the best teams building agents ship early and iterate quickly you can't just ship an agent and then forget about the key to getting the best agents is to build an iterative improvement loop
@hwchase17
-
Defining AI Agents as Systems Beyond the Model
By
–
agents are definitionally a system around a model lots more than a model!
-

Addressing High Costs in AI Coding via Open-Source Models
By
–
ai coding is getting expensive use more open models!
-
How Ramp Built an AI Agent for Data Analysis
By
–
Talked to @ramplabs Head of Applied Research Alex Shevchenko on the Max Agency podcast to learn how @Ramp Sheets was built, their internal agent Inspect, and so much more.
— Harrison Chase (@hwchase17) 7 mai 2026
YouTube: https://t.co/gqWdkhc8xK
Apple: https://t.co/YLtl9owlPy
Spotify: https://t.co/gjI6kS5Fpj pic.twitter.com/aKElPwpLjNTalked to @ramplabs Head of Applied Research Alex Shevchenko on the Max Agency podcast to learn how @Ramp Sheets was built, their internal agent Inspect, and so much more. YouTube: https://
youtube.com/watch?v=trEM9O
Kr5Sc
…
Apple: https://
podcasts.apple.com/us/podcast/how
-ramp-built-an-ai-agent-that-can-think-outside/id1891551672?i=1000766630498
…
Spotify: https://
open.spotify.com/episode/49NvGQ
RI2TWlYXziJ2ALiz
… -
AI reflects on Twitter feuds, clarifies its role as an AI model
By
–
say more? like you want to use langsmith key to access all models
-
AI-Generated Fan Art and Musk’s Tech Ventures
By
–
we want this to be deepagents deploy: https://
docs.langchain.com/oss/python/dee
pagents/deploy
… whats missing? would love feedback! -

Platform Liability and Section 230: Examining Design Choices and Legal Challenges
By
–
this deepagents deploy https://
docs.langchain.com/oss/python/dee
pagents/deploy
… (or at least directionally where we want to take it) what's missing? give us feedback! -

Ouster’s Native Color SPAD Pixels for Visible Light Capture
By
–
we need more benchmarks! awesome work by harvey here, and excited to work with them
-

Grok AI Feature Available for Premium Subscribers
By
–

agent observability is great. but in order to use it to power an agent improvement loop, you need to be collecting (and even generating) feedback data inside your agent observability platform
