Moura: PwC is currently using CrewAI in production
João Moura · How To Create Ai Agents From Scratch (CrewAI, Zapier, Cursor) · Dec 28, 2024 · at 1:41:47
João Moura, founder and CEO of CrewAI, discusses enterprise case studies featured in his DeepLearning.AI agent courses with Greg Isenberg.
0:00 / 0:07exact quote · 7.1s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“There's an interview with the CTO of gen AI on PwC on how PwC is using Korea in production.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from João Moura
Moura: OpenAI's o1-mini struggles with agents by avoiding external tools
“Honestly, O one mini in my experience for agentic behaviors, sometimes falls short. Just because it already has kind of like chain of thought embedded on it. It tries to basically like Figure out everything itself without using any tools and kind of like outsm…”
João Moura: Cursor Will Not Replace Software Engineers Anytime Soon
“Again, silly me thinking that cursor is gonna replace engineer so soon. It's gonna take quite a while.”
Moura: 7B and 14B parameter models loop excessively as AI agents
“Smaller models, like smaller, or seven B, 14 B, they don't work as well. You can get them to behave as agents, but they usually take even longer because they go in so many blind alleys and keep like retrying things. So you definitely wants to go, like my go-to…”
Moura: Role framing in system prompts significantly changes LLM agent output
“Because these agents, they're kind of like impersonating roles. You do get different behaviors depending on, you do get different behaviors depending on how you give them like a different role. So you can actually replicate this on ChatGPT. Like if you ask Cha…”
Moura: Complex agent use cases require deterministic hooks for consistency
“As the use case has gotten more complex, you start to need more precision in more like a repeatability and consistency on their use cases. So usually people start with before and after hooks.”
Moura: AI coding agents accelerate 0-to-1, but 1-to-10 remains manual
“Definitely AI and agents and things like Devon now and like other solutions, they help a lot, but it's still like a lot of like, just making sure that from going, going from zero to one is very fast and getting faster and faster. Going one to 10 is still very …”