SODAX SDKDigital asset flows you can build and deploy with AI.
Promoted
Propane gives your product team and agents one connected, always-current view of your customers. Automatically collected from all your tools. Collaborate on a shared canvas. Commit straight to any coding or design agent. Secure, maintained, always on. You just build products people love.
Congrats on the #1 spot today! Automatic context for agents is such an underrated problem — most teams are still manually re-explaining the same context every time. Curious what was the trickiest part of keeping that context accurate as products evolve?
Propane
@martin_mo appreciate that Martin!!🤝
100% this is a problem we have been grappling with ourselves, and for sure really useful product context is buried in the tools that users already use, but often scattered and inaccessible!
One tricky thing in the AI-era there is dealing with a lot of noise - it's not just finding the important product context, but also working out what actually matters and what is emerging across customers..
tackling this was hard, but we think we have gone to great efforts to make this simple with signals. we constantly dig through your customer feedback, product analytics etc. to give you the most important product context at your fingertips!
what have you found challenging as a builder building SURO AI in this era!?
@benfleming "Really appreciate the detailed take — and the signal-vs-noise framing resonates, though as a solo builder I'd say I'm dealing with the inverse problem: not too much data, but too little. With a small early user base, it's genuinely hard to tell whether something is a real pattern or just noise from a handful of people. I've had to lean more on direct conversations than analytics at this stage — though I can already see how a tool like yours becomes essential once that scales up. Biggest challenge for me right now is probably wearing every hat at once — product, support, and growth — with no team to delegate any of it to. How did your team decide which signals to prioritize surfacing first when you were validating the idea?"
Propane
@martin_mo anytime man!
for sure there are different problems at different stages, however something useful for you may be the competitors tracking, so you can see what others are building and keep on top of that!
sometimes it is hard with so much information out there coming at a rapid pace!
@benfleming That's a great point — competitor tracking is something I've been doing pretty manually so far, mostly just checking in on a handful of tools every week or two. Do you have a lightweight way of doing this yourself, or is it more about setting up alerts for specific moves (pricing changes, new features, etc.) and reviewing those periodically? Trying to find something sustainable that doesn't eat up too much time as a one-person team.
Propane
@tehreem_fatima5 No, we take care of that, we are also planing to enable the agent to talk to the handover to get what i needs to do the job and use the spec to eval the job.
Congrats on the launch Dennis. Can Propane distinguish between strong customer signals and one-off noisy feedback from a loud account?
Propane
@rohanrecommends Thanks, a few people have ask this in a few ways; We have our company context that is vision, icp etc. then we have a clustering system as well that tried to balance this but user intern is also key so it a hard balance between 1 strong voice vs many small; all that is down to startegy or intern when you shape an new feature.
Nas.com
What the strongest use case has been so far: product discovery, roadmap decisions, or handoff into build/design workflows?
Propane
@nuseir_yassin1 Yeah i don't like my answer a bit of them all but the power is in the middel, the shaping as a team in the canvas; Also what we get the best feedback on
Question: Can Propane distinguish between strong customer signals and one-off noisy feedback from a loud account?
Propane
@ranjan_kumar45 Yes we do some clustering and weighting in our signals system but sometime a load voice can be impactfull feedback, so we have to design for the users/company's intern and vision.
Onpilot
Looks Great.. Context is really the bottleneck. How does it keeps the context fresh in case the data connected changes or gets out of date ?
Propane
@nischaydhiman we index data automaticly if there is a new support ticket then we intake it
I had the pleasure of giving Propane a spin with @atherkildsen and I have to say that I believe they're really onto solving "the real" headache for product managers and anyone else working with qualitative (plus quantitative) data collection. Distilling insights from phone calls, emails, usage patterns and shower-thoughts used to be an art form. Propane helps make the process transparent and solid from insight to deployment. Junior PMs get a nudge towards quality and senior PMs get speed and collaboration on the artefacts that matter.
Excited to see where the team will take this!
What are you looking at next @greenlieber ? I suppose with launch on product hunt there will be a lot of insights for you to capture now, and distill? ;)
Propane
@atherkildsen @stian_nm Take over the world haha... I want to enable all Product teams to build amazing products based on context, this values them and their customer, fighting AI slop products.
@atherkildsen @greenlieber amazing, looking forward to seeing where you'll go with this! ✨
Propane
@atherkildsen @stian_nm so do we :)
Propane
@greenlieber @stian_nm 💚 A lot happened since our chat (a month ago 🤪), so you should go check it out!