Chris Goodbaudy

Chris Goodbaudy

Experienced developer, fledgling founder

Badges

Tastemaker
Tastemaker
Gone streaking
Gone streaking

Maker History

  • The Flight Steward
    The Flight StewardMobile order taking for Alaska Air Flight Attendants
    Sep 2026
  • 🎉
    Joined Product HuntSeptember 17th, 2026

Forums

I merged a money/budgeting app and a macro tracker into one. Smart bundle or a mistake?

About 6 months ago I was thinking I wished there was a better way to track my spending - especially what purchases now would do to my account balance at the end of the month. I was also thinking that I really didn't know whether or not I was following a keto diet and didn't have any good way to track it if I were.

Then I had an epiphany. I went out to eat and stared at the restaurant receipt. On there I saw my money purchase, I wished there was a better way to calculate the tip (I always hate doing the math at the table), but I also saw what I ate listed out on the receipt. On this one piece of paper was my spend and my food! If I could just take a picture of it I could capture both in one go.

•

2h ago

I feel behind. Does anyone else feel this?

I open Product Hunt every day and I see so many people launching amazing products, getting upvotes, and sharing their success stories.

>

> And honestly, instead of feeling motivated, sometimes I feel behind. I start thinking, everyone is moving so fast and I have not even started properly yet.

>

•

3h ago

How we reduced AI support hallucinations by restricting our knowledge base to solved tickets

During our beta we linked our AI support bot to the Notion workspace, which had old product specs and meeting notes. We believed that giving the AI support bot context would let it answer any question but the AI support bot began to create features that we had cancelled six months before.

We solved the problem by disconnecting the wiki and feeding the AI support bot only verified, resolved customer support threads from the last ninety days. We also set a retrieval threshold so that the AI support bot refuses to answer when the similarity score is lower than 0.82 and then sends the user to a human instead.

Within two weeks wrong answers dropped to zero and our support team saved about twelve hours each week because they no longer had to apologize for inaccurate AI support bot replies.

Curating clean verified data matters a lot more, than letting your AI see everything you have ever written. How do you stop outdated documents from polluting the answers of your AI support bot?

View more