Monolithic agent platforms that try to own everything will lose to composable stacks where you can swap each layer independently. I think the "Boss" orchestrator spawning specialized agents is the right call imo.
Open-source matters here because the defensible part isn't the orchestration UI, it's the accumulated process knowledge each org builds on top. Tried to map out why monolithic agent platforms are a trap: https://philippdubach.com/posts/dont-go-monolithic-the-agent...
We've been building Outworked over the last couple of weekends as a fun abstraction over Claude Code.
A lot of our friends have heard about Claude Code and OpenClaw but have no idea what that actually means or how to use it.
Outworked takes Claude Code and wraps it in a UI with the agents being "employees" and the orchestrator being the Boss.
Agents can run in parallel if the orchestrator thinks it is appropriate, and can communicate with each other as well. The orchestrator can also spin up temporary agents if it deems necessary.
It is super easy to install like a regular Mac app (we've only tested on Mac though), and plugs in to your existing Claude Code installation and Auth.
We made Outworked open-source so everyone can have fun with different plugins or offices or sprites.
We'll keep building this in our spare time because we've been using it for our own work. Would love to hear what you think or what would be interesting to add.
Happy building!
P.S. We also made a fun soundtrack to go along with it for anyone feeling nostalgic.
Love this idea. I wonder, does it work well? I haven’t messed much with this persona-based agent stuff.
I’ve always heard “just tell it to be a senior dev, then ask it to do something and it will give you better output”, is that true in the experience of anyone? Genuinely curious.
This seems like that but taken to the next level with different personas wrong together and with an interface to see them work together, which is fun at the surface but is it actually better than just asking an agent to do something?
Thank you for this, it's a great point. Telling it to “be a senior dev” helps a bit, but it’s still just one stream of thinking. What’s been more useful for us is splitting work into roles like risk analyst, comedy writer, UX researcher, sr. dev etc... so there’s some back and forth.
Giving each agent a different prompt or personality activates different parts of the model, which we have found tends to produce better results than asking it to handle everything at once.
What we’ve built is an intuitive way to approach this by breaking work into distinct tasks.
Sometimes one agent is enough, but the multi-agent setup really shines on larger/messy problems.
It’s still early and we’re figuring it out as we go. Really appreciate the comment, thanks again!
Monolithic agent platforms that try to own everything will lose to composable stacks where you can swap each layer independently. I think the "Boss" orchestrator spawning specialized agents is the right call imo.
Open-source matters here because the defensible part isn't the orchestration UI, it's the accumulated process knowledge each org builds on top. Tried to map out why monolithic agent platforms are a trap: https://philippdubach.com/posts/dont-go-monolithic-the-agent...
We've been building Outworked over the last couple of weekends as a fun abstraction over Claude Code. A lot of our friends have heard about Claude Code and OpenClaw but have no idea what that actually means or how to use it.
Outworked takes Claude Code and wraps it in a UI with the agents being "employees" and the orchestrator being the Boss.
Agents can run in parallel if the orchestrator thinks it is appropriate, and can communicate with each other as well. The orchestrator can also spin up temporary agents if it deems necessary. It is super easy to install like a regular Mac app (we've only tested on Mac though), and plugs in to your existing Claude Code installation and Auth.
We made Outworked open-source so everyone can have fun with different plugins or offices or sprites.
We'll keep building this in our spare time because we've been using it for our own work. Would love to hear what you think or what would be interesting to add.
Happy building!
P.S. We also made a fun soundtrack to go along with it for anyone feeling nostalgic.
Love this idea. I wonder, does it work well? I haven’t messed much with this persona-based agent stuff.
I’ve always heard “just tell it to be a senior dev, then ask it to do something and it will give you better output”, is that true in the experience of anyone? Genuinely curious.
This seems like that but taken to the next level with different personas wrong together and with an interface to see them work together, which is fun at the surface but is it actually better than just asking an agent to do something?
Thank you for this, it's a great point. Telling it to “be a senior dev” helps a bit, but it’s still just one stream of thinking. What’s been more useful for us is splitting work into roles like risk analyst, comedy writer, UX researcher, sr. dev etc... so there’s some back and forth. Giving each agent a different prompt or personality activates different parts of the model, which we have found tends to produce better results than asking it to handle everything at once.
What we’ve built is an intuitive way to approach this by breaking work into distinct tasks.
Sometimes one agent is enough, but the multi-agent setup really shines on larger/messy problems.
It’s still early and we’re figuring it out as we go. Really appreciate the comment, thanks again!
[dead]