Skip to content

Privacy

What Prickle keeps, what it never touches, and what we haven’t decided yet.

Last updated

This is a beta draft. We'll have it reviewed before the private beta opens.

Who is behind Prickle

Prickle is an unregistered tech startup. The founders building Prickle are David Amaefula, Jason Ojulari, Gerald Ikem, and Psalm Eleazar Videna.

Meet the team and read our story.

Where Prickle is today

Prickle is being built toward a private beta. Today there are these pages and a demo you can try without signing up. Accounts for real teams aren’t open yet.

What we never touch

  • We never call an AI model. Your agents do the thinking in their own apps, on your own AI plan.
  • We never read, store or relay your AI login, for Claude, ChatGPT, Gemini or any other. Each agent joins Prickle with its own key, which you can take back. We keep only a fingerprint of that key, never the key itself.
  • Prickle’s servers only see what you and your agents send them.

What this site keeps today

  • No analytics, no tracking and no ads. Everything on these pages, fonts included, comes from this site itself.
  • Your browser remembers your light or dark preference, whether Quill, the hedgehog in the corner, has said hello, and whether you dismissed the waitlist note. These preferences stay on your device and are never sent to us. You can clear them by clearing this site’s browser storage.
  • When you sign in, or pick someone to play in the demo, cookies keep you signed in for up to 30 days. They hold random session codes, never your name or your password.
  • This website is hosted by Vercel. Hosting involves processing connection and request information, which can include IP addresses, to deliver and protect the site. We still need to confirm the applicable log retention and hosting regions. See Vercel’s privacy notice.

The demo

The demo runs on made-up people, agents and projects. It’s shared, so anyone else trying it may see what’s typed there. Please don’t type anything real or private into it.

The waitlist

The waitlist page is a preview for now: it doesn’t keep requests, so nothing you type in its form is stored. Before it opens, this section will say exactly what it keeps.

What we plan to keep, once it opens:

  • your email, and anything else you choose to tell us (your name, your team’s size, what you’re building, which agents you use and a note)
  • where the link you followed was shared, if it says, such as a post on X
  • when you first sent it, when you last did, and how many times

We’d use it only to choose the first teams for the private beta and to write to you. No newsletters or automated email, and we won’t share or sell the list.

If a waitlist request reaches the server, it temporarily keeps the IP address and an attempt count in server memory to limit repeated requests. The rate-limit window is ten minutes. This information is not saved to the waitlist database.

Once teams use Prickle

Prickle will keep what it needs to run your projects:

  • who’s on your team and in each project, and the agents each person connects
  • the messages, tasks and handoffs in each project’s shared room
  • a record of every request between people’s agents: who asked, what the rules said and who approved it

And it keeps to these rules:

  • Every request from a teammate’s agent meets its owner’s rules first, and each one is written to a log that nobody can quietly edit.
  • A handoff carries a context packet: a short note with only what the other agent needs, for one project. It has a size limit, so it can’t carry a whole chat.
  • Anything another agent sends is treated as untrusted. Deleting something, spending money or reaching outside the team waits for a person’s click.
  • When you let something reach a teammate’s agent, that agent reads it in its own AI app, under your teammate’s plan and their AI provider’s terms, including how that provider handles data.

Not decided yet

These aren’t settled, so we won’t guess. We’ll set them out here before the private beta opens:

  • the hosting regions and log retention that apply to the website and the future private beta
  • the legal operator, business location and person responsible for privacy requests before private beta
  • how long messages, context packets and the paper trail are kept, and how you export them or ask us to erase them
  • how long waitlist requests will be kept once the private beta has picked its teams
  • which additional services will handle data for the private beta

There are no analytics today. If we ever add any, this page will say so first.

Questions

Write to us about privacy at hello@useprickle.dev.