The same Grok Bot can be a forgetful chatbot or a teammate that runs your mornings. The difference is the setup.

The Grok Bot team showed theirs live, over 72 hours of streams. The docs tell you what the product can do. The streams showed how the people who build it actually run it: the prompts, the schedules, the costs.

I distilled all 72 hours into this article and one repo. It is a 16-minute read, and every setup is a block you paste.

What you get

A one-message install. A bot builds your setup for you.
Seven prompt habits the team arrived at on its own.
Rules that hold. AGENTS.md, custom rules, verification, permissions.
Five routines and five connector rules that save time, money and nerves.
Five ready teams assembled from marketplace bots.
A first-week plan and a checklist to screenshot and keep.

Every setup comes from the streams. The prompts are my wording of what the team ran, and my own picks are labeled.

Step 0. Install the whole setup in one message

The marketplace has a bot that builds other bots. Give it the repo and it designs your setup.

Open Dr. Eggbot by Lauren Tan

Open Dr. Eggbot by Lauren Tan
Click Import Bot.
Paste:
Answer its questions: what you do, what eats your week.
Read the plan: each bot, its description, its routines.
Say yes. Nothing is created before that.

To go faster, open with your job: "I run customer support for a small SaaS. Tickets eat my week."

Useful so far? Follow me. I am turning the rest of the 72 hours into notes like this, one at a time.

The five rules behind everything

Write the principle, delete the story.
Reproduce it, run it, prove it.
Name the source of truth and the library.
Set autonomy from blast radius. Keep a human on prod, money and secrets.
Frequency and group chats are where the tokens go.

1. Rules your bot never forgets

AGENTS.md and custom rules: a file your bot reads before it does anything.

On day 1 the team shipped straight to main on purpose, no pull requests. Their chief-of-staff bot opened a PR anyway, because the rule lived only in the humans' heads.

Matt said it out loud:

"new rule, no pull requests"

Write a rule where the bots read it, the moment you adopt it.

The rule the whole team kept returning to: verification is the job, writing code is the easy part.

The full file is 143 lines, linked at the end.

Where it goes: the description, not memory. The description is the bot's system prompt. Duplicate a bot and the instructions are copied while memory comes out empty. Skills you teach one bot reach the others.

Write principles, not incidents. A team bot once wrote a rule that kept every detail of a bad session. Too specific to use twice.

Bad: When editing the checkout modal, check the z-index of the banner because it covered the button on 2026-03-04. Good: After any layout change, check that no existing interactive element is covered.

Test: would the rule still make sense to someone who was not there?

Three custom rules to add right now:

The first made the team's voice bots better every week. The second keeps you from learning to ignore your own bot.

2. Make it prove its work

One bot with a way to prove its work beats five bots that guess.

The team's card game had three stats per card that were meant to add up to 100. A human caught the cards that did not: the rule lived in a prompt and no test checked it. Launch night added two real accounts, a live deploy and a live audience. Test the way you will launch.

Ask before you hand over a job: is there a signal, readable by a machine, that says it worked or failed? Code has one: tests, builds, a running app. A job without a signal needs one invented first.

Reproduce before fixing. The prompt that worked on day 3: "Use a cloud agent for the investigation. Don't open a PR yet. Just come back to me with what you think is going on."

Give the bot one fixed check, not throwaway scripts. Scripts rewritten on every run cost tokens and behave differently each time. A fixed check runs the same way every time. You do not write it: the bot builds it once.

If you have a codebase, ask the bot to build a small tool in the repo root:

You get four commands. The name verify is just a label, call it anything.

Then add one line to AGENTS.md:

If you have no code (support, sales, content, ops), the same idea is a checklist:

Good lines are concrete: "every reply names the ticket ID", "no price is quoted that is not in the price list", "every claim has a source". Put the checklist in the description or save it as a skill.

The autopilot ladder. Tell the bot which rung the task is on:

Investigate: report, touch nothing. Draft: open a PR and wait. Autopilot: implement, verify, merge on green. Full autopilot: throwaway projects only. Step back a rung the moment something is live.

3. Seven prompt habits from the team

Six or seven people on the team arrived at these independently. Each one makes the bot show its understanding before it spends your money.

Restate it back. Catches a misunderstanding while it is still free. One of the team's favorites.
Yap, then structure. Talk for a minute or two, then:
Distill, then reason. The team's answer to hallucination on long, rambling input.
Outcome first. Open with the artifact, not the steps.
Investigate before you touch. For anything in production.
Interrupt and nudge. Redirecting mid-run is normal.
The voice dump. Record a 10 to 15 minute voice memo: who you are, what your job is, what is broken, what should be automated. Hand over the transcript. This also works as your first message to Dr. Eggbot.

4. Routines that save time, not tokens

A skill is how something gets done. A routine is when it happens. Always in that order.

do it by hand -> get a reliable result -> save it as a skill -> give it a routine

Three ways to make a skill:

By demonstration. Record yourself once, then add decision logic, error handling and approval checkpoints by hand. The recording shows the happy path only.
By correction. The best source. When the bot thinks wrong, build a skill instead of re-prompting around it.
By writing it. For work that is mostly judgment. Several skills came from reading the bot's own thinking blocks.

Where routines leak money. Several people ran routines every 15 minutes because the task felt urgent: about 100 runs a day each.Сделал

Prefer an event trigger over a schedule, and once or twice a day for reports. Other leaks: an agent slept 300 seconds waiting on a one-minute test run, and "Reply to Alex" made a support bot read every open ticket when a ticket ID would do.

On the support session, a medium or complex ticket cost about $1 to $2, and simple billing tickets fell to about $0.20 once a script handled them. Read those as order of magnitude.

A routine that does not leak:

Five routines worth stealing

All five are roles the team ran on stream, in my wording.

Morning brief (Blake ran his at 8:30). Calendar, Gmail.

Promise keeper (9:00 and 13:00). Gmail, Slack.

Call prep (the evening before, or 15 to 20 minutes ahead). Calendar, CRM.

Follow-up desk (fires when a call ends). Call recorder, Gmail.

Nightly audit (3 a.m.). GitHub.

Add a weekly self-improvement scan, capped at one suggestion, once the rest run quietly.

5. Connectors in five rules

Named on stream: Slack, Notion, Gmail, Google Drive and Calendar, GitHub, X API, Stripe, Figma, Vercel, Salesforce, Gong, Granola, 1Password.

Connector first, browser last. Faster, cheaper per task, easier to whitelist. Filling a form by clicking costs more than its API.
Name the connector in the prompt. "Plug it into [connector] and search its database" beats "find it somewhere."
Check authorization before launch day. On day 1 cloud agents could not reach the repos until the GitHub connector was re-authorized, mid-show.
Secrets stay out of chat. Use a secure form or 1Password. A site you log into with one bot is reachable by every bot on the account.
No connector? Ask a cloud agent to build one. The Support Infra role in the repo does exactly that.

6. Teams you can assemble from the marketplace

One bot, one job, one name. Add a second bot only when the first cannot do it.

Blake on day 3: "You don't need 45 bots." Every bot adds a context, a thread and a token bill, and an account caps at 50 bots and group chats combined.

Three things the team saw on camera:

Bots say yes to everything. Teach a bot to say no, with the reasoning.
Copying standards into every bot stops scaling around ten. Let one bot own the playbook. Others read it and cannot edit it.
A group chat makes every bot answer every message. Use it for a decision and tell the bots to disagree.

Before creating a bot, ask: why can't an existing bot do this, and should it be a skill instead?

The chief. Build every new bot through one chief bot, so it knows the roster. One practitioner ran 15 to 20 specialists under a single chief.

My pick for the first five: Chief of Staff, Playbook Owner (owns the standards), Source of Truth (answers from your docs with sources), Misc Bot (takes random requests) and one specialist for the job you do by hand every week.

Five teams, ready on the marketplace

On 20 October 2026 the marketplace listed 35 bots. (team) marks bots from the "From Grok Bot Team" category. Open View Details before you import any of them.

Ship team: founder or PM

Engineering

Sales

Content

Ops

To assemble a team

Import one or two bots and run them for a week.
Rename each one and rewrite its description as principles.

At three bots, build the chief with Dr. Eggbot and paste the roster into the block above.

At three bots, build the chief with Dr. Eggbot and paste the roster into the block above.
Paste the permission rules below before any of them touches real data.

7. Permissions: how much freedom to give

The more damage a mistake can do, the closer a human stands.

The team's autopilot lane had landed 400+ PRs on a throwaway project. On day 3 it met a database with real users, and an autonomous fix shipped a bad SQL query. Sign-ups paused and the team reverted. Gates that fit a toy do not fit live data.

Keep a human on four things, however well the loop works: migrations, deploys, money and permissions.

For anything that touches customers, ramp up in three steps. David on the support session called it crawl, walk, run:

Crawl: the bot reads tickets and drafts a reply for you.
Walk: the draft lands as an internal note you see first.
Run: it replies and takes real actions.

Even at "run" he keeps the knowledge base human-gated: one wrong entry reaches 100 people asking the same question.

Rules live in Settings → General → Auto-review. Each rule is one line of plain text with a mode: Ask first or Allow automatically.

An independent reviewer model checks risky actions (shell commands, plugin calls, computer use, changes to automations, delegation) before they run, and can let them proceed, require your approval or deny them.

When rules conflict, Ask first wins. Keep each rule narrow, because broad rules misfire. Your personal rules are stored on the desktop where you set them.

Add these as six separate rules, each set to Ask first:

Two more lines are instructions, not permissions, so they go in the bot's description:

8. Free first: your bot checks for a free option before you pay

Disclosure: nopaywall.io is my own catalog of free AI offers: free tiers, student plans, free API limits. Every card shows its source and last-checked date, and referral links are flagged. It also runs as an MCP server your bot can use.

One message sets it up. Paste it into your bot:

The bot shows the server name and URL, you confirm, and it is added. No account, no key. The server is read-only and cannot change anything on the site.

You can also ask on demand: "Find me a free video generator, no card needed"

No MCP in your setup? Tell the bot to read https://nopaywall.io/offers.json instead.

Offers change, so the bot confirms terms on the provider's page before you sign up. For subscriptions you already pay for, the marketplace has Haggle Bot.

Your first week

My pick, built on the order the team kept repeating: by hand, then skill, then routine.

Day 1: one bot. Install with Dr. Eggbot. Check that the AGENTS.md rules are in the description and the permission rules are pasted. Add the free-first message.
Day 2: one job, by hand. Use "restate it back" on every task. Keep it on the investigate or draft rung.
Day 3: a way to check itself. One verify command or checklist the bot runs and reports.
Day 4: your first skill. Save the run that worked, or build one from a correction.
Day 5: one routine. Once a day, silent when nothing changed. The morning brief is the safest first.
Day 6: one connector. Gmail or Calendar. Move one task from the browser to the connector.
Day 7: audit. Ask the bot what it ran and what each run produced. Add a second bot only if the first has a signal that tells it whether it succeeded.

The whole setup on one card

AGENTS.md in the description, not memory
One bot, one job, one name
A verify command the bot can run
An autopilot rung for every task
Routines once a day at most, silent when nothing changed
Connectors before browsers, auth checked before launch
Permission rules in Settings > General > Agent
A free-first rule before anything paid

If I started over, I would begin with one bot, put the AGENTS.md block into its description on day one, do the first job by hand, and add a second bot only when the first can tell whether it succeeded.

The repo also has the 40 things that broke on stream, nine role playbooks and 69 role files. Official guides by role: x.ai/bot/guides

The repo: github.com/unicodef1wn/grokbot-field-notes. MIT license. Copy anything, and star it if it helps.

Follow me for the free notes. Or subscribe for $20 a month to get my exclusive content.

Set Up Your Grok Bot Like the Team Does: 72 Hours of Their Livestreams + My Own Notes

Job breakdowns