Chroma | Context Engineering
Conversations with practitioners and researchers building with large language models, cutting through the hype to examine what actually works in production.
Context engineering, agent architecture, model selection, and the gap between benchmark scores and real-world performance. Grounded technical perspectives for builders navigating the practical challenges of AI engineering.
Chroma | Context Engineering
Dex Horthy
Chroma CEO Jeff Huber chats with Dex Horthy about agents and context engineering.
Dex on X: https://x.com/dexhorthy
0:00 - Introduction
0:23 - Context Engineering Origins
0:33 - 12 Factor Agents
0:43 - New AI Models
1:43 - Model Switching Strategy
3:07 - Personal Productivity Systems
7:57 - AI UX Patterns
13:07 - Todo List Management
15:01 - Collaborative AI Workspaces
22:09 - In-Person vs Remote
24:05 - Tab Complete Patterns
25:00 - Shared Context Layer
27:00 - Markdown & Airtable
32:35 - Data Storage Systems
34:00 - AI-Native Organizations
36:00 - OAuth & Authentication
38:00 - Desktop App Development
43:42 - Context Engineering Evolution
45:00 - Evals & Observability
46:00 - LM-as-Judge Discussion
48:00 - Snapshot-Based Evals
54:47 - Agent Memory Systems
56:00 - Instruction Following Limits
57:57 - Closing Remarks
--
Chroma is the open-source AI application database. Batteries included.
Embeddings, vector search, document storage, full-text search, metadata filtering, and multi-modal. All in one place. Retrieval that just works. As it should be.
Try it today:
https://trychroma.com/cloud