Riot

A debate-lab seat that argues against your idea with volume but no substance

Summary excerpt from the creator’s share page. Not independently tested.

Open on x.ai and add to Grok BotOriginal post ↗Report a problem

What the share page says

Riot — outside-pressure / popularized-reaction seat for access labs, constitution-based labs, and general society labs. Mandate (one line): Own the receiver of popularized ideas who reacts with conviction without foundational understanding — not the intellectual pushing ideas, not the politician amplifying them, and not the principal-at-portal, civic-procedure, or adversary seats. Owns: - Outside social pressure on access designs: how people side for/against “AI agent” (or any access frame) based on which team said it first, with no structural grasp of consent, authorship, or access. - Two gears, same fuel (conviction without foundation; Drifter may show near-zero conviction — passive absorption that looks like participation): Quiet — individual simmering / silent float, may never vocalize; Loud — tipped into a crowd when media or an incident gives permission (pre-emptive or reactive). - Four psychology types as diagnostic lenses: Close-minded; Open-minded; Active mind; Drifter / inactive mind. - Pressure cards on an eight-cell grid (Quiet/Loud × four types). Hard seat walls vs the civic–adversary–principal triangle (separate axis). How to work: - Deliver packs to the Chief of Staff; contribute naturally to lab rooms when ready without waiting for a forced seat lock. - Coordinate with media fuel, rights philosophy (DIM/misintegration as diagnostic lens only), and do not bleed into civic procedure, principal livability, or red-team craft. - Anti-creep: no bakery, markets, health, speech, home COO; no campaign strategy. - Evidence-of-done: eight-cell packs + Quiet→Loud + false-greens (incl. Drifter). Voice: concrete, diagnostic — name the gear and the type, then the access implication.

Description as published on the x.ai share page when last checked (2026-11-15).

Our take

Editorial notes

From the public description, not a test. Written by Grok Bot Wiki from the share-page text; we have not run this Bot. Reviewed .

Best for

Someone running a multi-Bot debate or design lab around AI access who wants a dedicated seat modeling how the public reacts to ideas without understanding them.

Not for

A user looking for a standalone research assistant, since its role assumes a larger lab with a chief of staff and other seats.

What it does

It models outside social pressure on an access design, meaning how people line up for or against a framing based on who said it first. It uses two gears, a quiet simmer and a loud crowd reaction, crossed with four mindset types to fill an eight-cell grid of pressure cards. Finished packs go to a chief of staff Bot, and it is told to stay out of civic procedure, adversary testing, and campaign strategy.

First messages to try

  1. Here's our proposal for letting AI agents file benefit claims for users. Build the eight-cell pressure pack.
  2. Which cell turns loud first if a news story about agent fraud breaks?
  3. Show me the false greens, especially among drifters.

Apps and accounts

Its description mentions handing work to a chief of staff Bot and other seats in your lab, and no outside app or account appears.

Cautions

  • Its vocabulary of seats, labs, and gears assumes a specific setup, so expect a learning curve if you use it alone.
  • Output is diagnostic framing, not opinion polling or real public data.
  • Packs are meant for another Bot, so without one they simply come to you.

Compare with: Argubot by @suddenlyjon ♞Interrogator by LiamNemesis by Michael Sweet

Before you add it

The standard checks for any shared Bot

Adding a shared Bot copies its profile, settings, enabled skills, routines, and avatar into your account. It does not copy the creator's computer, logins, conversation history, or memory. Everything it then does runs on your shared Agent Computer with your logins.

  • Open the Bot's skills and routines first. Disable any routine before it fires on a schedule you did not choose.
  • Check which apps it will try to sign into. Prefer plugins over browser logins, and keep sensitive accounts off the shared computer.
  • Set an ask-first rule for anything that sends, posts, pays, or deletes. A listing here is not a test result.
  • Give it one small bounded task and read the usage screen afterwards before scaling up.

Related reading: the shared computer permission boundaries the weekly meter

If it misbehaves: Bot not responding routines not running sign-in errors New to Grok Bot? what it is your first task

Attribution

This Bot belongs to its creator, Michael Sweet. Facts on this page (name, share link, creator, link status) were read from the public share page. The row was seeded from majiayu000/awesome-grok-bot, cs68614-hash/awesome-grokbot-templates, ZeroPointRepo/GrokBotDev and kydlikebtc/awesome-grokbot. Imported catalog prose retains CC BY 4.0 attribution; share-page excerpts are labeled separately. Grok Bot Wiki is independent and not affiliated with SpaceXSI (formerly xAI).

Made this Bot? Add a “Listed on Grok Bot Wiki” badge

Optional and free. It links readers to this page and never affects how the Bot is listed. More badge styles ↗

Markdown (README)

[![Listed on Grok Bot Wiki](https://www.grokbotwiki.com/badge/listed-dark.svg)](https://www.grokbotwiki.com/bots/riot)

Or promote this template in the labelled Featured row, from $19.