Long before there was Claude Tag and Victor, there was Scarlett.
We built Scarlett over a year ago as a fun experiment to see what agents could do. To our surprise, she almost immediately started doing probably 90% of our work for us.
We've been reluctant to launch because we knew the competition would be fierce, but our benchmarks show that Scarlett is more than holding her own on both speed & quality.
She also has a host of unique qualities & features:
1) She Just Works. After a year of experimenting with various models, architectures & backends, she just works (and does work).
2) Autopilot. She is trained on 50+ business/growth books, you have the option to use her passively or to set her free to essentially run your whole company from marketing to support.
3) iMessage. A lot of people (solopreneurs) don't like or need slack, so we have an alternative.
4) Use Our Keys. With OpenClaw, Claude, etc you need to buy subscriptions to the things you want to use like HeyGen or XAI, but with Scarlett you can use our keys and we'll pass along the cost.
5) Right Model, Right Job. You can use Opus for chat, Sol for Coding, Fable for design, you pick the right model for the job.
Great product guys, love the fact it comes with 500+ connectors. Let's goo!
congratulations! after a year of testing internally, what was the biggest wow moment that convinced your team she was ready for a public launch?
Played around with Scarlett for a bit and was surprised how naturally it slotted into our slack workflow without feeling like another chatbot. The autopilot features still need some tuning but the teammate framing actually clicked for me.
Congrats! the autopilot feature is fascinating. can users customize how much control Scarlett has over marketing, support or operations based on their comfort level?
congratulations! the she Just works philosophy really stood out. what were the biggest engineering challenges you faced over the past year to make Scarlett reliable enough for daily use?
one thing that caught my attention was the ability to use your managed keys for external services. that's a great onboarding experience. how easy is it for users to switch to their own API keys if they decide to later?
Really interesting direction. How do you think about control vs. autonomy - especially when decisions have real business impact? Congrats on the launch!
Congratulations on the launch!
i really like the idea of using your API keys instead of requiring users to manage multiple subscriptions. how do you handle usage limits and cost optimization behind the scenes?
the Autopilot capability sounds powerful. for founders who are just getting started, what are the first three workflows you would recommend automating with Scarlett to see value quickly?
Congratulations on the launch!
Scarlett sounds like a practical AI agent rather than just another chatbot. how does she decide when to act autonomously versus asking the user for approval, especially in business workflows?
I like that you're positioning Scarlett as a co-worker rather than another AI assistant. That's a much higher bar, because teammates aren't judged by how much they can do—they're judged by whether people trust them with responsibility. If AI reaches that point, the relationship users have with these products changes completely.
Love the "right model, right job" approach ☺️☺️ Curious how you think about external tools and live data, do you see Scarlett becoming more of an orchestrator that can plug into specialized capabilities over time, or do you prefer building everything natively?
@dansutera This one's personal. I've been duct-taping AI tools together at Ctruh to cover exactly this gap, and an AI teammate that actually holds context and owns the ops glue is the dream. Congrats team, taking it for a spin this week. 🔥
Congrats on the launch, Dan! 🚀 It’s awesome to see you guys pulling back the curtain on how Scarlett runs. The decision to skip the traditional Vector DB route and stick to an SQL-heavy setup for speed (similar to Hermes) is a really fascinating engineering choice.
Since you mentioned Vector DBs sometimes over-cluttered the context, how do you handle deep semantic search or long-term recall when a user asks about a conversation from months ago? Is it purely structured querying, or do you have a hybrid text-search layer built into the SQL database?
The iMessage angle is underrated for solo operators. A lot of small businesses do not live in Slack, and forcing them into a new cockpit can kill adoption. The piece I would want very visible is the control surface: what Scarlett is allowed to do alone, what needs approval, and what happened while nobody was watching.
This is neat. Does it keep context across different Slack channels or only within threads?
What makes Scarlett different from Claude Code and Viktor?
About Scarlett. on Product Hunt
“Your AI Co-Worker in Slack & iMessage”
Scarlett. launched on Product Hunt on July 10th, 2026 and earned 346 upvotes and 47 comments, earning #3 Product of the Day. Not another AI bot, a real colleague to work alongside your team. Give your team superpowers or even run your company on autopilot.
Scarlett. was featured in Marketing (465.8k followers), Artificial Intelligence (473.1k followers) and CRM (2k followers) on Product Hunt. Together, these topics include over 183.9k products, making this a competitive space to launch in.
Who hunted Scarlett.?
Scarlett. was hunted by Ben Lang. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Scarlett. stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Ben Lang
Hello PH fam!
Long before there was Claude Tag and Victor, there was Scarlett.
We built Scarlett over a year ago as a fun experiment to see what agents could do. To our surprise, she almost immediately started doing probably 90% of our work for us.
We've been reluctant to launch because we knew the competition would be fierce, but our benchmarks show that Scarlett is more than holding her own on both speed & quality.
She also has a host of unique qualities & features:
1) She Just Works. After a year of experimenting with various models, architectures & backends, she just works (and does work).
2) Autopilot. She is trained on 50+ business/growth books, you have the option to use her passively or to set her free to essentially run your whole company from marketing to support.
3) iMessage. A lot of people (solopreneurs) don't like or need slack, so we have an alternative.
4) Use Our Keys. With OpenClaw, Claude, etc you need to buy subscriptions to the things you want to use like HeyGen or XAI, but with Scarlett you can use our keys and we'll pass along the cost.
5) Right Model, Right Job. You can use Opus for chat, Sol for Coding, Fable for design, you pick the right model for the job.
We hope you love her as much as we do!
Cheers,
Dan