giving a talk tomorrow on "building agents that work like coding agents" at @LangChain we help folks build all types of agents, but a lot of them "work like" coding agents in terms of harness design
@langchain
-
Managed Deep Agents Adds Scheduling and Per Run Configuration
By
–
TL;DR on Managed Deep Agents 0.9:
— LangChain (@LangChain) 26 octobre 2026
✅ Agent-created schedules: agents can set up reminders and recurring tasks from a conversation.
✅ Per-run configuration: one deployment can pick its model, skills, and tools for each run.
✅ Slack reactions: agents acknowledge messages before… https://t.co/V1uD4t8kfoTL;DR on Managed Deep Agents 0.9:
✅ Agent-created schedules: agents can set up reminders and recurring tasks from a conversation.
✅ Per-run configuration: one deployment can pick its model, skills, and tools for each run.
✅ Slack reactions: agents acknowledge messages before -
Managed Deep Agents Introduces a Getting Started Keynote
By
–
What’s new in Managed Deep Agents 0.9? And how can you get started?
— LangChain (@LangChain) 26 octobre 2026
Watch @VictorMoreira16's keynote from Interrupt London for an inside look. https://t.co/cMWoYlj69f pic.twitter.com/F059jHymSRWhat’s new in Managed Deep Agents 0.9? And how can you get started? Watch @VictorMoreira16
's keynote from Interrupt London for an inside look. https://
youtu.be/Wb3hQaG_xf0 -
A Production Agent Event Explores Live Web Information Use
By
–
On November 12th, we're teaming up with @tavilyai to showcase how production agents find, understand, and use information from the live web. RSVP for this NYC event: https://
luma.com/ivrwjk0o -
Continual Learning Talk Examines Integration Into Software Delivery
By
–
Continual learning is about to get boring, in a good way.@willcb from @primeintellect took the stage at our recent Learning Loop event to make the case.
— LangChain (@LangChain) 23 octobre 2026
If you're thinking about how continual learning fits into the way your team already ships software, this full 21-minute… pic.twitter.com/CzwSgmEX77Continual learning is about to get boring, in a good way. @willcb from @primeintellect took the stage at our recent Learning Loop event to make the case. If you're thinking about how continual learning fits into the way your team already ships software, this full 21-minute
-
AI Design Quality Depends on Context Beyond Correct Code
By
–
taste is the judgment that separates work that's correct from work that's good models can already write html, css, chart specs and animation code. what they don't have is your context, so they reach for the same familiar patterns (i.e distributional convergence) our design
-
LangChain Academy Explains Timely Retrieval in Agent Memory
By
–
🎓 New from the LangChain Academy team How agents remember to retrieve the right info at the right time ⤵️
-
LangSmith Workshops Cover Deep Agents and Agent Engine Development
By
–
Next stop on the LangSmith Roadshow? Chicago! Hear about the current state of agent development, and get ready for two hands-on workshops focused on Deep Agents and LangSmith Engine. Interested in attending? RSVP today!
-
Content Studio Demonstrates a Shared Company Harness for Design Agents
By
–
Content Studio is a truly epic example of a company harness built on Managed Deep Agents. It is multiplayer by nature, I work with it in a public channel so others can weigh in on the design process https://t.co/nSsMwtdfUi
— Caspar (@caspar_br) 21 octobre 2026Content Studio is a truly epic example of a company harness built on Managed Deep Agents. It is multiplayer by nature, I work with it in a public channel so others can weigh in on the design process
-
LangSmith Agent Traces Support Fine Tuning a Specialized Model
By
–
amazing to see such a successful example of using agent traces in LangSmith to fine tune a model! Was awesome working with the @corridor team on this