plutonium.io
PricingDocs

Your customers ask. Your loop answers, acts, and tells you what matters.

plutonium.io Reactor runs AI agents for your business, on your site and in your tools, around the clock. You say what the loop should do. We run it safely, on a budget you set, and everything it collects is yours.

Get on the waitlist Try a loop Read the docs

We run the loop. You own the data.

Answers questions about Reactor from its own docs, and names the page it used.

What a loop does for you

Answers from what you already wrote

Point it at your site and docs. It reads them, keeps them current, and answers at 2 a.m. with a link to the right page. When it does not know, it hands the conversation to your team.

Catches an unhappy customer before they leave

It reads every message, files the problem, and tells your team when someone is stuck or upset.

Does the work, not only the talking

Books the appointment, qualifies the lead, files the expense, starts the refund. Anything that needs a yes waits for your team to approve it.

Decides on its own, where you let it

On a schedule, or when an event arrives, with nobody in the chat: sort the inbox, summarise the week, act on a new order. Always inside the limits you set.

Built in

Search that understands the question. Text and semantic search over your docs, your pages and your own records, for your loops, your team and your visitors. Inexpensive enough to give every visitor a search box.

An agent loop is easy to start and hard to run. We run it.

You describe what the loop is for. We handle everything after that.

Run it yourself, and you own these problems

  • It calls a tool it should not, or the wrong one.
  • A hostile message talks it into something.
  • One busy user spends your month’s budget.
  • A prompt change quietly breaks it.
  • Nobody can say what it did last Tuesday.

With Reactor

  • It can use only the tools you grant. Nothing a user types adds one.
  • Caps per loop, per user and per run, checked before each call.
  • A new version serves nobody until its test conversations pass.
  • Every run, step and cent is on your console as it happens.
  • Hosting, models, retries and restarts are ours.
  • Your own tools and APIs plug in, and ours are there when you need them.

You own the data

Every lead, booking, ticket and answer lands in your own collections. Read them over an API, have each one sent to your webhook or your inbox, or watch them arrive on your console. A loop reads only what you give it.

How you start

  1. Describe it

    Tell LoopAssistant what the loop is for, in plain words.

    A LoopAssistant conversation on the console: asked for a page of leads, it asks which collection holds them, and the person approves the page it proposes.

  2. Check it

    Read what it will do, what it may use and what a run may cost. Try it before anyone else does.

    A published loop on the console: what runs now, what a run in this version is told, and the capabilities every run holds.

  3. Put it live

    A chat on your site, or your own app over our API. Watch every run from your console.

    A run on the console: the loop's first reply to a prospect, and what that turn cost, $0.0004.

Get on the waitlist

We’re opening Reactor to a few teams at a time, and we add each one by hand. Tell us where to reach you, and we’ll email you when your account is ready.

You’re on the list

We add people by hand. When your account is ready, we’ll email you, and you sign in with Google at that address.

One moment…