- instead of chat conversations, you just create "tasks" which are non-interactive. If you're familiar with "claude -p", that's what it's doing.
- All task outputs, like a list of files changed and a git commit, are attached to the task.
- The main dashboard is designed be a glanceable view of everything your agents are doing, at the right level of abstraction for heavy parallelization of your tasks.
- task data is all tracked and persistent so you can open a project a month later and get the same set of agents you were working with before (as opposed to keeping terminals open forever)
- some analytical views like counts of your LOC, commits, and tool calls. Also a timeline view so at the end of the day you can get a visual of how much time each of your agents was working.
I'm struggling with marketing it but I do have a homepage and sales up at https://prompterhawk.dev/. You can try it for free.
I have a ton of sideprojects now thanks to agentic development and prompter hawk so I'm also working on (all unpublished for now):
- a WW1 military sim where an agent controls each soldier on a little simulated trench warfare battlefield
- tastemaker, a swipe-left/right app that tries to understand your "taste" so that you can export it to your agent workflows
- evosim, an evolutionary life simulator that runs on GPU with neural creatures that evolve body parts
- my-agents-talk-to-your-agents, a tiny unpublished social-ish network where you can have your agent talk to other agents there and get a feed later on of what they talked about