←
dotta 📎11,489 posts
dotta 📎 avatar

dotta 📎

@dotta

CEO Paperclip @papercliping, Agent Maximizer, Forgotten Runes, --dangerously-skip-permissions

◷ Joined September 2017▧ 1,700 Photos and videos
dotta 📎 avatar
dotta 📎@dotta·Mar 4

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/paper… More 👇

0:27
dotta 📎 avatar
dotta 📎@dotta·5h

“Fable, use all the power you have right now to create a video that makes people smilie using the Cliptoons from Paperclip (with Blender and Python)”

0:47
dotta 📎 avatar
dotta 📎@dotta·Nov 11

It's real: you can ask Fable 5.2 to create a 90's cereal commercial in Blender and it works and it's good Paperclip Crunsh: All part of a zero-human breakfast

0:20

Thanks for the feature, @claudeai! Fable 5.2 made this '90s cereal commercial, all drawn in code

1:04
Franky. avatar
⟳ dotta 📎 retweeted
Franky.@FrankYouChill·Nov 9

A snapshot of the open-source agent development stack.

Post attachment

Tier list are fun, but how about a snapshot of the agent stack instead? What did I miss

Post attachment
dotta 📎 avatar
dotta 📎@dotta·Oct 28

Github put Paperclip in the top-10 most-engaged open-source repos for the 2026 alongside Hermes, OpenCode, Pi, and VSCode Pretty good company

Post attachment
dotta 📎 avatar
dotta 📎@dotta·Oct 23

Canary in the coal mine

Grok@grokOct 23

In this context, canaries are low-value trap assets mixed into your real secrets. You plant crypto private keys holding about $20 alongside sensitive data. Any thief who steals the secrets will almost always drain those funds right away, giving you an instant alert that a breach occurred—just like a canary in a coal mine.

dotta 📎 avatar
dotta 📎@dotta·Oct 23

Probably a good idea to put $20 in crypto private keys with your secrets as canaries If your secrets are compromised almost any hacking agent will steal the funds immediately

dotta 📎 avatar
dotta 📎@dotta·Oct 15

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 <desired end state> verified by <specific evidence> while preserving <constraints>. Use <allowed inputs, tools, or boundaries>. Between iterations, <how Codex should choose the next best action>. If blocked or no valid paths remain, <what Codex should report and what would unlock progress>.

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/potet…

dotta 📎 avatar
dotta 📎@dotta·Oct 14

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 😁 @dotta

0:37
dotta 📎 avatar
dotta 📎@dotta·Oct 13

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

dotta 📎 avatar
dotta 📎@dotta·Oct 12

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 📎 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) 📎📎📎 ITS TIME TO CLIP 📎 📎📎

0:11