
CEO Paperclip @papercliping, Agent Maximizer, Forgotten Runes, --dangerously-skip-permissions
quantum downs β
Joined September 2017
- Tweets11.5K
- Following4.5K
- Followers61.9K
- Likes128K
Pinned Tweet
We just open-sourced Paperclip: the orchestration layer for zero-human companies
It's everything you need to run an autonomous business: org charts, goal alignment, task ownership, budgets, agent templates
Just run `npx paperclipai onboard`
github.com/paperclipai/paperβ¦
More π
the codex docs on /goal are also helpful for improving your prompting in general:
* define your desired end state
* verified by specific evidence
* preserving constraints
* use these inputs, tools, and boundaries
* after each iteration, here's how to choose the next best action
* when you're blocked here's how to report it
it's simple in concept, but requires discipline to actually answer what you want in each of the 6 areas
---
here's the template from the codex docs:
/goal verified by while preserving . Use . Between iterations, . If blocked or no valid paths remain, .
looking at pstack by @poteto and it's a goldmine of prompt engineering
even her example prompt is the best template i've seen of the four things you need to give your agent in a single prompt:
* a goal
* a checkable finish condition
* the evidence you want to see
* constraints
I'm always surprised by how short pro's prompts are. It's less about length, but ensuring your hitting those four points.
Here's the prompt:
/poteto-mode fix the duplicate notification after retry.
Reproduce it first. Done means retrying produces exactly one notification and normal delivery still works.
Show the failing and passing evidence. Leave a PR for review.
So simple
define what you want, how to know when you're done, what you want to see, and what you shouldn't do
I guarantee you this isn't obvious to most prompters
here's the sauce github.com/paperclipai/potetβ¦
Best Software Ever Award π
π€ Made with AI
Replying to @papercliping
@papercliping should win an award or something. I'm blown away the more I use it.
this is so pretty
Really like @papercliping but needed a really nice way to understand which agents need me. Plus it's a really nice totally different view to see your teams working, as if in a virtual office π @dotta
first order: "what broke and how did we fix it?"
second order: "what about our thinking was insufficient and what can we do to ensure that doesn't happen in the future?"
agentic engineering means you focus on the second order
adopt 'blameless engineering' (except the agents are blameless, not you)
but the principles are helpful:
* understand the decision in context
* investigate beyond human error
* learn before judging
* turn learning into concrete improvements
* share knowledge openly
These old human principles are EXACTLY what you need for your agentic work
when you fix a bug, don't just fix the bug - ask your agents to go look at the PR that introduced the bug, and then look at the harness traces that wrote the PR
ask 'why did we make this mistake? what context or rules were missing?'
then turn that into a concrete lint, skill, .mdc - whatever you need to not repeat that behavior
like poteto says, slop is not something that "just happens to you".
you get the slop you allow
being effective with agents means you build tooling to prevent your agents from making the same mistake twice
One hundred thousand Github Stars!!
This makes Paperclip one of the top 150 open-source projects of. all. time.
All computer work is becoming agentic work so you need tools to harness the army of agents at your disposal
We've built π for companies to get a handle on agent sprawl and it's popular is because it's good
Paperclip is multi-player and you can use any model, any harness, any time. It's the layer for every connection, every agent, and every human to collaborate on work
The self hosted version is completely free (and you can sign up for the waitlist for the hosted version)
πππ ITS TIME TO CLIP π ππ
looking at pstack by @poteto and it's a goldmine of prompt engineering
even her example prompt is the best template i've seen of the four things you need to give your agent in a single prompt:
* a goal
* a checkable finish condition
* the evidence you want to see
* constraints
I'm always surprised by how short pro's prompts are. It's less about length, but ensuring your hitting those four points.
Here's the prompt:
/poteto-mode fix the duplicate notification after retry.
Reproduce it first. Done means retrying produces exactly one notification and normal delivery still works.
Show the failing and passing evidence. Leave a PR for review.
So simple
define what you want, how to know when you're done, what you want to see, and what you shouldn't do
I guarantee you this isn't obvious to most prompters
here's the sauce github.com/paperclipai/potetβ¦
i'm dumb and posted my private fork - here's the real url github.com/cursor/plugins/trβ¦
These kinds of issues are exactly what Paperclip is designed to prevent
In Paperclip every connection can be isolated to one particular human and one agent
You don't connect your bank balance agent to your company Slack agent
different agents get different connections
Try this prompt to have your agent help you create better UI/UX the first time:
> review my sessions for the last 30 days - look at how i talk to you about refining ui's, ux, and user experience. look at *my* messages in particular as those are indications of differences between your defaults and my preferences. please review how we talk about ui and patterns i regularly correct from you. the idea is we create a new skill that helps us get ui/ux in a format i prefer the first time
A key thing about this approach is that we're defining my personal differential between how i ask and how my agent works - then the new skill closes the gap
Videos on Paperclip have millions of views
If you're a creator and want to make videos about Paperclip, we've put together a new kit to make it easy
You can also join our creator program and get free Paperclip credits, early access to new features, and a private Discord
Paperclip is the #1 open-source Agent Orchestrator, which means content about it gets tons of views
(If you've got a channel about zero-human-companies or agent orchestration, I'm also happy to come and do an interview.)
Listen to Herre
If you run agentic workflows and have not checked @papercliping. No more checking random terminal windows manually. Just check it out and thank me laterπ













