CrewAI’s Post

CrewAI reposted this

View profile for Tony Kipkemboi

Sr. Developer Advocate - AI Agents @ CrewAI

we just shipped CrewAI v0.121.0! 🎉 so far, most of the agent have been jumping into accomplishing tasks without thinking. just like humans do. so yesterday we released agent reasoning. it's simple; agents now stop and plan before they act. the code change is literally one line: ```python reasoning=True ``` another bonus feature is automatically setting your task outputs to be in markdown. i joked at the webinar today i'll finally stop begging the agents to output in proper markdown 😂 my tasks used to look like this: ```yaml ... expected_output="IMPORTANT: make sure the output is in markdown format without the '```markdown' or '```' tags. ``` now it's just (set this in Task()): ```python markdown=True ``` more details in our docs! (https://docs[.]crewai[.]com)

  • No alternative text description for this image
  • No alternative text description for this image
Aryan Bhargav

Google DSC APP DEV Lead '24 | ex-SWE Fellow @Headstarter AI | ex-Developer @buildspace N&W s5 | Final Year CSE '26

1w

The last yaml part is so relatable specially when we generate both json and markdown and it always mentions markdown with the indicators 🤡 It is a hectic yet fun thing to fix🤣 So this feature would be really helpful 🙌

Philemon Kiprono

AI Engineer | Microsoft Certified | Agents | CrewAI | LlamaIndex | RAGs | DSPy | Azure

1w

I love these new features. I used to struggle with getting agents to output markdown consistently with every run without very explicit examples and instructions, now this setting simplifies it

Alisson Fernandes

Senior Consultant in Innovation, Strategy and Agility

1w

Tony Kipkemboi wow! Can't wait to try and see the difference that reasoning brings! Will this be a better improvement for non-reasoning models, right?

Somesh Bagadiya

AI & Software Engineer | AI, RAG Pipelines, Full-Stack Development, Automation | I Help Companies Boost Productivity by Automating Tasks and Improving Efficiency

1w

Finally Markdown format problem for agents is solved!

Lucas Erb

Founder @AIExperts.com | Helping businesses harness the future | Top Voice in AI | Public Speaker | GenAI & LLM Engineer

1w

Congratulations Tony!

Rodrigo Rocha

Product Strategy | Head of Product | Startup | Antler | Reforge

1w
Like
Reply
lalo morales

Technology & AI Enthusiast | Healthcare Specialist | Self Publisher | Full Stack Developer | Air Force Veteran

1w

bullish on agents!

Edward Acee Jr.

Technology Leader | Platform Engineering | Cloud Strategy | FinOps Innovator

1w

Attended this virtual launch and some of these updates are awesome, especially the markdown=True. Tony Kipkemboi said it well..."No more begging for proper formatting". 👍

Sumit Jha

Building Business @ Detoxio AI @ ElintData ❤️ HPI & Deep Tech [Crypto Quantum Cyber Security AI safety platforms and NLP genAI RAG LORA SFT PEFT RLHF ML/AgeAI] products. Visiting Prof. at IITs IIMs & SPJIMR

1w

Smruti tag chandan as well

See more comments

To view or add a comment, sign in

Explore topics