Ready, Fire, Aim

We built an AI bot, and it went viral.

Author

Josh Cadorette
December 22, 2022

Howdy from Durham, NC,

Welcome to the 11 new subscribers from this past week!

My 2022 Annual Review is getting pushed back to next week for a great reason.

This week, my friend David and I built an AI bot for a hackathon.

We went viral - 600k+ saw our idea, 125k+ watched our demo video, and 1k+ signed up for our beta (which you can try for yourself here.)

You'll get the annual review next week.

For now, here are the details on the insanely fun 24 hours we just had.

It started with Ben's Bites Hackathon.

Ben Tossell is an entrepreneur and the creator of Ben's Bites, a daily newsletter on all things AI.

A few weeks back, Ben announced that he would host a hackathon. Teams had 1 week to put an AI solution together. Judges pick the top 3 projects and hand out cash prizes to the teams.

I immediately reached out to my friend, David, to collaborate. How come?

David and I have built successful AI products in the past, we know each other's skill sets, and we know how to effectively work with one another asynchronously.

David does the engineering. I do the product/design. We're both creative in different, complimentary ways.

I went to David with an idea that solves a problem I myself have as a podcaster - writing the show notes.

Long time newsletter subscribers will remember David from van breakdown #1 in June of this year. David and I had worked remotely for 1yr+ but had never met in-person. On the day that I was supposed to meet David in real life for breakfast in Illinois, Caroline's fuel pump gave out in a Walmart parking lot (her fav spot to die.) Instead, David was kind enough to come to me so we could still meet up.

Enter Feather AI - the premier audio-to-text summarizer.

The biggest pain when producing a podcast is trying to type up a summary of everything that happened in the episode.

I thought to myself, "What if you could summarize a conversation so that it could serve as the 1st draft of your show notes?"

That way, you could decrease production time and become a more prolific creator.

Suddenly, more use cases past podcasting emerged:

  1. What if you were a government consultant who wanted to summarize congressional hearings so that you could stay on top of legislative affairs?

  2. What if you were an investor who wanted to summarize earnings calls/fed meetings so that you could stay on top of earnings/interest rates?

  3. What if you missed a zoom call but wanted to read a quick summary of what was said so that you didn't have to rewatch the entire recording?

  4. What if you missed a webinar but you wanted to read a quick summary so that you could still extract value from the speaker's session?

In one week, we produced a prototype that can generate a text summary from audio.

Click on the image below to try our demo for yourself.

We worked to make this as user friendly as possible. Click on the image to see Feather AI in action.

Time to take Feather AI to Twitter.

We haven't yet heard about the Hackathon results, but we wanted to share Feather AI with more folks than just our family, friends, and fellow Hackathon members.

I thought back to the wacky thing I did this past November: I published a thread on twitter every single day.

This exercise taught me how to write engaging tweets that tell a good story, so I applied this skill to Feather AI and published a Twitter thread on our nifty little product.

The thread went viral. 600k+ saw it, 125k+ watched our demo video, 1k+ signed up for our beta.

The product kept breaking due to high usage. We kept fixing it. It was awesome.

First, the servers were overwhelmed (so we upgraded them.) Then, one of the components of the AI model gave out (so we rebooted it.) In comes the server again with another issue (so we performed another upgrade.) Then, gmail capped our account for sending too many emails (time to make a new email address.) Up. Down. Up. Down. Up. Down. Up. Down. Up.

At it's peak, we were processing 4 summaries per minute. It was so dang cool to see people across the world engaging with a product that was just an idea a week ago, and the feedback was incredibly positive too.

We even did our best to contact everyone who made a summary request when Feather AI was temporarily down so that we could: 1. Thank them for giving us a try. 2. Apologize for our lackluster performance and 3. Invite them to give us another shot.

The Twitter thread that went viral.

Biggest takeaway from the last 24 hours - ready-fire-aim.

Ready, aim, fire? No - "ready, fire, aim," according to Michael Masterson.

Masterson is a successful entrepreneur who argues that balancing calculated risks/quick decision making skills + careful planning/intentional strategy is the key to business success - not one or the other but both.

We had planned, strategized, and prototyped all week long, but this product wasn't going to improve itself from the sidelines.

Did we stress test our product? Yes. Did we think it'd get this much traffic? No. Is having "too much traffic" a great problem to have? Yes, and we met the moment.

David and I had to fire in order to uncover the server issues, API problem, and gmail cap so we could then aim in on them quickly. The result? We captured 1k+ beta users.

We now have a stronger Feather AI and are more prepared for future product launches because of the experience we gained while firing and aiming.

So what happens next? We follow-up with all of the people who gave us great feedback on our beta version, chart a roadmap forward for Feather AI in 2023, and wait to hear the results of the hackathon.

I don't know where we'll end up, but I do know that building, adapting, and surviving was fun and insane in all of the right ways.

And shoot, that's been the whole purpose of The Build and Building Out Loud all along - to build cool stuff, have fun, and share what I learn with others.

The 2min Feather AI pitch we submitted for the hackathon.

What I'm paying attention to:

Photos of The Week

Location this past week: Durham, NC

One guy replied saying he'd test Feather AI using an Irish podcast to see if it could trip us up. Still haven't heard back from him, but I'm thinking we can handle an Irish brogue 😂

Screenshot of some of the feedback we received.

More feedback.

We built the prototype on a platform called Streamlit. They came across our app on Twitter and helped us increase the memory on our app.

Spent time with fellow newsletter writer, Aidan, in Durham.

Thanks for reading

Try out our beta version and let me know how you like it by replying here!

Josh

Want more Build content? Check out the links below

Listen to the Building Out Loud Podcast on Spotify or Apple Podcasts

Reply

or to participate.