The biggest blocker for AI agents? It is performance quality, BY FAR For all the talk of cost, latency, safety… the fact is, most people are still just struggling to get agents to work Full survey here: https://
langchain.com/stateofaiagents
@hwchase17
-
Performance Quality: Main Blocker for AI Agents
By
–
-
Top Agent Use Cases and Emerging Market Trends
By
–
Top agent use cases: – research and summarization
– personal assistant
– customer service
– code gen interesting that most agent startups popping up seem to be in customer service and coding Full report: http://
langchain.com/stateofaiagents -
Multimodal Support: Adding Attachments to Traces
By
–
More multimodal support! Add attachments to traces https://t.co/BL2gZCJMx8
— Harrison Chase (@hwchase17) 14 novembre 2024More multimodal support! Add attachments to traces
-
Language Agents Discussion and Clarification
By
–
Yeah agree. I think implicitly wrote this focused on language agents but you’re correct
-
Prompt Optimization Tools Released in Python Library
By
–
prompt optimization has been something we've been experimenting with for a while, and excited to release some initial tools there right now just a python library, but working to improve and integrate with LangSmith in the future
-
LangGraph Academy adds memory module for GenAI agents
By
–
LangChain Academy will be an up-to-date reference for all things GenAI We've updated our LangGraph course to add a NEW module on memory Learn how to enable long term memory for your langgraph agents from the one and only @RLanceMartin
-
Cursor for Prompt Engineering: Introducing Prompt Canvas
By
–
What is the "cursor for prompt engineering"? We've started exploring this with "Prompt Canvas", a novel UX for developing prompts I think it's a really cool first step – check it out and lmk what you think Blog: https://
blog.langchain.dev/introducing-pr
ompt-canvas/
…
Video: https://
youtu.be/nXrx-_9Yucc -
Canvas UIs Superior to Chat for Content Creation
By
–
If you are using chat interfaces for writing text (blogs, essays, code) you're doing it wrong UXs like Canvas are SO much better for this. Diffs, highlight specific pieces, quick actions, etc See OpenCanvas for a fully OSS implementation of this https://
github.com/langchain-ai/o
pen-canvas
… -
Berkeley Research on AI Evaluations and Agent Systems
By
–
Two of the things we spend the most time thinking about are evals and agents This new research from @sh_reya and Ankush Garg at Berkeley touches on BOTH those things Includes an example notebook for how to run on your LangGraph app!