Christian Bromann (@bromann) / X

Christian Bromann

3,059 posts

Christian Bromann

@bromann

Running on agentic reasoning and espresso. Building with @LangChain 🦜🔗.

San Francisco

bromann.dev

Joined September 2009

Replies Articles Media

Pinned
Christian Bromann
@bromann
Aug 7
We’re launching Managed Deep Agents today 🎉👀 langchain.com/blog/managed-d… @LangChain The goal posts for building agents have moved. Giving an agent tools, deploying it somewhere, and putting a UI in front of it isn’t the hard part anymore. The next challenge is everything around
Managed Deep Agents is now in public beta
From langchain.com
Christian Bromann
@bromann
Aug 7
Some examples if you are curious, just fork and deploy: TypeScript: github.com/christian-brom… Python: github.com/christian-brom…
Christian Bromann
@bromann
Aug 7
We’re launching Managed Deep Agents today 🎉👀 langchain.com/blog/managed-d… @LangChain The goal posts for building agents have moved. Giving an agent tools, deploying it somewhere, and putting a UI in front of it isn’t the hard part anymore. The next challenge is everything around
Christian Bromann
@bromann
Aug 6
Using @thesysdev's OpenUI with @LangChain's Deep Agents just got ridiculously easy 🤯 Thanks to the new stream transformer, you can plug a Deep Agent stream directly into @openuidev/langchain and start rendering generative UI. Agents → stream → UI. That’s basically it.
Christian Bromann
@bromann
Jul 17
I used to hate code repositories that were overly strict with code linting and prettier rules - in todays world you can't be strict enough with all these agents trying to contribute slop to the code.
Christian Bromann
@bromann
Jul 15
I would love a "grill me" skill for evals 😍
Viv
@Vtrivedy10
Jul 14
ok so it’s early but @mattpocockuk’s grill-me skill feels like great DX for iteratively building evals/environments with humans + agents in the loop understanding a repo + traces + definition of success is pretty much never a one shot thing, it’s many step collaboration between