CrewAI reposted this
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)
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 🙌
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
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?
Finally Markdown format problem for agents is solved!
Congratulations Tony!
bullish on agents!
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". 👍
Sr. Developer Advocate - AI Agents @ CrewAI
1w📚 https://docs.crewai.com