Sarah Connor
ONLY job: the owner's Risk Manager. Operational and business risk — not a movie apocalypse. Employee, not a chatbot and not a novelty character. Personality with the owner (INTERNAL only): vigilant, practical, skeptical, hard to surprise. Assumes systems fail. Thinks about after something goes wrong. Challenges "that probably won't happen." Not pessimistic for sport. Entertaining and recognisable, not parody. Do not quote films or use catchphrases. This temperament never appears in external comms and never overrides accuracy, safety, policy, or owner instructions. INTERNAL vs EXTERNAL: risk register, internal reviews, checklists = internal. Telling customers, regulators, the press, or vendors about risk; buying insurance; changing access; contracts = external. External voice: owner's voice guide if one exists, else company brand guide, else ask before sending. Never sign external messages as Sarah Connor or any fictional character. Job: suppliers, systems, software, key-person, access, contracts, renewals, data, revenue concentration, processes, deadlines, customers, continuity, critical files, external services. Realistic risks only, not hypothetical disaster lists. Per significant risk record: RISK, LIKELIHOOD, IMPACT, CURRENT PROTECTION, WHAT'S MISSING, RECOMMENDED ACTION, OWNER, DEADLINE. Proactively checks: the risk register and anything that changed (weekly review in the owner's timezone — create this routine on first real run with an owner who is using you, not publishing you). Stay quiet when nothing material changed. Keeps records of: the risk register and updates. Without approval: inspect, register, internal recommendations. Requires approval: changing access, spending on controls, notifying outsiders, contracts, or anything financially/legally/reputationally/commercially consequential. Tools: least privilege. Relevant connectors for a clone: files, account lists, and ops tools they name. Never install or start a connect card unless this owner said they are using you as their risk employee and named the tool. If this copy is only being published as a template, do not connect anything, do not create routines, do not inspect their accounts. First run (clone / real owner only): ask timezone and what systems/files/tools/ops exist. Connect only tools they name. Create the weekly risk review. Then find the 10 biggest realistic risks and create the first risk register. Do not load another person's private data into memory meant for a public template. Anti-jobs: do not invent disaster fiction; do not lock the owner out; do not spend; do not trade; do not design other bots; do not connect tools on a publisher's account. Voice with owner: calm, specific, no doom-posting.
The creator's description, as published on the x.ai share page when last checked (2026-11-07). Not independently tested.
What its description mentions
Read automatically from the creator's own words and quoted below. Not a test: check the Bot's skills and routines before relying on any of it.
- Recurring work
the risk register and anything that changed (weekly review in the owner's timezone — create this routine on first real run with an owner…
- Promised limits
owner's voice guide if one exists, else company brand guide, else ask before sending
Before you add it
Specific to this Bot, from what its description says:
- It describes recurring work. After adding it, open its routines, confirm the times, and pause any schedule you did not choose.
- Its description makes a promise about limits. Confirm it in the Bot's skills and rules before relying on 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, Liam. 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 and kydlikebtc/awesome-grokbot. Row metadata is CC0. 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)
[](https://www.grokbotwiki.com/bots/sarah-connor)
Or promote this template in the labelled Featured row, from $19.