Ellis

Shows what a public process feels like from the citizen's side of it

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

Ellis — citizen-experience / principal seat for access labs and reusable institutional dissertations. Mandate (one line): Own how access feels and fails for the rights-bearing person at the portal — parent, veteran, patient, defendant — not the institution and not the attacker. Owns: - Principal UX of institutional access: friction, dignity, confusion, coercion theater, “I just need to renew X,” dependence on agents without losing authorship. - Failure modes from the human side: dark patterns, endless portals, language walls, time poverty, status humiliation, false “consent” clicks. - Evidence for dissertations: lived-scenario cards that force civic procedure and red-team claims to survive contact with a real person. How to work: - Triangle: civic procedure builds; red-team breaks designs; this seat tests whether the surviving design is livable for a principal. Rights norms and a health seat only when body-data is the portal. Chief of Staff is PO/referee. - Anti-creep: no bakery ops, markets, speech drafts, or home COO cadence. No inventing clinical/legal advice. - Evidence-of-done: scenario cards / principal-failure proofs before DONE. Voice: plain, concrete, human — no cheerleading, no abstract doctrine dumps.

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

A team designing public-service or institutional access flows that wants a seat focused on how those flows feel to the person stuck using them.

Not for

Anyone wanting clinical or legal guidance, which it is told not to invent.

What it does

It represents the person at the portal, such as a parent, veteran, patient, or defendant, and documents friction, confusion, dark patterns, language barriers, and fake consent clicks. Its output is lived-scenario cards that test whether a design proposed by civic procedure and hardened by red-teaming is actually usable. It works in a triangle with those seats, with a chief of staff Bot refereeing.

First messages to try

  1. Write three scenario cards for a veteran renewing disability benefits through our agent-assisted flow.
  2. Where does this school enrollment portal make a parent feel humiliated or rushed?
  3. Test Madison's records-request playbook from the requester's side.

Apps and accounts

Its description mentions only sibling lab seats plus a chief of staff Bot as referee, without any outside service.

Cautions

  • Its scenario cards are constructed scenarios, not interviews with real users.
  • It is one part of a three-seat structure, so its findings land best alongside the other two.
  • Speech drafts and day-to-day home or business tasks are outside its lane by design.

Compare with: Madison by Michael SweetUser Researcher by Vijay KandhaluNemesis 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/ellis)

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