SmithDB: The data layer for agent observability
Skills:
Agent Foundations80%
Key Takeaways
Introduces SmithDB, a distributed database for agent observability that backs LangSmith workloads
Original Description
Introducing SmithDB, our purpose-built distributed database for agent observability that now backs core LangSmith workloads.
SmithDB gives LangSmith industry-leading performance across key observability workloads, the portability to run wherever customers need their data to live, and the flexibility to support agent-native query patterns that traditional observability stores were not designed for.
SmithDB: The Data Layer for Agent Observability
00:00 Introducing SmithDB
00:05 What is a Trace?
00:18 The Problem with Traces
00:36 The Solution: SmithDB
00:51 Iterating Faster
Resources:
Blog: https://www.langchain.com/blog/introducing-smithdb
LangSmith: https://www.langchain.com/langsmith-platform
LangChain: https://langchain.com/
Watch on YouTube ↗
(saves to browser)
Sign in to unlock AI tutor explanation · ⚡30
More on: Agent Foundations
View skill →Related Reads
📰
📰
📰
📰
GATS: Graph-Augmented Tree Search with Layered World Models for Efficient Agent Planning
ArXiv cs.AI
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
ArXiv cs.AI
ARCANA: A Reflective Multi-Agent Program Synthesis Framework for ARC-AGI-2 Reasoning
ArXiv cs.AI
L-MAD: A Systematic Evaluation of Multi-Agent Debate Structures in Legal Reasoning
ArXiv cs.AI
Chapters (5)
Introducing SmithDB
0:05
What is a Trace?
0:18
The Problem with Traces
0:36
The Solution: SmithDB
0:51
Iterating Faster
🎓
Tutor Explanation
DeepCamp AI