Harrison's In the Loop Series

Your harness, your memory

Agent harnesses are becoming the dominant way to build agents, and they are not going anywhere. These harnesses are intimately tied to agent memory. If

Harrison's In the Loop Series 7 min read

Continual learning for AI agents

Most discussions of continual learning in AI focus on one thing: updating model weights. But for AI agents, learning can happen at three distinct layers:

Harrison's In the Loop Series 4 min read

Two different types of agent authorization

LangSmith Fleet introduces two types of agent authorization: Assistants, which use the end user's own credentials, and Claws, which use a fixed set of credentials.

Harrison's In the Loop Series 4 min read

How Coding Agents Are Reshaping Engineering, Product and Design

EPD (Engineering, Product, and Design) at software company is about creating good software. Separate roles exist, but the end goal is functional software that solves

Harrison's In the Loop Series 8 min read

On Agent Frameworks and Agent Observability

Every time LLMs get better, the same question comes back: "Do you still need an agent framework?" It's a fair question.

Harrison's In the Loop Series 4 min read

From Traces to Insights: Understanding Agent Behavior at Scale

Visibility is the easiest piece. The hard part is analyzing and understanding what you’re observing. I’ve spoken to teams recording 100k+ traces every

Harrison's In the Loop Series 5 min read

In software, the code documents the app. In AI, the traces do.

TL;DR * In traditional software, you read the code to understand what the app does - the decision logic lives in your codebase * In AI

Harrison's In the Loop Series 5 min read

Agent Frameworks, Runtimes, and Harnesses- oh my!

There are few different open source packages we maintain: LangChain and LangGraph being the biggest ones, but DeepAgents being an increasingly popular one. I’ve

Harrison's In the Loop Series 3 min read

Reflections on Three Years of Building LangChain

by Harrison Chase Almost exactly 3 years ago, I pushed the first lines of code to langchain as an open source package. There was no

Harrison's In the Loop Series 6 min read

Not Another Workflow Builder

By Harrison Chase One of the most common requests we’ve gotten from day zero of LangChain has been a visual workflow builder. We never

Harrison's In the Loop Series 4 min read

Deep Agents

Using an LLM to call tools in a loop is the simplest form of an agent. This architecture, however, can yield agents that are “shallow”

Harrison's In the Loop Series 3 min read

The rise of "context engineering"

Header image from Dex Horthy on Twitter. Context engineering is building dynamic systems to provide the right information and tools in the right format such

Harrison's In the Loop Series 5 min read