Building with AI: Bryan Helmig on Zapier
AI lets us build automations which we could never have built through traditional programming. Because AI is able to process unstructured information in a common sense way, a whole new class of tasks can now be automated for the first time. AI is also empowering; because the main interface to AI is natural language, anyone can build automations without any programming experience.
Bryan Helmig, co-founder and CTO of Zapier, joins Anton to discuss how Zapier is using AI to automate workflows for businesses. Bryan shares how Zapier is making AI accessible to non-technical users and how they are building tools to help users iterate on their AI models. They also discuss the challenges of building AI tools for non-technical users and how to collect and evaluate feedback on AI models.
***
Links and Chapters below:
Flo Crivello on X (Twitter) - https://x.com/Altimor
Lindy.ai - https://www.lindy.ai/
***
0:00 - intro
1:35 - zapier and AI apps
3:11 - AI has a great feedback loop
3:35 - zaps and AI
8:30 - zaps and billing for AI
10:00 - AI is early and moving quickly
11:00 - teaching people AI
14:49 - teaching people iteration
15:50 - evals and feedback
25:50 - packing the users prompt
28:12 - constrained outputs and chains
30:00 - tool use is underrated
31:15 - multiturn zaps
35:00 - biggest user misconception
36:20 - just try it
39:38 - what is Zapier automating with AI
42:24 - AI & human iteration
43:05 - how to think about models getting smarter
45:05 - everyone can upskill and build
46:25 - misconceptions