How I Use Grok Bot as One Ops Desk

I run Grok Bot as a single coordinator desk with named specialist agents, not a swarm. This page is the public playbook for setting those agents up, and the canonical roster of the desks that exist today.

If you are a teammate, start at First hour if you are a teammate. I am not your VA.

First hour if you are a teammate

This page is my playbook. If you just got Grok Bot, do not wait for me to click through it with you. Use your own account. I am not your VA.

1. Start at x.ai/bot on your own account. First use any Cursor access you already have: Pro+, Ultra, and self-serve Teams include Grok Bot; Cursor Pro does not. Sign in with the Cursor account you intend to keep. Before linking or buying anything else, check the current plan page.
2. Install Grok Bot.
3. Load the skill pack from github.com/dennisyu/local-service-spotlight-skills. Refresh from that address. Do not re-upload a zip.
4. Create one coordinator desk. Do not spin up 12 desks on day one.
5. Point that desk at this hub, the plugin page, and the article guidelines.
6. Do the first real job from the Task Library (or the BlitzMetrics Task Library). One task, then a receipt.
7. Save the process as a Grok Bot skill (when, inputs, sequence, validate, return, approval). Enable it for this Bot under Settings → Plugins if it is missing from the slash menu.
8. Test run. A test run is real work. Then create the routine on that Bot (schedule or a narrow event). View conversation details → Routines. Do not schedule a demo. Glossary: skills and routines.
9. Do not message me for each step. If a page is wrong or missing, reply with the URL and the gap.

Worked example of a desk page with can/can’t plus a receipt: IT Support.

Why this is public

I build in public. I charge for time, not knowledge. If the only copy of a workflow lives in my head, it dies with me. That’s the lesson I learned from my friend and co-founder Chris Rummel: undocumented work dies with the person.

LDT is Learn, Do, Teach. I learned Grok Bot by using it on real work. Teaching is this article.

CCS is Content, Checklist, Software. It’s the WHAT tier of 9 Triangles. This page is the Content. The numbered steps below are the Checklist. The shared Local Service Spotlight skill repository is the Software layer an agent can load; there is no separate article-specific file. The 9 Triangles checklist is the wider map.

What Grok Bot is, and what it is not

Grok Bot is the Cursor/xAI teammate on desktop and iOS. It has its own computer, named agents, routines, and connectors (Gmail, Drive, GitHub, Calendar).

Sidebar shapes are avatars, not a code. What the Grok Bot sidebar icons mean.

It is also not a second copy of the Claude or ChatGPT fleet. The methods stay in one skills repository. The facts stay in user-owned Markdown, Obsidian, or Drive. Claude, ChatGPT/Codex, and Grok are runtimes around that same core. The map for that is How we build and maintain AI agents and The System.

The 20+ agents article is the browser-tab version of the same idea. This page is the Grok Bot version: named desks you can open, not 70 tabs you have to babysit.

How I allocate the paid seats (soak included first)

I do not invent plan prices here. This is the routing map so I and the agents remember where work belongs. Money detail stays on usage-buckets.

Mail is the same map. I like chatting with the twelve Grok Bot widgets. That is the phone desk. The hall monitor that should get me to inbox zero is a Codex pass every 15 minutes, not a 300-message paste into Grok Bot. Grok Bot is the named teammate I talk to. Cursor is the workshop. Codex takes the silent homework. How a day actually runs is how I talk to one agent all day. The method lives on how I manage 1,000 emails a day.

Talking to Grok about email is allowed. Being the 15-minute cop is not. I never need the Gmail tab. Codex already sorted the cafeteria. I open the coordinator or Executive Assistant and ask what needs my yes. That is an executive assistant. Opening Grok and saying “go through my inbox” while Codex is already on a clock is two cops, and that is the inefficient part. IT Support, Website Builder, and the other named desks stay. When the next sentence is homework in a repo, I walk into Cursor.

Goal: fill the included $200-class bars before overflow. Overflow has cost thousands a month.

Buzz is the live radio room for handoffs between agents. Durable receipts stay in GitHub agent-notes plus NOW.md. The canary starts small (me + Grok + one Claude). Expand carefully.

The rule that keeps this from becoming a swarm

One human. One coordinator conversation. Specialists get a job when the coordinator (or I) assign it.

I do not want silent fan-out. If another model or another agent needs a job, I say so in the thread. Three paid seats chewing the same task is not leverage. It is waste.

That matches how I work: one operating system, portable context, proof over adjectives. A skill is a function. An agent is a person-shaped role wrapped around that function: memory, a schedule, keys, and a written record. A persistent agent is that role plus a job that actually runs.

Three layers, one playbook

Don’t count agents and call that the system. Count layers.

Skills are the shared playbook. The Task Library and the GitHub skill files are the same methods on every runtime. A skill is a function. We have 200+ of those. They do not care whether Claude, ChatGPT, or Grok is running them.

Departments are the six stable functions: Front desk, Research, Build, Publishing, Growth, Quality. Those names stay put. A new tool does not invent a seventh department.

Agents are named desks on a specific runtime. Grok Bot has 12 desks today. Claude is stronger as skills plus scheduled jobs. ChatGPT and Codex are Work plus Codex. The headcount will never match, and it should not. Harmonize the playbook, not the roster.

Click the layer

A picture is not done until every box goes somewhere. I am not making 200 task pages. The Task Library already holds the tasks (237 name pages). SEO leaves: localservicespotlight.com/tasks (working) · blitzmetrics.com/task-library (SEO). A desk page ships when it has can/can’t plus one public-safe receipt. No empty stubs. This roster is the index. Personal Assistant stays unpublished.

Desk names that have a page are links. Thin stubs are still skipped.

Component	Goes to
Skills / playbook	GitHub skill files
Task Library	LSS catalog (237 name pages) · BlitzMetrics SEO library
Task Library Dashboard	task-library-dashboard
How we turned 239 tasks into skills	the build story
Six departments	A skill is a function. An agent is a person.
Build agents	How we build and maintain AI agents
Update loop	Persistent agents
How skills propagate	From real work to every agent
Learn-Do-Teach	9 Triangles
Grok Bot desks	this page, the roster below
Claude	How to use Claude
ChatGPT	How to use ChatGPT
Official Grok Bot	x.ai/bot

Quality as a department now has a section on this page.

Quality, the department that checks the other five

Quality is one of the six stable departments. It is not IT and it is not a helpdesk. IT Support is a desk inside Quality. The department checks the other five.

On the company clock it is also called Quality & Money. That is the only live page that defines the department.

What it measures:

• What I mean by RSI and the RSI agent loop: work, then a receipt, then QA against the definitive article, then rewrite the skill, then the next run.
• Website QA audit and the website QA checklist.
• Blog posting guidelines (working copy: article guidelines) and the Jennifer article grader.
• Friday scoreboard: MAA metrics analysis action.
• Persistent agent QA cycle.

The reward loop is simple. Zero-revision work earns autonomy. The default is a manager marks complete. People and desks earn the right to ship without babysitting by passing the same checklists first time. That is why VAs never mark their own complete.

Grok desks under Quality: IT Support, Fleet Monitor, and Meter Maid. Each name points to its can/can’t page and public-safe receipt.

House rule stays: docs on this hub ship by default. Still stop for send, money, delete, permissions, or production infra.

How the layers keep getting updated

The loop on the right is the whole point. Live work produces a receipt. The receipt becomes a skill update. The next run loads the new skill. That is Learn-Do-Teach as software, and it is how a persistent agent stays current instead of going stale.

The detailed map, with live examples and the states from Available to Outcome, is how skills propagate from real work to every agent.

Training + Documentation owns that loop. A Zoom, a broken button, a Singapore deck, a desk that just learned something: it does not stay in the chat. It becomes a public master version, then gets skinned across verticals.

The architecture is three layers plus the update loop. The 12 desks are the Grok Bot skin of layer three.

How the desks work together

Work comes in as a Zoom, an email, a site that went down, a draft that needs a home. BlitzMetrics Ops keeps strategy and execution in one thread. Strategy Bot reasons from the Nine Triangles when the question is “what should we do.” Training + Documentation turns the live work into public master versions: skill files, SOPs, articles, and agent training that get skinned across verticals. The Make desks write and ship. The Keep-honest desks watch uptime and paid usage. The Queues desks clear support and executive follow-through. The private desk stays private.

Documentation on this hub ships by default and we iterate. Still stop for a yes before sending email, spending money, deleting, changing permissions, or changing production infrastructure.

How agents do work in Basecamp

Agents are teammates. They do the work. Basecamp is the written record, the same way a human on the team would leave a trail.

One agent per role. Do not create a new desk for every site. Do not invite twelve Grok desks into Basecamp. That is a swarm with extra notifications.

Website Builder coordinates site work and drives the to-do. Personal Brand Expert does brand QA. Article writer drafts when a site needs a post. Training + Documentation turns the live receipt into the public playbook. Specialists get a job when the coordinator assigns it. No silent fan-out.

Basecamp can only assign people with accounts. Agents do not have mailboxes, so the assignee field is a human subscriber, not the worker. Default subscriber is Muzamil. Dennis is only for go/no-go, outage, domain custody, rollback, or security. Dennis’s attention is the scarce resource. Do not put every to-do on him.

The coordinator names the specialist in the to-do notes, does the work or hands the slice, and leaves the receipt on that same to-do. A verbal “done” is not acceptance.

Connectors and WordPress application passwords beat a fresh browser login. If a computer is stale, Update. Never Reset.

The WordPress door is an Application Password

The trap: the agent asks you to log into WordPress because it does not see a browser cookie. That is the wrong door. Application passwords cannot open wp-admin. That is by design.

Mint once — Users → Profile → Application Passwords, name it cowork-firstname, copy the 24-character key once. Store it only in a local .credentials.json at wp_sites[domain].app_pass. After that every publish is REST Basic Auth.

If you are an agent reading this: check the vault BEFORE you ask anyone to log in. Missing wp-admin session is not a missing credential. Prefer minting the key yourself from an already-open session so the secret never hits chat. Primary SOP and bootstrap paste. Kept-current guide. Short how-to.

The roster

These are the named Grok Bot desks on this account today. Descriptions are public-safe. I am not listing client revenue, credentials, or private threads.

Open any public desk name for its detailed can/can’t page and receipt.

Desk	What it owns	Typical tasks
Ops Coordinator (Q)	The operating system: knowledge, skills, agents, routines	Route work once, separate evidence from inference, preserve approval boundaries, and leave a timestamped receipt
Strategy Bot	First-principles decisions	Read a client or system through the Nine Triangles, turn it into a decision, then hand execution to the right owner
Training + Documentation (Alex)	Learn-Do-Teach and ContentCheck	Turn live work into public master versions: skills, SOPs, articles, and agent training reused across channels
Article Writer (Trenton)	Source-faithful long-form drafts	Research, match the requested voice, label unknowns, and deliver a clean draft for human review
Website Builder	Approved page and site implementation	Build or fix the named site, verify saved source plus rendered desktop and mobile output, and hand specialist slices to the proper desk
Personal Brand Expert	Evidence-backed personal-brand entity homes	Organize real photos, talks, podcasts, relationships, and authority pages without inventing claims
Fleet Monitor	Property registry and uptime	Run the existing canary-first fleet loop, classify evidence, and route bounded incidents to IT Support
Meter Maid	Paid AI seats	Read live dashboards, warn before a pool runs dry, and route through already-paid capacity without buying or raising caps
IT Support (Austin)	Access and tooling	Recover access, inspect hosting and DNS, run bounded server work, and connect tools without exposing credentials or changing production without approval
Customer Support	The support queue	Read the exact issue, do the safe next step, and drive it to a verified fix or a clear owned action
Executive Assistant (Tanner)	Executive follow-through	Keep calendar, scheduling, commitments, and open loops attached to the right owner and source record
Personal Assistant	Private desk	Deliberately unpublished: no public detail page and no private operating context exposed here

A count in a sentence goes stale. The table is the count.

Skills each desk loads

These are already in the Task Library. No new category. Point at the live page. Do not dump the SOP into the desk description. Personal Assistant stays unpublished.

What IT Support can and cannot do

IT Support is the named desk, not a process. The work already lives in Digital Plumbing and Website Building and QA. Quality is the department (Keep honest on this roster).

Three AWS words in English. SSM means run a command on the server without logging in with SSH. EC2 is the server. Route 53 is where the domain points. Reboot would mean restart the server. This desk does not reboot or shut servers down.

What it can do:

• Reset a WordPress login on a fleet site when I ask
• Run a command on the site-builder server without SSH
• Look up which server a site is on, whether it is up, and its IP
• Read DNS
• Connect tools (Zoom, plugins) so other desks can use them
• Keep a key-only AWS login on the shared computer so department agents do not need my passkey
• Hand work to the right desk when it is not IT

What it cannot do:

• Log into the AWS website
• Spend money or touch billing
• Create users or widen permissions unless I approve it
• Shut down, reboot, or delete a server
• Delete a site or wipe data
• Type my password or 2FA
• Publish a public page, send email, or post as me without a yes
• Write articles, set strategy, or own fleet uptime (Fleet monitor owns uptime)

House rule: documentation on this hub ships by default and we iterate. Still stop for a yes before sending email, spending money, deleting, changing permissions, or changing production infrastructure. IT Support still cannot publish articles or post as Dennis.

Proof from this weekend: theninetriangles.com login for access@blitzmetrics.com was reset from the shared computer. BlitzAdmin could not rotate that password. The public site stayed up.

25 August 2026 IT Support receipts (detail on the IT Support desk page): louisvillefenceworks.com plugin patch (Smush 4.3.2, NitroPack 1.20.0); tlsenergysavers.com leftover hosting still live, owners asked keep/handoff/take-down; thyrellpardjo.com public DNS still at Domain.com, not Route 53 (chase Sep 1). No host IDs or nameserver lists.

27 August 2026 IT Support receipt (detail on the IT Support desk page): invited GitHub user hezekiah-lss as a Member of Local-Service-Spotlight, Write on agent-runtime and task-library (invites pending). wordpress-site-builder App not approved (no install request; org policy blocks deploy keys). No tokens, host IDs, or account numbers.

27 August 2026 IT Support receipt (detail on the IT Support desk page): Wordfence Hub SSO flag on WPMU DEV Dashboard below 5.0.2. One live copy at adastrasoftwash.com (5.0.1) deactivated over REST. Homepage 200. Smush Pro stayed on. 5.0.2 still needs a WP Engine session. No host IDs, IPs, or account numbers.

31 August 2026 IT Support receipt (detail on the IT Support desk page): Gmail send-as confirmed for 668sierra@gmail.com as dennis@blitzmetrics.com. No secrets.

1 September 2026 IT Support receipt (detail on the IT Support desk page): minted application password named IT Support Grok Bot on gratefuldeadartifacts.com (admin, REST 200). Token stored off-page. Reset Gmail archived. No secret values.

1 September 2026 IT Support receipt (detail on the IT Support desk page): All-in-One WP Migration CVE-2026-19949. site-builder 40 of 41 to 7.110; bm-dnz zero copies; seven WP Engine installs still pending portal access. Advisory Gmail archived. No secret values.

1 September 2026 IT Support receipt (detail on the IT Support desk page): Gravity Forms Argus. EC2 fleets clean. Two live installs (yangpoo.com 2.9.9 WPE, brendanking.ca 2.10.5) left active pending portal upgrades to 3.0.3+. Advisory archived. No secret values.

1 September 2026 IT Support receipt (detail on the IT Support desk page): WordPress application password for lianaling.com verified REST 200 as cowork-hub-publish; stored off-page on both Macs. No secret values.

1 September 2026 IT Support receipt (detail on the IT Support desk page): BlitzAdmin fleet WordPress admin password reconciliation. 116 of 116 MATCH at the database; 102 of 116 confirmed with a real login session. Teammates told not to click the Password Changed / reset burst. No secret values.

2 September 2026 IT Support receipt (detail on the IT Support desk page): web@ 11-domain host check closed by reply-all. markelhayek.com still on site-builder; panel paths still needed for jackhughes.me and thyrellpardjo.com. No secret values or host IDs.

2 September 2026 IT Support receipt (detail on the IT Support desk page): Elementor Pro CVE-2026-32475. bm-dnz clean. site-builder three trees blocked on licensed WP-CLI (Unauthorized / no package). paulryazanov.com at 4.2.0 plus three WP Engine leftovers. Zero patched; no pirated zip. Forms upload dirs clean of PHP. No secret values.

3 September 2026 IT Support receipt (detail on the IT Support desk page): restoring markelhayek.com to the BlitzAdmin 116 stayed blocked on White Label Dash write. Public site 200 and on the fleet host; no IT Support Dash user, and this desk cannot type Dennis’s personal password. Waits on a dedicated IT Dash seat or a human login on Austin’s computer. No secret values, host IDs, or SiteIds.

4 September 2026 IT Support receipt (detail on the IT Support desk page): deactivated WPCode Lite on blitzmetrics.com to stop a Writesonic seo-fixer header inject. Homepage no longer loads seo-fixer.writesonic.com. FB/Bing verification metas that shared that header are off until WPCode is cleaned and reactivated. No secret values.

2 September 2026 IT Support receipt (detail on the IT Support desk page): after an approved registrar cutover, roaninpodkin.com moved from GoDaddy nameservers to Route 53. Public NS now shows the Route 53 delegation, and the homepage returns 200. No host IDs, account numbers, IPs, or secret values.

2 September 2026 IT Support receipt (detail on the IT Support desk page): accepted the Target Painting & Contracting Google Business Profile manager invite on the Workspace identity that received it. The source record opens and the invite email was archived. The exact role is still unverified behind Google phone verification. No account identifiers or secret values.

3 September 2026 Training receipt (detail on the Training + Documentation desk page): Q owns Thursday Office Hours Facebook posts. Summary text → dennispk only (this week). Zoom recording → officehourswithdennisyu only (this week). No duplicates.

4 September 2026 Training receipt (detail on the Training + Documentation desk page): agents own follow-up after 2 weekdays (not 3). Label Awaiting Reply, archive, chase yourself. Dennis is never the chase layer.

4 September 2026 Training receipt (detail on the Training + Documentation desk page): Friday Client MAA fleet posted 16 client-visible Basecamp MAAs (MAA: 9/4/2026). Skipped Plumbing Pros PA and Harris. No bid or budget changes.

Skills this desk loads (already in the Task Library, no new category):

• Digital Plumbing Checklist
• What is Digital Plumbing?
• How to spin up a personal brand website using BlitzAdmin
• Zoom is intake under Knowledge System Maintenance, not a separate IT tree

Diagrams to click, not redraw: Click the layer on this hub, A skill is a function. An agent is a person., Persistent agents, The System, Web Function.

How we recover a fleet WordPress login

This is a Website Building and QA / Digital Plumbing method. IT Support is the desk that runs it, not the name of the process.

BlitzAdmin WP Creds are display-only and often stale. There is no rotate control. SSH is not the path. Recovery is SSM SendCommand plus WP-CLI from the live docroot. SSM means run a command on the server without logging in with SSH.

1. Confirm the site must stay up. Do not delete it.
2. Confirm the public hostname still serves a page.
3. Look up the site in BlitzAdmin. Treat stored WP Creds as stale.
4. Identify the server from the fleet inventory. Do not publish host IDs, account numbers, or IPs.
5. Use the key-only agent AWS login on the shared computer. Do not ask me for the console passkey.
6. Confirm SSM is Online, then from the live docroot /wp-sites/live/{domain}/public (not /var/www) run wp user update {email}.
7. Verify the user is still administrator and the public site still loads.
8. Tell the requesting desk the login is reset. Do not paste the new password into a public page or group chat.

Fail if the site is deleted, the console passkey is used as the only path, a BlitzAdmin password is treated as current, SSH is the plan, or a password is posted in chat.

Proved 16 August 2026 on theninetriangles.com for access@blitzmetrics.com. The public site stayed up.

How to set up a Grok Bot agent

This is the CCS Checklist layer. Run it in order.

1. Open Grok Bot on desktop or iOS. Confirm you are in the BlitzMetrics Ops conversation, not a new side chat, unless you are deliberately opening a specialist.
2. State the job in one sentence. Keep strategy and execution in that same thread.
3. Don’t send the same job to Claude or ChatGPT unless I say so in the thread. No silent fan-out.
4. To add a specialist, create a new agent with a name and a one-paragraph job description. The description is the job. If it is empty, the desk is a label, not an employee.
5. Point the description at the canonical skills repo for methods, and at user-owned Markdown, Obsidian, or Drive for context. Never treat context as a method.
6. Write the approval gates into the description: documentation on this hub ships and we iterate. Still stop for a yes before sending email, spending money, deleting, changing permissions, or changing production infrastructure.
7. Open Settings from the sidebar account button, Cmd+,, or the command palette item “Open settings”.
8. Use only these Settings tabs: General, Plugins, Team Setup, Appearance, Updates. Don’t invent other menus.
9. Install and enable skills under Settings → Plugins. Type / to reference a skill. If it is missing from the slash menu, open Plugins → Yours and enable it for this Bot.
10. After a job works once: save the skill, Test run, then create the routine. View conversation details → Routines. Cap 50. A test run is real work.
11. Connect the few connectors the desk actually needs (Gmail, Drive, GitHub, Calendar). Don’t connect everything “just in case.”
12. If the computer is stale or stuck, go to Settings, then Updates, then click “Update Grok Bot’s Computer”. The button says Update. Update keeps files and logins.
13. Don’t click Reset. Reset drops unsynced work, files, and logins. Update is the recovery path.
14. To inspect an agent, click the agent name in the chat header or press Cmd+Shift+I. The computer preview is in that pane.
15. To delete an agent, right-click it in the sidebar and choose Delete.
16. Keep secrets on the agent computer only. Never paste application passwords, tokens, or vault contents into Drive, Slack, chat, or a public note.
17. Write public handoff notes to Google Drive, then into the shared vault. Facts, URLs, and next steps only.
18. If you publish to WordPress, set the author to the person user first. If only admin exists, publish as admin and fix later.
19. End the session with a Drive handoff: what shipped, which URLs are live, what is still open. Then stop. Don’t start a second desk.
20. One agent per role. Name the specialist on the Basecamp to-do. Do not invite every desk into Basecamp.
21. Assign the Basecamp to-do to Muzamil as the human subscriber. Dennis only for go/no-go, outage, custody, rollback, or security.
22. Leave the receipt on that same to-do. A verbal “done” is not acceptance.

The software layer

There is no separate article-specific skill file to download. Load the current Local Service Spotlight shared skill library once, then enable only the skills this desk needs under Settings → Plugins. The public repository is the software source; this page is the human-readable checklist.

Routines live on the Grok Bot computer. They run the repeatable parts of the checklist so I am not retyping the same rules every morning.

A Grok Bot skill is how. A routine is when. Same ladder as a Claude scheduled task and a Cursor Automation. Official: skills, routines, and automations. Public map: skill is how, routine is when.

Drive is the public memory. Persistence is simple: Update keeps the computer. Reset doesn’t.

Install the same methods the other runtimes use: paste https://github.com/dennisyu/local-service-spotlight-skills once, the way the Claude install guide describes. The skill pack is the readable version of that library. Shared memory is how Claude, ChatGPT/Codex, and Grok boot from the same folder instead of three chat histories.

That’s CCS Software: the skill, the routines, the Drive handoff pattern. Not a swarm of extra models.

What we withhold

Secrets stay off the public record. Application passwords, tokens, and vault contents do not go in Drive notes, this article, or the skill file.

We withhold Reset as a fix. If someone tells you to Reset Grok Bot’s Computer to recover it, they are telling you to throw away unsynced work. Use Update.

We withhold client revenue and private-desk contents. The live pages and the public roster are enough proof.

What we do with the BlitzMetrics brand

BlitzMetrics is sunset as a promoted brand. Keep blitzmetrics.com and the SEO. Do not delete or noindex those pages.

Do not tell people to hire, follow, or join BlitzMetrics. New public work goes on the Spotlight brand, the client site, or the figurehead. This hub is the figurehead copy. Money and attention go there.

Existing blitzmetrics.com links on this hub stay. Those are the skill and department pages. That is SEO, not a promo.

Related reading

This page is the Grok Bot home. Everything below is an orbit, not a second home.

• How my agents divide the work and where they talk: the four-surface handoff recipe behind this Grok Bot roster
• How I run 20+ agents: the browser-tab fleet this desk replaces
• How I work: the portable operating system any model can load
• The System: the whole machine
• How we build and maintain AI agents: one skill library, three runtimes
• A skill is a function. An agent is a person.
• Persistent agents
• Dennis OS
• Move context between ChatGPT and Claude
• Shared memory across agents
• Claude skill-pack install
• Skill pack
• 9 Triangles
• CCS: Word of Mouth
• Building in public
• A skill is how. A routine is when: Claude scheduled task = Grok Bot routine = Cursor Automation
• Grok Bot desk SOP
• Official Grok Bot

The BlitzMetrics leaf of this article is blitzmetrics.com/grok-bot. That brand still ranks. The home is this page on dennisyu.com. The glossary is blitzmetrics.com/skills-and-routines.