In the Loop

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”

In the Loop 3 min read

How and when to build multi-agent systems

Late last week two great blog posts were released with seemingly opposite titles. “Don’t Build Multi-Agents” by the Cognition team, and “How we built

In the Loop 6 min read

The Hidden Metric That Determines AI Product Success

Co-authored by Assaf Elovic and Harrison Chase. You can also find a version of this post published on Assaf's Medium. Why do some

In the Loop 8 min read

How to think about agent frameworks

TL;DR: * The hard part of building reliable agentic systems is making sure the LLM has the appropriate context at each step. This includes both

In the Loop 20 min read

How do I speed up my AI agent?

I get this question a bunch. Developers generally first spend time getting the agent to work, but then they turn their attention to speed and

In the Loop 4 min read

MCP: Flash in the Pan or Future Standard?

Model Context Protocol (MCP) is creating quite the stir on Twitter – but is it actually useful, or just noise? In this back and forth, Harrison

In the Loop 5 min read

Communication is all you need

“What we’ve got here is failure to communicate” - Cool Hand Luke (1967) Communication is the hardest part of life. It’s also the

In the Loop 7 min read

Memory for agents

At Sequoia’s AI Ascent conference in March, I talked about three limitations for agents: planning, UX, and memory. Check out that talk here. In

In the Loop 5 min read

UX for Agents, Part 3: Spreadsheet, Generative, and Collaborative UI/UX

Learn about spreadsheet UX for batch agent workloads, Generative UI, and collaborative UX with agents.

In the Loop 4 min read

UX for Agents, Part 2: Ambient

This is our second post focused on UX for agents. We discuss ambient background agents, which can handle multiple tasks at the same time, and how they can be used in your workflow.

In the Loop 4 min read

UX for Agents, Part 1: Chat

At Sequoia’s AI Ascent conference in March, I talked about three limitations for agents: planning, UX, and memory. Check out that talk here. In

In the Loop 4 min read

Planning for Agents

The fourth installment in our "In the Loop Series," in which we talk about what planning means for an agent and how to improve it.

In the Loop 6 min read