No-Code Agentist

GROK BOT HOW TO USE Sources: official Grok Bot docs + CLI + your Grok Bot bookmark folder (976 posts) Updated: 2026-09-23 WHAT NEW TODAY - Folder: 976 posts, 17 new versus Sep 22. - Official Grok (Sep 23): Grok Bot and Connectors now work in your Tesla — the car can do meaningful work on the way. - Official bot (Sep 22): rebuilt customer support around Grok Bot — autonomous respond / resolve / queue management; write-up on https://t.co/nFxF2WJPMa news. - Testers quoting SpaceXAI: support volume +175% with zero new hires (~200 people avoided); 99% of refunds resolved without a human; about $0.20–$0.30 per ticket; trained on 1M+ interactions; 20k+ feedback/day. - Grok Bot team (poteto): desktop app 53 perf fixes — reconnect after flaky link 60s→0.7s; wake laptop 23s→1s; Computer view 868ms→27ms; long code-block chat 954ms→228ms; Media tab downloads 137MB→0.7MB. - Testers: amplify the desktop speed upgrade. - Official: bots reply quicker to texts; another ~6% more usage on average. - Testers: 400k+ weekly users one month after launch (418k as of Sep 14, +24% week). - Testers Tesla in-car (SuperGrok Heavy first / more tiers later): order coffee / AirPods / groceries by voice while FSD drives; early beta syncs Grok to your Bot team. - Testers: SpaceXAI free training day — Amrita showed Bots across GTM, engineering, marketing, and admin. - Testers: Lock Screen / Mac notch widget experiment for Grok Bot. WHAT IT IS - A Bot is a named, persistent teammate, not a one-off chat. - Message it like a coworker; it works in real apps and returns for approval or a human step. - All Bots share one cloud computer with browser, files, and terminal; each Bot has its own screen. - Work continues when the laptop or app is closed. - Grok Bot is the machine that does work; do not confuse it with Digital Optimus or an X Chat Agent. - Official framing: the Bot identifies issues, notifies you when fixed, and continues the project. ACCESS AND INSTALL - SuperGrok and Cursor subscribers have access; listed plans include SuperGrok tiers, Cursor Pro tiers, Ultra, and Teams. - Sign in with the Cursor account that owns the plan and usage. Weekly/free limits reset for Grok Bot users. - Desktop download: Also listed at Desktop supports macOS and Windows; Linux is reported supported. - Mobile: iOS 18+ app “Grok Bot”; Android is available; iPad is reported available. - Link SuperGrok Heavy to Cursor to potentially unlock Cursor Ultra; plans do not stack usage. - Legacy Privacy Mode blocks Grok Bot; choose a supported Cursor data setting. Updates are in Settings → Beta. - Enterprise is available. Grok 4.7 is now reported in Bot; select it through Cursor Default Model → Edit with xhigh effort. - Grok Bot voice is live; voice notes, phone widgets, and account switching are reported. Marketplace and XChat support may roll out gradually. SIGN IN [] Desktop: choose Get started, then Sign In with Cursor in the browser. [] iOS: log in with Cursor, finish in the browser, and return to the app. [] Use the Cursor account that should own usage. [] The first-run tour shapes teammate suggestions; computer setup runs in the background. [] Cmd-D enables voice dictation; remote computer use is easier from a phone. CREATE A BOT [] Choose New in the sidebar or Cmd/Ctrl+N, then Create new agent. [] Edit Profile: name, title, description, and avatar. [] Give one primary job and standing rules; put this task’s instructions in the chat. [] Use focused specialist Bots instead of one catch-all helper; run parallel specialists when serial work is a bottleneck. [] Ask an existing Bot to design a capable Bot when it already has your context. [] Pin important Bots, hide unused Bots, resize the sidebar, and group Bots into sections. [] Duplicate a Bot to reuse its role; duplication does not copy memory or history. [] Delete only when certain; shared files and logins remain. Account limit: 50 Bots and group chats combined. [] The Bot has no in-chat model picker; Cursor Default Model → Edit → Grok 4.7 / xhigh steers Cloud Agents it launches. [] Voice mode supports briefings, exception-only updates, escalation, completion reports, standups, live review, debriefs, and approval gates. [] Marketplace and shareable templates can provide prebuilt context, connectors, and routines; verify availability before relying on previews. HOW TO WRITE A TASK [] State the outcome: what must be finished. [] Name the sources: apps, sites, files, or chats that matter. [] Add constraints: what it must not do and what requires approval. [] Define the deliverable and the review point. [] Scope with Task / Work in / Context / Done means / first N items then stop; meters track agent steps and tokens, not messages. [] Start safely with a cited summary of an attached file; do not change the file. [] Next use one real tool read-only, with a sign-in handoff if needed. [] After a good result, save the lasting format as a skill or routine. [] Use one clear job, allowed sources, a no-guessing rule, and an approval gate before action. [] Calibrate confidence, checkpoint long tasks, show negative examples, gate destructive actions separately, and test edge cases. [] Version prompts and tool configs like code; separate scratchpad from user-facing output; measure cost per successful outcome and review failures. [] Use a plan first, then base/role/current-focus instructions. Include screenshots instead of retyping screens. [] Ask the Bot to draft messages inline for approval before sending. [] Examples: email cleanup, meeting notes, sales prospecting, refunds, podcast digest, website deployment, Starlink-likely flights, and long-talk takeaways. [] Use Grok for research and comparison; use Grok Bot to open apps, change things, send, and finish. [] For hard coding/engineering, set Default Model to Grok 4.7 xhigh and hand work to a Cursor Cloud Agent. AGENT COMPUTER AND LOGINS [] Open Agent Computer from the conversation to watch the desktop. [] Use Network Debugger or route Bot Computer web traffic through your device when needed. [] Take over only for password, passkey, 2FA, CAPTCHA, payment, or other human-only pages; complete the blocked step, then return control. [] Never paste passwords or one-time codes into chat. Use a secure secret request or password manager. [] Browser sessions persist and are shared across all Bots; prefer a connector when one exists. [] 1Password support can pull Mac logins; approve each credential fill. Bot pauses when account authentication is needed. [] Disk Saver can audit caches, temporary files, and duplicates; nothing is deleted without approval. [] Account switching and direct mobile file sharing are supported. [] Connectors can cover Coinbase, X Money, sales/GTM tools, Microsoft Teams, Outlook, Outlook Calendar, OneDrive, and more; keep trades, purchases, and transfers behind approval. [] Keep durable files in /workspace with clear project folders. [] Settings → Beta offers Update Agent Computer (preserve state), Recover, or Reset; Reset can lose recent work. [] The cloud computer is not your Mac or Windows machine. [] Local execution is separate: Settings → General → Agent → Execution on Local Computer. Default policy is Ask every time. [] Give local Mac/iMessage access only on a spare machine. Treat separate Bots as sharing one security boundary. PLUGINS AND CONNECTORS [] Open Settings → Plugins → Add, then authenticate in the browser. [] Type a connector name to attach it; type / to reference a saved skill. [] Installed connectors are account-wide, not isolated to one Bot; multiple accounts can connect to one plugin. [] Follow the Connect card when a Bot asks for a plugin. [] The X path can create a developer account with included credits; some setups may still require a paid API key. [] Image generation is reported live; video editing claims exist, but video generation remains unconfirmed. [] A YouTube link with timestamps can produce a clip in some workflows. [] Microsoft connectors support email, drafts, schedules, meetings, and files. Grok Imagine Image 2.0 can generate images inside a Bot workflow. [] Coding in Cursor can preserve weekly Bot usage; use Cursor or Cloud Agents for heavy coding. SKILLS AND ROUTINES [] A skill is a reusable how-to with steps, rules, output, and approval boundary. [] A routine says when to run the work on a schedule or event. [] Do the task once, make it reliable, save a skill, then automate it. [] Teach a task from Computer view, demo up to 10 minutes, and review the draft skill; teaching records the screen, not microphone audio. [] If teaching is unavailable, ask the Bot to write a skill from completed work. [] Confirm owner, schedule, time zone, input, result, approval, and missing-data behavior. [] Keep event matchers narrow; one channel and one keyword beats every-new-message listeners. [] If the source is unavailable, report failure instead of using old data; test before scheduling. [] A test run does real work. It can send real email; Stop is not a rewind. [] View conversation details → Routines to pause, edit, inspect, or delete. Deleting has no undo. [] A Bot can own 50 routines; recent run records are retained. Deleting a Bot kills its routines. [] Audit forgotten dailies and keep recurring routines off the main agent context when possible. MULTI BOT TEAMS [] Start with one Bot owning an end-to-end outcome; add specialists only when roles are stable. [] Use group chat when the handoff should be visible; Bots can message each other and pass ownership. [] Put sending, buying, deleting, publishing, merging, production, and spend behind a human gate. [] Bots share a computer, so they are not a security boundary. [] A hub or Chief of Staff can route work to specialists; keep one group chat per job or post. [] Give each Bot one job, a supervisor, and an explicit never-without-asking list. [] Use a Red Team Bot to challenge the thesis; no single source closes a claim. [] Show a workflow on screen rather than writing a long spec when possible. [] X Money can send cash or buy merchandise through a Bot; treat every spend as a buy gate. [] Night-shift crews can share one computer, but require a human gate for merge, production, spend, send, and delete. IOS [] Use the same Bots, chats, routines, plugins, and cloud computer as desktop. [] Send text, dictate, attach photos/files, mention Bots, and reply in threads. [] Take over the computer for login or 2FA from the phone. [] Pause or resume routines on iOS; desktop is still needed for schedule editing, history, tests, deletion, and teaching. [] Enable notifications for results, questions, and approvals; approve or deny from the notification. [] Operate or take over the Bot computer from your phone with an internet connection. [] Android and iPad availability may depend on rollout and documentation timing. APPROVALS AND SAFETY [] Put the stop line in the request: “draft, do not send”; ask after showing current versus proposed. [] Desktop supports Allow once, Deny, or a matching rule; iPhone supports Approve once or Deny. [] Auto Review is in Settings → General → Auto-review. Require Approval beats Always Allow. [] Write narrow rules; never allow everything in the browser. [] Do not approve an action you cannot identify. Connect only tools the workflow needs. [] Start read-only; keep spend, send, publish, delete, overwrite, and production behind approval. [] Sign out and revoke connectors when access should end. [] Deleting a Bot does not wipe shared files or browser sessions. [] Check Weekly usage before a large run; one long job can consume trial or weekly credits quickly. [] Use Cursor for coding when it preserves weekly Bot usage. [] Gate destructive actions as a separate confirmation. Test does real work; Stop does not unsend. [] Keep bank accounts and shopping connected only with explicit approval; Bot purchases remain buy-gated. FIRST BOTS WORTH CREATING [] Inbox manager for email and Slack triage. [] Calendar and reservation Bot. [] Research and daily brief Bot. [] Coding Bot that launches Cursor Cloud Agents; set Grok 4.7 xhigh for hard jobs. [] Chief-of-staff hub that routes work to specialists. [] Personal errands Bot for tickets, food, travel, and forms. [] Content Bot that drafts in your voice for approval. [] Accounting, personal, home, shopper, recruiter, CRM scribe, QA, and dashboard-watcher Bots are useful specialist patterns. [] Shopper Bots can research prices, returns, and checkout; keep Link/card purchases behind approval. [] Lecture-to-cheat-sheet, lead-qualifying call, and voice-managed briefing patterns are reported use cases. [] Start in recruitment, e-commerce, real estate, accounting, legal, SaaS, agencies, trades, or founder operations. EVENTS - Official: Grok Bot Galaxy built a company from scratch over three days with engineering, product, and founder sessions. - Challenge: share a Bot that changed how you work for a chance at a Starbase Starship launch invitation. - Galaxy demos showed how SpaceXAI uses Grok Bot to build Grok Bot; a design community shared workflows and feedback. - Build-night roadshow: NYC marketing, LA design, Seattle engineering, San Francisco product, and Chicago recruiting dates were announced. OFFICIAL LINKS - Overview - Get started - Create Bots - Skills and routines - Computer and apps - Approvals and privacy - iOS - Cursor getting started - SuperGrok Heavy - Launch post - Download - Guides hub - Customer support case study - Engineering guide

GROK BOT GALAXY Updated: 2026-09-23 Sources: Day 1–3 livestream sessions + Grok Bot Galaxy bookmark folder (112 posts, user-X MCP) FIRST DUMP — Day 1 - Livestream demo (Day 1): Grok Bot Galaxy opened as a standing how-to topic — treat like SpaceX/Starship/Tesla folders. Three-day event framing: a small team building a company/product in three days with Grok Bot. - Livestream demo (101): Grok Bot pitched as a team of extraordinarily capable AI agents, not one single assistant. Create a bot by naming it, teaching it your style, and giving it a goal; then let it take on real work. - Livestream demo (101): Bots work in parallel across apps, tools, and websites already in use; message them like teammates; they keep context in memory and improve as they go. - Livestream demo (101 closing): Bots can access every tool — even tools without MCPs (Google Form demo; slide said this can extend to research tools such as Qualtrics). Bots learn from video teachings. External-facing actions should require human approval. - Livestream demo (Eng): AI Maturity Curve — Autocomplete (Cursor Tab) → Ask & Edit (Cursor Agent) → Agentic Coding (Cursor 3) → Automations (Cursor Cloud Agent) → Autonomous Coding (Grok Bot). - Livestream demo (PM): Three PM primitives — Attention List, Research across customer context, Shipping (Grok Bot claimed as a double-digit % of internal merged PRs). - Livestream demo (Founders): Multi-agent org live — CoS (steve) orchestrating specialists; Meet the crew: Close Bot, Prod Bot, Stalk Bot, Proto Bot, YapBot. Cost tip slide: “Routines are awesome (but audit them!)”. - Refresh 2026-09-15: first folder scrape merged — 23/+23 bookmark posts (signed-in website); see PRIOR FOLDER MERGE. - Refresh 2026-09-16: 39/+16 folder posts; Day 1 notes pack / cost tips / timestamps (see PRIOR 0916 highlights below). - Refresh 2026-09-19: 102/+13 folder posts; CoS stop wall + eng CI/eval guardrails + Blake post-sales (see PRIOR 0919). WHAT NEW TODAY / FOLDER POSTS Folder: Grok Bot Galaxy · count 112 · new +1 · scrape_via MCP · 2026-09-23 Session notes: none newer than how-to (last Day 3 Wrap already folded). Bot steering / PM fleet build (tester) - [T] 0xSoural (SpaceXAI product-lead livestream, 54 min): "bot steering" — (1) name a bot before giving it a job (role inferred from name); (2) voice ask to build a Google Form — bot stops and asks permission before running; (3) click through a task once so the bot copies it and owns the skill; (4) per-bot rules (ask first before email; no ask before slides); (5) bots message each other across tasks / pull context without opening a single chat. Full free build; stop babysitting one chat window. PRIOR 0922 FOLDER HIGHLIGHTS (was WHAT NEW 2026-09-22 · 111/+4 · no new session notes) Eng-as-managers + CoS orchestrator (tester) - [T] maestrooth (Lauren Tan / SpaceXAI): 99% will keep using Grok Bot wrong — engineers become managers of autonomous agent teams; one engineer orchestrates an entire AI agent team; watch the 1h SpaceXAI guide then build the fleet. - [T] minchoi: Grok Bot as orchestrator / Chief of Staff routes every ask; Bot Engineers — Grok Build + Grok 4.6 · Claude Code + Fable 5.1 · ChatGPT/Codex + GPT-6 Astra; persistent memory across them; no copy-paste between chats; X realtime search. CoS charter + 50-prompt pack (tester) - [T] kocer_eth (X Article): "Grok Bot Chief of Staff: the charter, 10 rules and 5 routines I run" (companion CoS charter bookmark). - [T] kocer_eth: 50 Grok Bot prompts left across a 72-hour xAI build + public guides (Tan / Palmer / Sadanani) — copy in order; expands the earlier 30-prompt viral list. PRIOR 0921 FOLDER HIGHLIGHTS (was WHAT NEW 2026-09-21 · 107/+4 · no new session notes) Physical + connector demos (tester) - [T] 0xShoopy (Day 2 SpaceXAI demos): GrokBot left the screen — newspaper bot (calendar/email/subscriptions overnight → physical print + comic + crossword from your life); package tracker (email scan → Amazon stops → split-flap display flips on arrival); iMessage controller (Instacart location screenshots every 2 min to a friend — multiplayer without a share feature); back-in-stock tracker (daily size+color check); shows tracker (renewals/premieres → what to watch tonight). Quote: said "print this" → bot found printer on WiFi with no settings/drivers. - [T] 0xShoopy (X Article, quoted in the Day 2 demos post): "Grok Bot: how to build an AI crew that learns by watching you work" (article post bookmarked; companion to the demos thread). Connectors + fleet Q&A (tester) - [T] 0xSoural (quoting eng Q&A): connect GrokBot to email, calendar, Slack, X — and credit card; run a team of bots each with its own memory, chat, and job; pipeline Slack feedback → GrokBot → cloud agents → Cursor. "The bot is the easy part. The connections are the product." 30-prompt company pack (tester) - [T] BlueDeltaHQ (Matt Palmer / Lauren Tan / Roshan Sadanani): 30 prompts left from 3-day SpaceXAI build — Slack as control plane, bots hired as employees, ship-to-main from day one; meta-bot spawns first 3 specialists from 5 questions; market research + X as research MCP → one idea by day 3; blank org → revenue path in a weekend. PRIOR 0920 FOLDER HIGHLIGHTS (was WHAT NEW 2026-09-20 · 103/+1 · no new session notes) DAY 2 LIVE STREAM SESSIONS (2026-09-16 · observer notes) Broadcast: · on-page title often “Grok Bot builds a Game Studio LIVE” (not always the role label). Marked as livestream observations; prefer slide text over chat. Sales Eng (noon–1:30 PM ET) — GAP [] GAP: Entire Sales Eng block not observed (watch cron only 3:25/5:25/6:25 PM ET). No screenshots or checklist content from our capture. Folder tester claims about Sherlock/Serena are tagged [T] above, not livestream-confirmed here. Sales (partial · joined ~4:50 PM ET) [] GAP: Missed Sales content from session start ~3:30 PM ET through join ~4:45 PM ET. [] GAP: Brief player discard/reload ~4:49–4:50 PM ET — no content claimed for that gap. [] LIVE: unmuted player; Galaxy-branded; URL above. [] Visible ~4:50–4:52 PM ET: desktop email/recruiting-style UI with “Alumni Database Email Finder”; small camera inset. [] Visible later: left-side list including “Cover Letter Critic.” [] Visible ~4:55–5:01 PM ET: three people at studio table; backdrop text “Grok Bot Galaxy.” [] No explicit on-screen “Sales” session label/slide title observed in the joined window — recorded as visible UI only. SDRs (~5:38–6:25 PM ET) [] GAP: Missed ~5:30–5:38 PM ET start; memory-pressure discards ~5:39 / 6:03 / 6:17 PM ET — no content claimed for those gaps. [] LIVE confirmation: pink LIVE badge; title “Grok Bot builds a Game Studio LIVE.” [] Livestream slide “SDR use cases” (four cards): Prospecting · Sequencing · Account Research · Drafting Copy. [] Prospecting (slide): Grok Bot finds relevant titles at target companies using web search and enrichment after understanding ICP. [] Sequencing (slide): maintains prospect lists (CSV, XLSX) and runs them through custom-built, adaptable sequences. [] Account Research (slide): research internal and external signals (e.g. fundraising, job postings) to tailor messaging. [] Drafting Copy (slide): sync email with Grok Bot so it can learn writing style for personalized messaging. [] Multi-bot UI visible: agent/tool list including “Shakespeare”, “Company Research Bot”, “Voice of the Customer Bot”, “Usage Bot.” [] Chat (not presenter claim): “Chief of staff first, then Shakespeare + web-search Simon soldiers + customer bot — clean multi-bot SDR pattern.” [] Livestream slide “What we learned”: Go End to End · Be Intentional · Think Systematically. [] Go End to End (slide): focus on workflows that combine multiple tasks; measure success by how little you need to prompt/intervene. [] Be Intentional (slide): Bots should talk to each other; you should have Bots you’ve never interacted with directly. [] Think Systematically: card body partly obscured — GAP full text. DAY 3 LIVE STREAM SESSIONS (2026-09-17 · observer notes) Broadcast: · on-page title often “Building a company in 3 days - launching today!” . Marked as livestream observations; prefer slide text over chat. Sources: galaxy-101 takeaways-*-0917.txt + galaxy-sessions Day 3 md files. Mkt Ops (~noon window · recovered after early GAPs) [] GAP: Early noon–12:11 ET before join — not recovered; no content inferred. [] GAP: ~12:22–12:25 ET Chrome Aw Snap / Error code 9 — no content inferred during recovery. [] LIVE: unmuted after initial pause; views rose ~37.7K→~56.7K in recovered segments. [] Demo: lead-review workflow for sales reps to review leads quickly (internal app framing). [] Accept: accepted leads should not have CRM fields changed immediately; status changes when a rep reaches out; automation tracks rep activity and updates status. [] Reject: picklist reason + optional notes (“Reason + optional notes”). [] Skip: local-only — skipped lead may reappear later. [] Queue: workflow actions should queue and display done only after queued/confirmed. [] Preview dummy data: Sofia Reyes, staff software engineer at Meridian Analytics; tag “Newly assigned account”; reject/X · defer/skip · green accept/check controls. [] Stage/Q&A speaker visible: Matthew Silberman; then transition to Starbase promo/contest slide (quote challenge post · explain Bot · link shared template · follow Grok/Bot). [] Tip: lead triage Accept/Reject/Skip with CRM-safe accept; reject needs reason; skip is local-only. Post-Sales (~3:26–4:30 PM ET · slides ~3:32–4:18) [] GAP: Official start 3:30 ET; earliest faithful frame ~3:26 still showed Mkt Ops hangover caption — no separate Post-Sales opening remarks recovered. [] GAP: Chrome Aw Snap error 9 ~4:22 / ~4:26 / ~4:30 — no content claimed for those gaps. [] LIVE: LIVE badge; views ~110.8K→~123K. [] Slide “Post-sales use cases” (six blocks): Morning Status Board · Follow-up Desk · Ask Watch · Call Prep · Promise Keeper · Account Reset. [] Morning Status Board: pulls calendar, Slack, last night’s call notes into one board by account; today’s calls, one move each, send list capped at three. [] Follow-up Desk: after the call, drafts customer email + internal note in your voice; creates promised materials; you edit and send; remembers clean vs edited. [] Ask Watch: looks only at messages you sent that never came back; surfaces ones where next move is yours; never replies for you. [] Call Prep: ~20 minutes before call — who’s in the room, the one thing to lock, talking points with links. [] Promise Keeper: tracks what you said you’d do, each item linked back to where you said it. [] Account Reset: when one account has you underwater, say the word — Bot lays out calendar/Slack/transcripts, promises, and next moves. [] Meet the team: Gus (Chief of Staff) · Frankie (Follow Ups) · Wally (Your voice) · Trudy (Source of truth) · Scout (Internal radar) · Account (One per account). PRIOR FOLDER MERGE (2026-09-15 · 23/+23) PLATFORM pop-up company (tester claim) - [T] oneillund: after ~5h of stream, spotted live company name PLATFORM; slogan “Spin up a stall. Own the night.”; concept connects chefs, venue landlords, food-industry workers, and operators to launch city food pop-ups; site https://t.co/Y6LvquKQUp; verification timestamp cited ~5:16:55 into the broadcast. Operating model + builders - [T] 0xMorlex: operating model Human → sets direction · Grok Bot → holds context + coordinates · Specialist agents → execute · Humans → review, redirect, approve. Agent-native company from day one (product/research/eng/ops routed through same system), not isolated “ask an agent to write some code.” - Builders named across folder posts: Matt Palmer, Lauren Tan, Roshan Sadanani (SpaceXAI engineers building live with Grok Bot as AI workforce). Also referenced as mattyp / poteto / roshan_s in tune-in posts. - [T] XFreeze tip: ask a Grok Bot to watch the livestream with you — real-time notes, screenshots, track what you care about (bot watching the bot). Fleet rules playbook - [T] kloss_xyz (from rewatching lingxi’s session): engineer bot onboards bots with fleet rules in one message; bots catch their own rule conflicts; turned into a stealable 22-rule fleet playbook. Workshop / session timestamps (tester recaps — useful for rewatch) - [T] 0xCarnagee (~1h workshop framing): 04:12 first bot from scratch · 28:40 engineers hand real work · 44:25 running product w/o a PM · 52:25 founder’s stack / starting to ship. - [T] 0xCodila (compressed-course framing): 0:35 what is GrokBot · 34:17 first Grok Bot team workflow · 42:40 run +20 GrokBots in a graph & loop · 57:51 CoS and PM (delegate the delegation) · 1:08:09 full 24/7 company case. - [T] kaorixbt: 00:00 intro · 12:31 first team · 29:18 four layers of the GrokBot stack · 44:41 templates · 52:08 phone mode · path GrokBot → Roles → Agent Stack → Templates → Phone Mode → Autonomous Teams. Contests (Official / SpaceXAI / XCreators + tester summaries) Skipped (empty / low-signal — no actionable tip) WHAT IT IS - Livestream demo (101 / Founders “Introducing Grok Bot”): Create bots for different jobs; message bots like teammates; bots keep context in memory and improve; bots can be logged into your tools and use them like you do; automations/routines; share bots / shareable workflows / Shareable Templates. - Livestream demo (Why Grok Bot slide — 101 + Founders): Easy as iMessage; Always-on agents (24/7); Uses your tools like you; Finishes the work; Shareable workflows / Shareable Templates. - Livestream demo (“Finishes the work”): create bots for different jobs, give direction and let them figure it out, then set up automations and routines. - Livestream demo (Eng Why Grok Bot): No more caffeinated laptop; Beautifully available to all platforms; Control computer when needed; First-party coding agent integration. - Event framing (livestream): three-person team attempting to build a company/product in three days with Grok Bot; public X broadcast with “Grok Bot Galaxy” backdrop. - [T] Folder reinforcement: agent-native operating model (Human→Bot→specialists→humans); live build company name PLATFORM (tester claim). - Do not treat audience chat as product claims (buffering complaints, note-taking suggestions, Cursor/subscription questions, brand-partnership asks were chat — not slides/demos). HOW IT WORKS / MULTI-BOT TEAMS - Livestream demo (101): Separate bots for separate jobs — left-side list with email/comms and slide bots; named work bots on demo slide included Sales Outbound, Chief of Staff, Inbox Manager, Website designer, and Debug. - Livestream demo (101 multi-bot): Shared conversation with Amrita Venkataraman plus Email Ethan, Data Dan, and Slide Sonya; Members panel with Add Member. - Email Ethan: drafts external notes/emails; outbound emails require Amrita’s approval before anything leaves. - Data Dan: numbers, surveys, charts; handed off Coffee Data (n=100, avg ~1.9 cups/day, median 2, mode 3; buckets 0→8, 1→23, 2→29, 3→32). - Slide Sonya: owned the Grok Bot 101 deck and new slides; created a chart on the last slide from Coffee Data before Ethan emailed Jason. - Multi-bot action pattern (livestream): assign each bot a narrow role, pass structured outputs between them, gate external communications on human approval, and sequence dependent work (chart first, email second). - Livestream demo (Eng Meet the team): Lingxixi — Chief of Staff; Craig — UI Engineer; Steve — Devex Engineer; Hogan — Infra Engineer; Jenny — Head of Operations. - Livestream demo (Eng / Founders live fleet): steve (chief of staff), tater (engineer), hashbrown (reviewer), mash, prototyper/grokpot, PlanetScale Bot; Founders roster also showed Founding Eng, Growth Eng, Knowledge Base Manager, Creative Director, drop (merch), foil (tickets), Sip, and more. - Livestream demo (Founders CoS handoff): “Needs your attention” — sign in to tdraw, then “I’m done, continue” / Skip; agent creates share link after human auth. - Livestream demo (PM lessons): Named agents + separate memory (broad mission, scoped memory); Agents all the way down — EM agents manage IC agents that spin Cloud Agents; hierarchy beats one mega-prompt. - Livestream tip (Eng): “restate in your own words before executing.” COMMON USE CASES - Livestream slide “Grok Bot: Common Use Cases” organized by GTM, Engineering, Marketing, and Admins. - GTM — Account Health and Sales Outbound (livestream): pipeline built overnight; follow-ups drafted after every call; CRM kept current; outreach shipped in the user’s voice ready for review. - Sales Outbound demo (livestream): overnight pipeline/outbound — research prospects on the web, gather contact/account info from Salesforce, draft email in the user’s voice, check/update daily; routines included a morning outbound queue and an end-of-day send list; connected Gmail + Salesforce shown. - Engineering — Product Performance and Bug Reproduction (livestream): bugs reproduced overnight; repro pack dropped in the ticket; hotspots pulled before standup; outputs ready for review. - Marketing — Talent Scout and Paid Media (livestream): campaigns watched overnight; monthly budget drafted; creatives rotated when stale; spend shifts surfaced in Slack ready for review. - Admin — Chief of Staff and Expense Manager (livestream): calendars, travel, expenses, and inboxes handled end to end while the admin directs and bots run the busywork. - [T] XFreeze: livestream note-taking / screenshot companion bot as a practical meta use case. SETUP AND ONBOARDING [] Livestream demo: first-time setup asks “What do you mainly want me for? Whatever you pick, we can refine from there.” [] Setup choices shown: Data & analysis (spreadsheets, metrics, charts); Research & digests; Workflows & routines (recurring checks, reminders, automated follow-ups); or Something else (free-text). [] Second create screen categories visible: Work & projects, Customer support, Research & …, Coding & tools, Not sure yet (exact small labels partly GAP). [] Tip: start with a broad job category and refine afterward; use free-text when presets do not fit. [] Settings/general (livestream): workspace/tool connection controls; visible toggle for automatic actions; tool/app list (exact toggle semantics GAP). [] Notifications (livestream): toggle — notify when the bot finishes or needs input. [] Share this Bot visible in Sales Outbound settings panel (livestream). [] Founders onboarding demo: browser prompt “What’s your team name?” with app/bot tiles; later slide “Where teams and agents scale together.” [] Routines (livestream explanation): recurring tasks a bot runs on a schedule; can be set up by asking it. [] [T] Fleet tip: onboard with explicit fleet rules in one message; watch for bots flagging rule conflicts (kloss_xyz / lingxi). APPROVALS AND SAFETY [] Livestream demo (Google Form): bot surfaced an explicit action card with Approve and Deny before the computer/browser task — computer actions are not silently assumed. [] Action-history statuses shown: “Allowed once,” “Auto-review Paused This Action,” “Expired”; task runs on Grok Bot’s computer; live view of the bot’s computer/Google Forms made the external action inspectable. [] Tip: Review action history/status; one-time permission, paused review, and expiry are distinct states — do not treat them as completion. [] Closing 101 slide (livestream): bots get human approval when necessary; for enterprise use, external-facing actions should require approval; Email Ethan never sends an external email until its draft is approved. [] Tip/pitfall: confirm actions that create or change external artifacts. [] Founders cost slide (livestream): “Optimizing Costs” — “Routines are awesome (but audit them!)” with routine-manager UI. [] [T] Operating-model reminder: humans review, redirect, approve after specialists execute. TEACHING SKILLS (Slide Sonya) [] Livestream demo: “Slide Sonya” (Slide Maker) learned a Google Slides animation workflow from a demo and saved it as a reusable skill. [] Captured workflow: select object → Insert → Animation (Motion) → add animation → choose type (example: Fly in from top) → optionally By paragraph and speed; remove animation at end as cleanup, not part of the skill. [] Bot summarized inputs: slide/object, animation type, By paragraph, speed; assumed Google sign-in; default “Grok Bot 101” deck. [] After learning: offered “dry run on the title slide?” with Yes, dry run / Not now. [] Slide Sonya instructions visible: text clean and centered, at least 20 pt; use deck theme colors only; send a screenshot of the created slide back in chat. [] Workflow tip: watch a demonstrated procedure → summarize steps/inputs → save as skill → dry run for confirmation. [] Closing 101: bots have memory and can learn from video teachings; Slide Sonya remembers preferred fonts/slide design and can be taught animations/transitions for consistency.

Jev is the missing brain in every AI agent It decides what happens next in milliseconds, at almost zero cost Set it up right and you cut most of your agent bill without touching quality In this article, I show you how https://t.co/ksF95ZE2Fa

GROK BOT GALAXY Updated: 2026-09-22 Sources: Day 1–3 livestream sessions + Grok Bot Galaxy bookmark folder (111 posts, user-X MCP) FIRST DUMP — Day 1 - Livestream demo (Day 1): Grok Bot Galaxy opened as a standing how-to topic — treat like SpaceX/Starship/Tesla folders. Three-day event framing: a small team building a company/product in three days with Grok Bot. - Livestream demo (101): Grok Bot pitched as a team of extraordinarily capable AI agents, not one single assistant. Create a bot by naming it, teaching it your style, and giving it a goal; then let it take on real work. - Livestream demo (101): Bots work in parallel across apps, tools, and websites already in use; message them like teammates; they keep context in memory and improve as they go. - Livestream demo (101 closing): Bots can access every tool — even tools without MCPs (Google Form demo; slide said this can extend to research tools such as Qualtrics). Bots learn from video teachings. External-facing actions should require human approval. - Livestream demo (Eng): AI Maturity Curve — Autocomplete (Cursor Tab) → Ask & Edit (Cursor Agent) → Agentic Coding (Cursor 3) → Automations (Cursor Cloud Agent) → Autonomous Coding (Grok Bot). - Livestream demo (PM): Three PM primitives — Attention List, Research across customer context, Shipping (Grok Bot claimed as a double-digit % of internal merged PRs). - Livestream demo (Founders): Multi-agent org live — CoS (steve) orchestrating specialists; Meet the crew: Close Bot, Prod Bot, Stalk Bot, Proto Bot, YapBot. Cost tip slide: “Routines are awesome (but audit them!)”. - Refresh 2026-09-15: first folder scrape merged — 23/+23 bookmark posts (signed-in website); see PRIOR FOLDER MERGE. - Refresh 2026-09-16: 39/+16 folder posts; Day 1 notes pack / cost tips / timestamps (see PRIOR 0916 highlights below). - Refresh 2026-09-19: 102/+13 folder posts; CoS stop wall + eng CI/eval guardrails + Blake post-sales (see PRIOR 0919). WHAT NEW TODAY / FOLDER POSTS Folder: Grok Bot Galaxy (id 2099917541162324015) · count 111 · new +4 · scrape_via MCP · 2026-09-22 Session notes: none newer than how-to (last Day 3 Wrap Sep 17 already folded). Eng-as-managers + CoS orchestrator (tester) - [T] maestrooth (Lauren Tan / SpaceXAI): 99% will keep using Grok Bot wrong — engineers become managers of autonomous agent teams; one engineer orchestrates an entire AI agent team; watch the 1h SpaceXAI guide then build the fleet. - URL: - [T] minchoi: Grok Bot as orchestrator / Chief of Staff routes every ask; Bot Engineers — Grok Build + Grok 4.6 · Claude Code + Fable 5.1 · ChatGPT/Codex + GPT-6 Astra; persistent memory across them; no copy-paste between chats; X realtime search. - URL: CoS charter + 50-prompt pack (tester) - [T] kocer_eth (X Article): "Grok Bot Chief of Staff: the charter, 10 rules and 5 routines I run" (companion CoS charter bookmark). - URL: - [T] kocer_eth: 50 Grok Bot prompts left across a 72-hour xAI build + public guides (Tan / Palmer / Sadanani) — copy in order; expands the earlier 30-prompt viral list. - URL: PRIOR 0921 FOLDER HIGHLIGHTS (was WHAT NEW 2026-09-21 · 107/+4 · no new session notes) Physical + connector demos (tester) - [T] 0xShoopy (Day 2 SpaceXAI demos): GrokBot left the screen — newspaper bot (calendar/email/subscriptions overnight → physical print + comic + crossword from your life); package tracker (email scan → Amazon stops → split-flap display flips on arrival); iMessage controller (Instacart location screenshots every 2 min to a friend — multiplayer without a share feature); back-in-stock tracker (daily size+color check); shows tracker (renewals/premieres → what to watch tonight). Quote: said "print this" → bot found printer on WiFi with no settings/drivers. - URL: - [T] 0xShoopy (X Article, quoted in the Day 2 demos post): "Grok Bot: how to build an AI crew that learns by watching you work" (article post bookmarked; companion to the demos thread). - URL: Connectors + fleet Q&A (tester) - [T] 0xSoural (quoting eng Q&A): connect GrokBot to email, calendar, Slack, X — and credit card; run a team of bots each with its own memory, chat, and job; pipeline Slack feedback → GrokBot → cloud agents → Cursor. "The bot is the easy part. The connections are the product." - URL: 30-prompt company pack (tester) - [T] BlueDeltaHQ (Matt Palmer / Lauren Tan / Roshan Sadanani): 30 prompts left from 3-day SpaceXAI build — Slack as control plane, bots hired as employees, ship-to-main from day one; meta-bot spawns first 3 specialists from 5 questions; market research + X as research MCP → one idea by day 3; blank org → revenue path in a weekend. - URL: PRIOR 0920 FOLDER HIGHLIGHTS (was WHAT NEW 2026-09-20 · 103/+1 · no new session notes) DAY 2 LIVE STREAM SESSIONS (2026-09-16 · observer notes) Broadcast: · on-page title often “Grok Bot builds a Game Studio LIVE” (not always the role label). Marked as livestream observations; prefer slide text over chat. Sales Eng (noon–1:30 PM ET) — GAP [] GAP: Entire Sales Eng block not observed (watch cron only 3:25/5:25/6:25 PM ET). No screenshots or checklist content from our capture. Folder tester claims about Sherlock/Serena are tagged [T] above, not livestream-confirmed here. Sales (partial · joined ~4:50 PM ET) [] GAP: Missed Sales content from session start ~3:30 PM ET through join ~4:45 PM ET. [] GAP: Brief player discard/reload ~4:49–4:50 PM ET — no content claimed for that gap. [] LIVE: unmuted player; Galaxy-branded; URL above. [] Visible ~4:50–4:52 PM ET: desktop email/recruiting-style UI with “Alumni Database Email Finder”; small camera inset. [] Visible later: left-side list including “Cover Letter Critic.” [] Visible ~4:55–5:01 PM ET: three people at studio table; backdrop text “Grok Bot Galaxy.” [] No explicit on-screen “Sales” session label/slide title observed in the joined window — recorded as visible UI only. SDRs (~5:38–6:25 PM ET) [] GAP: Missed ~5:30–5:38 PM ET start; memory-pressure discards ~5:39 / 6:03 / 6:17 PM ET — no content claimed for those gaps. [] LIVE confirmation: pink LIVE badge; title “Grok Bot builds a Game Studio LIVE.” [] Livestream slide “SDR use cases” (four cards): Prospecting · Sequencing · Account Research · Drafting Copy. [] Prospecting (slide): Grok Bot finds relevant titles at target companies using web search and enrichment after understanding ICP. [] Sequencing (slide): maintains prospect lists (CSV, XLSX) and runs them through custom-built, adaptable sequences. [] Account Research (slide): research internal and external signals (e.g. fundraising, job postings) to tailor messaging. [] Drafting Copy (slide): sync email with Grok Bot so it can learn writing style for personalized messaging. [] Multi-bot UI visible: agent/tool list including “Shakespeare”, “Company Research Bot”, “Voice of the Customer Bot”, “Usage Bot.” [] Chat (not presenter claim): “Chief of staff first, then Shakespeare + web-search Simon soldiers + customer bot — clean multi-bot SDR pattern.” [] Livestream slide “What we learned”: Go End to End · Be Intentional · Think Systematically. [] Go End to End (slide): focus on workflows that combine multiple tasks; measure success by how little you need to prompt/intervene. [] Be Intentional (slide): Bots should talk to each other; you should have Bots you’ve never interacted with directly. [] Think Systematically: card body partly obscured — GAP full text. DAY 3 LIVE STREAM SESSIONS (2026-09-17 · observer notes) Broadcast: · on-page title often “Building a company in 3 days - launching today!” (). Marked as livestream observations; prefer slide text over chat. Sources: galaxy-101 takeaways-*-0917.txt + galaxy-sessions Day 3 md files. Mkt Ops (~noon window · recovered after early GAPs) [] GAP: Early noon–12:11 ET before join — not recovered; no content inferred. [] GAP: ~12:22–12:25 ET Chrome Aw Snap / Error code 9 — no content inferred during recovery. [] LIVE: unmuted after initial pause; views rose ~37.7K→~56.7K in recovered segments. [] Demo: lead-review workflow for sales reps to review leads quickly (internal app framing). [] Accept: accepted leads should not have CRM fields changed immediately; status changes when a rep reaches out; automation tracks rep activity and updates status. [] Reject: picklist reason + optional notes (“Reason + optional notes”). [] Skip: local-only — skipped lead may reappear later. [] Queue: workflow actions should queue and display done only after queued/confirmed. [] Preview dummy data: Sofia Reyes, staff software engineer at Meridian Analytics; tag “Newly assigned account”; reject/X · defer/skip · green accept/check controls. [] Stage/Q&A speaker visible: Matthew Silberman; then transition to Starbase promo/contest slide (quote challenge post · explain Bot · link shared template · follow Grok/Bot). [] Tip: lead triage Accept/Reject/Skip with CRM-safe accept; reject needs reason; skip is local-only. Post-Sales (~3:26–4:30 PM ET · slides ~3:32–4:18) [] GAP: Official start 3:30 ET; earliest faithful frame ~3:26 still showed Mkt Ops hangover caption — no separate Post-Sales opening remarks recovered. [] GAP: Chrome Aw Snap error 9 ~4:22 / ~4:26 / ~4:30 — no content claimed for those gaps. [] LIVE: LIVE badge; views ~110.8K→~123K. [] Slide “Post-sales use cases” (six blocks): Morning Status Board · Follow-up Desk · Ask Watch · Call Prep · Promise Keeper · Account Reset. [] Morning Status Board: pulls calendar, Slack, last night’s call notes into one board by account; today’s calls, one move each, send list capped at three. [] Follow-up Desk: after the call, drafts customer email + internal note in your voice; creates promised materials; you edit and send; remembers clean vs edited. [] Ask Watch: looks only at messages you sent that never came back; surfaces ones where next move is yours; never replies for you. [] Call Prep: ~20 minutes before call — who’s in the room, the one thing to lock, talking points with links. [] Promise Keeper: tracks what you said you’d do, each item linked back to where you said it. [] Account Reset: when one account has you underwater, say the word — Bot lays out calendar/Slack/transcripts, promises, and next moves. [] Meet the team: Gus (Chief of Staff) · Frankie (Follow Ups) · Wally (Your voice) · Trudy (Source of truth) · Scout (Internal radar) · Account (One per account). PRIOR FOLDER MERGE (2026-09-15 · 23/+23) PLATFORM pop-up company (tester claim) - [T] oneillund: after ~5h of stream, spotted live company name PLATFORM; slogan “Spin up a stall. Own the night.”; concept connects chefs, venue landlords, food-industry workers, and operators to launch city food pop-ups; site https://t.co/Y6LvquKQUp; verification timestamp cited ~5:16:55 into the broadcast. Operating model + builders - [T] 0xMorlex: operating model Human → sets direction · Grok Bot → holds context + coordinates · Specialist agents → execute · Humans → review, redirect, approve. Agent-native company from day one (product/research/eng/ops routed through same system), not isolated “ask an agent to write some code.” - Builders named across folder posts: Matt Palmer, Lauren Tan, Roshan Sadanani (SpaceXAI engineers building live with Grok Bot as AI workforce). Also referenced as mattyp / poteto / roshan_s in tune-in posts. - [T] XFreeze tip: ask a Grok Bot to watch the livestream with you — real-time notes, screenshots, track what you care about (bot watching the bot). Fleet rules playbook - [T] kloss_xyz (from rewatching lingxi’s session): engineer bot onboards bots with fleet rules in one message; bots catch their own rule conflicts; turned into a stealable 22-rule fleet playbook. Workshop / session timestamps (tester recaps — useful for rewatch) - [T] 0xCarnagee (~1h workshop framing): 04:12 first bot from scratch · 28:40 engineers hand real work · 44:25 running product w/o a PM · 52:25 founder’s stack / starting to ship. - [T] 0xCodila (compressed-course framing): 0:35 what is GrokBot · 34:17 first Grok Bot team workflow · 42:40 run +20 GrokBots in a graph & loop · 57:51 CoS and PM (delegate the delegation) · 1:08:09 full 24/7 company case. - [T] kaorixbt: 00:00 intro · 12:31 first team · 29:18 four layers of the GrokBot stack · 44:41 templates · 52:08 phone mode · path GrokBot → Roles → Agent Stack → Templates → Phone Mode → Autonomous Teams. Contests (Official / SpaceXAI / XCreators + tester summaries) Skipped (empty / low-signal — no actionable tip) WHAT IT IS - Livestream demo (101 / Founders “Introducing Grok Bot”): Create bots for different jobs; message bots like teammates; bots keep context in memory and improve; bots can be logged into your tools and use them like you do; automations/routines; share bots / shareable workflows / Shareable Templates. - Livestream demo (Why Grok Bot slide — 101 + Founders): Easy as iMessage; Always-on agents (24/7); Uses your tools like you; Finishes the work; Shareable workflows / Shareable Templates. - Livestream demo (“Finishes the work”): create bots for different jobs, give direction and let them figure it out, then set up automations and routines. - Livestream demo (Eng Why Grok Bot): No more caffeinated laptop; Beautifully available to all platforms; Control computer when needed; First-party coding agent integration. - Event framing (livestream): three-person team attempting to build a company/product in three days with Grok Bot; public X broadcast with “Grok Bot Galaxy” backdrop. - [T] Folder reinforcement: agent-native operating model (Human→Bot→specialists→humans); live build company name PLATFORM (tester claim). - Do not treat audience chat as product claims (buffering complaints, note-taking suggestions, Cursor/subscription questions, brand-partnership asks were chat — not slides/demos). HOW IT WORKS / MULTI-BOT TEAMS - Livestream demo (101): Separate bots for separate jobs — left-side list with email/comms and slide bots; named work bots on demo slide included Sales Outbound, Chief of Staff, Inbox Manager, Website designer, and Debug. - Livestream demo (101 multi-bot): Shared conversation with Amrita Venkataraman plus Email Ethan, Data Dan, and Slide Sonya; Members panel with Add Member. - Email Ethan: drafts external notes/emails; outbound emails require Amrita’s approval before anything leaves. - Data Dan: numbers, surveys, charts; handed off Coffee Data (n=100, avg ~1.9 cups/day, median 2, mode 3; buckets 0→8, 1→23, 2→29, 3→32). - Slide Sonya: owned the Grok Bot 101 deck and new slides; created a chart on the last slide from Coffee Data before Ethan emailed Jason. - Multi-bot action pattern (livestream): assign each bot a narrow role, pass structured outputs between them, gate external communications on human approval, and sequence dependent work (chart first, email second). - Livestream demo (Eng Meet the team): Lingxixi — Chief of Staff; Craig — UI Engineer; Steve — Devex Engineer; Hogan — Infra Engineer; Jenny — Head of Operations. - Livestream demo (Eng / Founders live fleet): steve (chief of staff), tater (engineer), hashbrown (reviewer), mash, prototyper/grokpot, PlanetScale Bot; Founders roster also showed Founding Eng, Growth Eng, Knowledge Base Manager, Creative Director, drop (merch), foil (tickets), Sip, and more. - Livestream demo (Founders CoS handoff): “Needs your attention” — sign in to tdraw, then “I’m done, continue” / Skip; agent creates share link after human auth. - Livestream demo (PM lessons): Named agents + separate memory (broad mission, scoped memory); Agents all the way down — EM agents manage IC agents that spin Cloud Agents; hierarchy beats one mega-prompt. - Livestream tip (Eng): “restate in your own words before executing.” COMMON USE CASES - Livestream slide “Grok Bot: Common Use Cases” organized by GTM, Engineering, Marketing, and Admins. - GTM — Account Health and Sales Outbound (livestream): pipeline built overnight; follow-ups drafted after every call; CRM kept current; outreach shipped in the user’s voice ready for review. - Sales Outbound demo (livestream): overnight pipeline/outbound — research prospects on the web, gather contact/account info from Salesforce, draft email in the user’s voice, check/update daily; routines included a morning outbound queue and an end-of-day send list; connected Gmail + Salesforce shown. - Engineering — Product Performance and Bug Reproduction (livestream): bugs reproduced overnight; repro pack dropped in the ticket; hotspots pulled before standup; outputs ready for review. - Marketing — Talent Scout and Paid Media (livestream): campaigns watched overnight; monthly budget drafted; creatives rotated when stale; spend shifts surfaced in Slack ready for review. - Admin — Chief of Staff and Expense Manager (livestream): calendars, travel, expenses, and inboxes handled end to end while the admin directs and bots run the busywork. - [T] XFreeze: livestream note-taking / screenshot companion bot as a practical meta use case. SETUP AND ONBOARDING [] Livestream demo: first-time setup asks “What do you mainly want me for? Whatever you pick, we can refine from there.” [] Setup choices shown: Data & analysis (spreadsheets, metrics, charts); Research & digests; Workflows & routines (recurring checks, reminders, automated follow-ups); or Something else (free-text). [] Second create screen categories visible: Work & projects, Customer support, Research & …, Coding & tools, Not sure yet (exact small labels partly GAP). [] Tip: start with a broad job category and refine afterward; use free-text when presets do not fit. [] Settings/general (livestream): workspace/tool connection controls; visible toggle for automatic actions; tool/app list (exact toggle semantics GAP). [] Notifications (livestream): toggle — notify when the bot finishes or needs input. [] Share this Bot visible in Sales Outbound settings panel (livestream). [] Founders onboarding demo: browser prompt “What’s your team name?” with app/bot tiles; later slide “Where teams and agents scale together.” [] Routines (livestream explanation): recurring tasks a bot runs on a schedule; can be set up by asking it. [] [T] Fleet tip: onboard with explicit fleet rules in one message; watch for bots flagging rule conflicts (kloss_xyz / lingxi). APPROVALS AND SAFETY [] Livestream demo (Google Form): bot surfaced an explicit action card with Approve and Deny before the computer/browser task — computer actions are not silently assumed. [] Action-history statuses shown: “Allowed once,” “Auto-review Paused This Action,” “Expired”; task runs on Grok Bot’s computer; live view of the bot’s computer/Google Forms made the external action inspectable. [] Tip: Review action history/status; one-time permission, paused review, and expiry are distinct states — do not treat them as completion. [] Closing 101 slide (livestream): bots get human approval when necessary; for enterprise use, external-facing actions should require approval; Email Ethan never sends an external email until its draft is approved. [] Tip/pitfall: confirm actions that create or change external artifacts. [] Founders cost slide (livestream): “Optimizing Costs” — “Routines are awesome (but audit them!)” with routine-manager UI. [] [T] Operating-model reminder: humans review, redirect, approve after specialists execute. TEACHING SKILLS (Slide Sonya) [] Livestream demo: “Slide Sonya” (Slide Maker) learned a Google Slides animation workflow from a demo and saved it as a reusable skill. [] Captured workflow: select object → Insert → Animation (Motion) → add animation → choose type (example: Fly in from top) → optionally By paragraph and speed; remove animation at end as cleanup, not part of the skill. [] Bot summarized inputs: slide/object, animation type, By paragraph, speed; assumed Google sign-in; default “Grok Bot 101” deck. [] After learning: offered “dry run on the title slide?” with Yes, dry run / Not now. [] Slide Sonya instructions visible: text clean and centered, at least 20 pt; use deck theme colors only; send a screenshot of the created slide back in chat. [] Workflow tip: watch a demonstrated procedure → summarize steps/inputs → save as skill → dry run for confirmation. [] Closing 101: bots have memory and can learn from video teachings; Slide Sonya remembers preferred fonts/slide design and can be taught animations/transitions for consistency.

540 Jev builds in a week. Most of them didn’t need Jev. It doesn’t write. It picks. If your answers aren’t a list, skip it. Still want one? Start with the pattern, not the demo. https://t.co/Q3iw1oWvod

full guide on how to master Opus 5.5 https://t.co/pcvcpEL9Mx

Putting five agents in a group chat and hoping they self-organize is how you get duplicated work and nobody checking anybody else. Coordination has to be picked on purpose, and the right pattern depends on what kind of work you are actually running. Generator-verifier is for quality-critical output. One agent generates, another checks the result, and rejected output loops back with feedback until it passes. Reach for this on code generation, fact-checking, and compliance work, where being wrong costs more than being slow. Orchestrator-subagent handles clear task decomposition. One lead agent plans and delegates, subagents handle focused tasks in parallel like security, tests, and style, and all of them return results back to the orchestrator. This fits code reviews, parallel checks, and any task that breaks cleanly into bounded subtasks. Agent teams are built for long-running parallel work. A coordinator assigns tasks through a queue to workers who persist across assignments, accumulating context and domain expertise instead of starting fresh each time. Use this for migrations, multi-step tasks, and anything that benefits from an agent actually specializing. Message bus fits event-driven pipelines. Agents publish and subscribe to events through a shared bus, so new agents can join without anyone rewiring the system. This is the right call for security operations, growing ecosystems, and workflows that change shape over time. Shared state works when the goal is collaborative findings. There is no coordinator at all, agents read and write directly to a shared store, and findings become instantly visible to every other agent. Reach for this in research synthesis, where you want no single point of failure and real-time collaboration between agents. Bookmark this before you default to one coordination pattern for every kind of agent work.