Loading video...

Video Failed to Load

Go Home

made a video covering my ai coding workflow + tools, built a dashboard < 5 mins ridiculous how easy it is to go from idea to product now half my day is just conducting ai (cursor, claude v0) to build things for me 0:00 - 1:48 tools overview 1:50...

239,081 views • 1 year ago •via X (Twitter)

10 Comments

Prompter's profile picture
Prompter1 year ago

It's truly crazy. Built this spend management workflow automation in about 8 minutes. Checks if there's a matching receipt in your GDrive on your expense tracker, and adds the name to your google sheet. Need to try cursor, this was on good 'ol ancient VS code ;)

Sully's profile picture
Sully1 year ago

Cursor is really good

RameshR's profile picture
RameshR1 year ago

MVP production duration from a year to one day? I can VCs salivating and reducing their investment costs.

Sully's profile picture
Sully1 year ago

Maybe a week l

Opulent Byte's profile picture
Opulent Byte1 year ago

The era of solo entrepreneurship is coming 😎

Sully's profile picture
Sully1 year ago

Yup

Dennis Kortsch's profile picture
Dennis Kortsch1 year ago

v0 also works really nicely with images of websites/apps that you like ...

Sully's profile picture
Sully1 year ago

Yep! It’s really good for starting off

Akash Manohar's profile picture
Akash Manohar1 year ago

Thanks for the overview. TIL cursor can create files from the terminal. At 7:11 in the video, how do you get the preview pane on the right side in Claude? My account only shows me code snippets in the chat window inline.

Sully's profile picture
Sully1 year ago

Artifacts! Gotta turn it on

Related Videos

I'm often asked for the best public example of AI evals done right for a real, production product. I finally have an answer. Teresa Torres shares how she shipped an AI interview coach, and used evals to rapidly squash bugs and improve the product. Teresa shows how she: 1. did error analysis FIRST to find real issues (instead of using generic metrics) 😍 2. used Jupyter notebooks to analyze errors 3. built custom annotation tools + custom widgets in notebooks 4. built a LLM-judge and assertions to test for specific errors 5. iterated through this feedback loop until it worked. 6. kept things simple the whole time It's also probably the best commercial for Jupyter notebooks you can imagine. 🥰 Chapter summary below. Link to YT in next thread 00:00:00 - Intro 00:01:45 - The Product: Building an AI Interview Coach 00:06:34 - The Problem: How Do I Know if My AI Coach is Any Good? 00:10:15 - Using Airtable for Traces and Annotation 00:12:15 - Discovering Jupyter Notebooks and Designing the First Evals 00:15:15 - Example Evals: LLM-as-Judge vs. Code-Based Assertions 00:21:00 - Learning Python with ChatGPT to Analyze Eval Results 00:31:00 - VS Code, Custom Tools, and an Eval Investigation Notebook 00:39:45 - Building a Custom Annotation Tool with Claude 00:41:00 - From Personal Project to Production App 00:46:02 - How Should PMs and Engineers Collaborate on AI Products? 00:55:45 - Q&A: Capturing Feedback and Annotations from End Users 00:58:11 - Q&A: Is a Technical Background Necessary to Build AI? 01:02:28 - Q&A: What's Next for Teresa? 01:03:13 - Q&A: Unpacking the Micro-Decisions of Building an AI App

Hamel Husain

51,376 views • 11 months ago