What is the core problem discussed regarding AI agents?
- The episode focuses on the still-unsolved problem of agent memory and how retrieval systems drive agent performance.
- How does database history relate to AI agents?
- Pete Johnson explains database architecture evolution, starting from E.F. Codd's relational model, to frame the challenges in building effective AI agent memory.
Page generated Oct 19, 2026. Summaries are Subvolts' own; the audio, artwork and notes belong to Erik Torenberg, Nathan Labenz.