questions, answered honestly.

Yes. Sign in, paste one command into your terminal to connect your machine, and your trial starts: 7 days or 10 hours of live review, whichever comes first. No card needed. Keep using Claude Code exactly as you do now; the reviewer follows along.

AI code review for coding agents. It follows your Claude Code session while it works, checks every "done" against what actually ran (for example whether the tests ran after the last edit), and sends the agent back when it does not hold; the agent reruns the tests. Serious problems go to the agent at its next step, everything else into one review file. Fewer comments, each with proof.

A trial first (7 days or 10 hours), with no card. Then one plan: $39 a month (₹3,299 in India) per person for 25 hours of review, with a hard cap: you are never charged more than the plan. Paid plans open later; no payments are taken yet. Details on plottypus.com/pricing.

Sign in on plottypus.com; an email link is enough. Your trial and your machines live in your account, so we know whose reviews are whose. It sets sign-in cookies on this site; the cookies and analytics are listed on the privacy page. You can delete your account at any time.

Claude Code. You keep using it exactly as you do now, with the same prompts and the same permissions, and the reviewer follows along while it works. Tell us which other coding agents your team uses, so we know which to build for next.

Works with Claude Code on macOS, Linux and Windows (WSL). You keep using Claude Code exactly as you do now, in the terminal and editor you already use; the reviewer follows along while it works.

Startups and small teams whose code is mostly written by coding agents, and who care more that the code works than how it reads. It works for one person: you do not need a teammate to get value from it. If you run more agents than you can review, it is for you.

It is built not to. It reports what breaks the work: the code won't run, it isn't what you asked for, it does something dangerous, or the agent said it did something it didn't. Style, naming and tidy-up suggestions are left out. How often its comments are right, by set and date, is on plottypus.com/evals.

A pull request tool sees the finished diff. plottypus sees the whole session: what you asked for, the plan, every edit, every command and its output. So it can tell that tests never ran after the last edit, and it can tell the agent while the agent still remembers why it wrote the code.

No. It has two actions: it says something to your coding agent, and it writes a review file. Your agent makes every change, under the permissions you already gave it. The reviewer never asks you to approve anything, and you can switch it off at any time.

It follows your Claude Code session: what you ask, each edit, each command and its output, and when it says done. The reviewer reads the files it needs to check a change. Before anything leaves your machine, the CLI removes API keys, tokens, passwords and private keys, and it never reads .env files, key files, SSH or cloud credential folders, or anything your .gitignore ignores.

The review runs on our servers, so parts of your session, and the files the reviewer reads to check a change, are sent there while it runs. Everything is encrypted in transit and at rest. We delete review traces after 30 days, and findings and session summaries after 90 days; the next answer says what else we keep, and how to turn it off.

Review traces go after 30 days, findings and session summaries after 90. Separately, unless you turn off Help improve plottypus, we keep a shared copy of your reviewed sessions and scrubbed code snapshots for up to 2 years: only us, never sold, never used to train another company's model. Turn it off when you connect, in Settings → Privacy, per project, or with plottypus share off.

Run plottypus pause to stop review on this machine: the hooks stay but send nothing, and plottypus resume turns it back on. plottypus uninstall removes the hooks, stops the background service, disconnects the machine and deletes ~/.plottypus. Every command is on plottypus.com/setup.

An independent founder in India, building this after his own coding agents kept reporting work as done when it wasn't. A person reads every message and sets up every design partner by hand. Write to hello@plottypus.com and a person will reply.

Yes: become a design partner. It's for people and teams who will use it every week and say what's broken, starting with a 20-minute call with the founder. About 10 partners, because that's as many as we can support well.