For you, your agent, your coworker and their agent. It holds the team's critical know-how, research, decisions and data. But it's not a dead storage. It's a workspace that makes the context workable for humans as well as agents.
Heyy builders! 👋👋👋
Meet Kanwas. Your teams brain. For you, your agent, your coworker and their agent.
It holds your team's critical know-how, research, decisions and data. But it's not a dead storage.
It's a real-time collaborative workspace that makes the context workable for humans as well as agents.
We love to run Kanwas for product discovery, positioning, competitors research as well as for GTM. To think things through. To do high-stakes decisions and have it all accessible by agents.
Kanwas brain is self-evolving, so every input, insight, iteration and agent run makes the next one smarter.
It's made to be iterative, visible, fully editable so it fits your workflow.
Hope you like it!!! ❤️
@johancutych This looks like a solid approach to the team knowledge problem—especially the part about making it actionable for both humans and agents. The self-evolving aspect is interesting; I'm curious how you're handling knowledge decay or outdated info that agents might pick up and amplify over time.
Report
@predrag_ristic1 Really like that you’re not trying to force everything into chat bubbles. The industry somehow decided every AI product needs to look like another messaging app and it gets exhausting fast.
One thing I’m curious about though is onboarding for non-technical teams. Engineers usually tolerate messy flexible systems because they understand the power behind them, but operations/marketing/sales teams often need stronger structure.
Have you noticed users naturally understanding how to organize work inside Kanwas, or do people initially create chaos everywhere before finding a workflow? Feels like this kind of product can become insanely powerful or completely overwhelming depending on first-time experience.
@josh_bennett1 Thats a great point and something we are focusing on with kanwas a lot. The first onboarding + what to do after that.
We worried about it a lot at the start but seeing user usage it seems most of them get it. I think canvas interface kind of helps here because most non technical people have used tools like figma or other canvases for creative work.
That said we do plan to do a lot of educational content around kanwas very soon. To really help you get 100% out of it.
@predrag_ristic1@josh_bennett1 EXACTLY! this comment warms my heart. Canvas is something we've put a lot of effort into and takes a lot of our focus, but I really love it for creative work where the work doesn't collapse.
also everyone starts differently. Someone goes chaos first and then turn it into structure, others like to create structure first and keep it clean
@josh_bennett1 Thank you for the nice comment and referencing on chat interfaces and our angle!
For quite a while we were struggling if canvas view is the best approach, but for all of us in the team it clicked from the start, and it was even hard to describe what exactly is making us to feel like that.
Happy to see that many people resonate with it, and find it more natural than chat ones. I guess it simulates the way the brain works, and also the flow when we are at the desk with pen and papers.
@josh_bennett1 This is great observation. It's the fundamental tension between order and chaos. And to be honest, it's one of the big challanges our users are facing. What we recommend to more non-technical user or someone who is just getting started with this is to keep it simple. Use the default structure, add the important context documents and grow it naturally because too much irrelevant context or some outdated documents can be often worse than nothing at all for the reasoning and outputs of ai agents.
Report
The idea of treating team knowledge as something “living” instead of static documentation is really interesting.
Feels like the challenge over time is keeping the context actually useful instead of turning into another layer of noise as more humans and agents interact with it.
@munevver_ertuncccc and we really believe that, at least for now, it also needs to be transparent, readable, workable by humans. Thats how you get actually living knowledge base
@munevver_ertuncccc Yep thats one of the biggest reasons we created kanwas. For ourselves first. Its very easy for context to get out of date. But if you can see it, iterate on it and have a smart agent that gardens it output of your LLMs becomes 10x better
@munevver_ertuncccc I agree, that is definitely one of the things that we want to focus on a lot. AI is still not in the phase of taking care of it on its own, and on the other hand teams don't have time to manage and update it, so we are trying to find a balance of keeping people in the loop by making agent support this flow, until we can bet on the complete solution from ai side
@munevver_ertuncccc Yes, “living” i think is the keyword for us. Context that compouds as you use the tool, and context that is actually useful, because Kanwas agent and other AI agents can tap it easily.
Report
as a solo founder, my 'team' is mostly just me and a handful of agents. keeping the context consistent across all of them is a full-time job. kanwas feels like it could save me hours of 're-explaining' the product vision to my dev and marketing agents. awesome @johancutych
@vikramp7470 yeah like having the whole thinking in one space where it's accessible by both humans and agents is like super power. you do better decisions + you go faster
@vikramp7470 I often use Kanwas for solo work too. The canvas interface is so much better than antyhing i have running locally. Also the CLI is a great way to give my AI agents a place to give me visibility into what is going on and share their output.
@vikramp7470 exactly! the best part is that you can still use your coding agents to pull the context and let it work on top of the same context rest of the agents have.
@vikramp7470 Yep the cool thing about kanwas is that we build on native filesystem files. So its very easy for coding agents to work with. Exporting and importing can be done with a simple CLI tool.
I have tried to make this work with Claude chats, Notion pages, GitHub issues, and random docs. The issue is not creating content, it is keeping context usable after the first session. Kanwas seems pointed at that exact gap.
@isratjahan17 Yeah. We want to solve this problem in a comprehensive way once and for all. Automatically updating context that you can verify and edit. Not just a blob of 300 documents you have no idea what to do with.
@cam_eddy we've two modes, Direct that is behaving similar to coding agents, executing.
but the mode that I love the most is "get my brain going", it's made to ask you a lot of questions so it really gets your brain going and makes the outputs sharp thanks to your taste and judgment
@cam_eddy We are really trying to do something different. Most AI tools will just produce more more and more output. We want to focus on quality instead. Output less, ask more and really think with the user.
@cam_eddy Interesting question Cam! As @johancutych already said we support 2 modes, but regardless of that you can update main instructions and your style and way of working to be more push back oriented
@cam_eddy The agent is something we have invested a lot into. It's opinionated, for example it asks a lot of targeted questions to get as much "soft" context that isn't yet captured to help you make good decisions. Being epistemologically honest and working well with assumptions is something we see as the biggest problem of todays AI agents and we are working on every day to improve.
Report
This is for sure worth looking into. What I worry about is the space getting overfilled with content which becomes irrelevant over time. How do you plan to solve this issue?
@josip_herceg Good to see you here Josip! yeah that's a real issue, and we are bringing more schedule tasks soon so you can easily setup agent to run linting process to keeps things clean.
the idea is to have like a gardener that goes through the context and finds things that contradicts, overlap, or are outdated and messy. Then to bring them to your attention so you can decide to weed them out or keep them
Report
@johancutych This sounds good. That is excatly what I am hoping to see. Keep it up guys!
Kanwas
RiteKit Company Logo API
@johancutych This looks like a solid approach to the team knowledge problem—especially the part about making it actionable for both humans and agents. The self-evolving aspect is interesting; I'm curious how you're handling knowledge decay or outdated info that agents might pick up and amplify over time.
@predrag_ristic1 Really like that you’re not trying to force everything into chat bubbles. The industry somehow decided every AI product needs to look like another messaging app and it gets exhausting fast.
One thing I’m curious about though is onboarding for non-technical teams. Engineers usually tolerate messy flexible systems because they understand the power behind them, but operations/marketing/sales teams often need stronger structure.
Have you noticed users naturally understanding how to organize work inside Kanwas, or do people initially create chaos everywhere before finding a workflow? Feels like this kind of product can become insanely powerful or completely overwhelming depending on first-time experience.
Kanwas
@josh_bennett1 Thats a great point and something we are focusing on with kanwas a lot. The first onboarding + what to do after that.
We worried about it a lot at the start but seeing user usage it seems most of them get it. I think canvas interface kind of helps here because most non technical people have used tools like figma or other canvases for creative work.
That said we do plan to do a lot of educational content around kanwas very soon. To really help you get 100% out of it.
Kanwas
@predrag_ristic1 @josh_bennett1 EXACTLY! this comment warms my heart. Canvas is something we've put a lot of effort into and takes a lot of our focus, but I really love it for creative work where the work doesn't collapse.
also everyone starts differently. Someone goes chaos first and then turn it into structure, others like to create structure first and keep it clean
Kanwas
@josh_bennett1 Thank you for the nice comment and referencing on chat interfaces and our angle!
For quite a while we were struggling if canvas view is the best approach, but for all of us in the team it clicked from the start, and it was even hard to describe what exactly is making us to feel like that.
Happy to see that many people resonate with it, and find it more natural than chat ones. I guess it simulates the way the brain works, and also the flow when we are at the desk with pen and papers.
Kanwas
@josh_bennett1 This is great observation. It's the fundamental tension between order and chaos. And to be honest, it's one of the big challanges our users are facing. What we recommend to more non-technical user or someone who is just getting started with this is to keep it simple. Use the default structure, add the important context documents and grow it naturally because too much irrelevant context or some outdated documents can be often worse than nothing at all for the reasoning and outputs of ai agents.
The idea of treating team knowledge as something “living” instead of static documentation is really interesting.
Feels like the challenge over time is keeping the context actually useful instead of turning into another layer of noise as more humans and agents interact with it.
Kanwas
@munevver_ertuncccc and we really believe that, at least for now, it also needs to be transparent, readable, workable by humans. Thats how you get actually living knowledge base
Kanwas
@munevver_ertuncccc Yep thats one of the biggest reasons we created kanwas. For ourselves first. Its very easy for context to get out of date. But if you can see it, iterate on it and have a smart agent that gardens it output of your LLMs becomes 10x better
Kanwas
@munevver_ertuncccc I agree, that is definitely one of the things that we want to focus on a lot. AI is still not in the phase of taking care of it on its own, and on the other hand teams don't have time to manage and update it, so we are trying to find a balance of keeping people in the loop by making agent support this flow, until we can bet on the complete solution from ai side
Kanwas
@munevver_ertuncccc Yes, “living” i think is the keyword for us. Context that compouds as you use the tool, and context that is actually useful, because Kanwas agent and other AI agents can tap it easily.
as a solo founder, my 'team' is mostly just me and a handful of agents. keeping the context consistent across all of them is a full-time job. kanwas feels like it could save me hours of 're-explaining' the product vision to my dev and marketing agents. awesome @johancutych
Kanwas
@vikramp7470 yeah like having the whole thinking in one space where it's accessible by both humans and agents is like super power. you do better decisions + you go faster
Kanwas
@vikramp7470 I often use Kanwas for solo work too. The canvas interface is so much better than antyhing i have running locally. Also the CLI is a great way to give my AI agents a place to give me visibility into what is going on and share their output.
Kanwas
@vikramp7470 exactly! the best part is that you can still use your coding agents to pull the context and let it work on top of the same context rest of the agents have.
Kanwas
@vikramp7470 Yep the cool thing about kanwas is that we build on native filesystem files. So its very easy for coding agents to work with. Exporting and importing can be done with a simple CLI tool.
FineCam
I have tried to make this work with Claude chats, Notion pages, GitHub issues, and random docs. The issue is not creating content, it is keeping context usable after the first session. Kanwas seems pointed at that exact gap.
Kanwas
@isratjahan17 Yeah. We want to solve this problem in a comprehensive way once and for all. Automatically updating context that you can verify and edit. Not just a blob of 300 documents you have no idea what to do with.
Kanwas
@isratjahan17 the best context is tight and nuanced + compounding!
Kanwas
@isratjahan17 Exactly! Kanwas the single "home" where the team and agents can work, collaborate and store the results.
Kanwas
@isratjahan17 Thank you Israt, that is what we are trying to solve, to give you the ready system out of the box, while having it collaborative
How opinionated is the agent? Does it mostly organize what is already there, or does it push back on assumptions and ask questions too?
Kanwas
@cam_eddy we've two modes, Direct that is behaving similar to coding agents, executing.
but the mode that I love the most is "get my brain going", it's made to ask you a lot of questions so it really gets your brain going and makes the outputs sharp thanks to your taste and judgment
Kanwas
@cam_eddy We are really trying to do something different. Most AI tools will just produce more more and more output. We want to focus on quality instead. Output less, ask more and really think with the user.
Kanwas
@cam_eddy Interesting question Cam! As @johancutych already said we support 2 modes, but regardless of that you can update main instructions and your style and way of working to be more push back oriented
Kanwas
@cam_eddy The agent is something we have invested a lot into. It's opinionated, for example it asks a lot of targeted questions to get as much "soft" context that isn't yet captured to help you make good decisions. Being epistemologically honest and working well with assumptions is something we see as the biggest problem of todays AI agents and we are working on every day to improve.
This is for sure worth looking into. What I worry about is the space getting overfilled with content which becomes irrelevant over time. How do you plan to solve this issue?
Kanwas
@josip_herceg Good to see you here Josip! yeah that's a real issue, and we are bringing more schedule tasks soon so you can easily setup agent to run linting process to keeps things clean.
the idea is to have like a gardener that goes through the context and finds things that contradicts, overlap, or are outdated and messy. Then to bring them to your attention so you can decide to weed them out or keep them
@johancutych This sounds good. That is excatly what I am hoping to see. Keep it up guys!
Kanwas
@josip_herceg Just want to mention the gardener is something I'm working on right now.
@marek_vybiral Marek that is a cool name ahahah.
Kanwas
@josip_herceg Yep thinking about this a lot. We will have something cool soon for this problem.
@predrag_ristic1 I am looking forward to it!
Kanwas
@josip_herceg can't wait to introduce gardener and other similar workflows!
@popovic_anja Again, the fact that you call it garender is so cool hahahah