Skip to content
How I AIHow I AI

7 Grok Bot agents I use every day

I’m running about 30 active agents at any given moment, and in this episode I break down my full Grok Bot setup: what it is, how it compares to OpenClaw, and the nine bots I’ve built for work and my personal life. We go deep on Chief (my chief-of-staff bot sweeping six inboxes and multiple Slack workspaces), TradBot (the family agent that prints a kitchen-table newspaper for my kids), two engineering bots handling my PR queue and SOC 2 compliance monitoring, Holly Helpdesk, and a handful of personal bots I didn’t expect to actually love. I also walk through how I migrated everything from OpenClaw, including the script I used to export and transplant each agent’s identity and schedule. *What you’ll learn:* 1. The three primitives Grok Bot is built on, and why one of them changes what agents can actually do 2. How Chief, my general-purpose chief of staff, handles a scope I didn’t think a single bot could manage 3. The writing quirk I noticed immediately with the Grok model, and what I did about it before letting it near my inbox 4. Why I created a family agent, what it produces every morning, and the design principle I used that has nothing to do with a screen 5. The two engineering bots doing work I used to do myself, and how one of them handles compliance in a way that surprised me 6. How Holly Helpdesk started getting five-star reviews from customers who had no idea they were talking to a bot 7. The personal bots I built mostly on a whim, and the one I now look forward to every Monday morning *My bot templates:* https://x.com/clairevo/status/2093496602522714362 *Brought to you by:* WorkOS—Make your app enterprise-ready, with SSO, SCIM, RBAC, and more: https://workos.com?utm_source=lennys_howiai&utm_medium=podcast&utm_campaign=q22025 Hyperagent—Deploy fleets of agents that handle real work: https://www.hyperagent.com/howiai *In this episode, we cover:* (00:00) Why I migrated from OpenClaw to Grok Bot (02:10) Grok Bot overview: the three core primitives (07:41) Chief: my chief-of-staff bot (11:51) OpenClaw vs. Grok Bot (12:41) TradBot: my family agent (19:51) LGTM the PR Closer (22:03) Lockdown: SOC 2 control monitoring bot (24:00) Holly Helpdesk: customer support (26:58) Penny Pincher: subscription audit, insurance negotiation, Rolex shopping (29:37) ShopZilla and Sylvie Style: personal shopping and wardrobe bots (32:54) How to migrate your OpenClaws (34:26) Final take *Blog and detailed workflow walkthroughs from this episode:* Grok Bot Agent Templates and Workflows: https://www.chatprd.ai/how-i-ai/grok-bot-agent-templates-and-workflows ↳ How to Build a Personal AI Stylist to Curate Your Wardrobe: https://www.chatprd.ai/how-i-ai/workflows/how-to-build-a-personal-ai-stylist-to-curate-your-wardrobe ↳ How to Create an AI-Powered Family Newspaper and Logistics Coordinator: https://www.chatprd.ai/how-i-ai/workflows/how-to-create-an-ai-powered-family-newspaper-and-logistics-coordinator ↳ How to Automate Customer Support with a 5-Star AI Agent: https://www.chatprd.ai/how-i-ai/workflows/how-to-automate-customer-support-with-a-5-star-ai-agent *Tools referenced:* • Grok Bot (SpaceXAI multi-agent platform): https://x.ai/news/introducing-grok-bot • OpenClaw (previous agent platform): https://openclaw.ai/ *Where to find Claire Vo:* ChatPRD: https://www.chatprd.ai/ Website: https://clairevo.com/ LinkedIn: https://www.linkedin.com/in/clairevo/ X: https://x.com/clairevo _Production and marketing by https://penname.co/._ _For inquiries about sponsoring the podcast, email jordan@penname.co._

Claire Vohost
Sep 2, 202636mWatch on YouTube ↗

CHAPTERS

  1. 0:00 – 2:00

    Why Claire switched from OpenClaw to Grok Bot (and what you’ll learn)

    Claire explains that after several weeks with Grok Bot, she’s replaced nearly all her OpenClaw agents. She previews a hands-on tour of practical bots you can copy, plus what Grok Bot still lacks.

    • Moved almost entirely from OpenClaw agents to Grok Bot
    • Episode focus: practical, stealable bot use cases
    • Will cover what’s better, what’s missing, and what she’s excited about
    • Bot links/templates will be shared in show notes
  2. 2:00 – 4:01

    Grok Bot platform tour: bots, plugins/connectors, computer, and routines

    Claire gives an overview of Grok Bot’s UI and the three key primitives: individual bots (agent threads), plugins/connectors, and a built-in cloud computer with scheduled routines. She highlights how the system maps well to her “hire bots like coworkers” mental model.

    • Bots are scoped agent threads with names/roles; naming helps infer purpose
    • Plugins combine skills + connectors (Gmail, Calendar, Drive, GitHub, Sentry, etc.)
    • Built-in cloud VM enables web login, installs, running code, local repo work
    • Routines let bots run on schedules for proactive work
  3. 4:01 – 7:03

    Why Grok Bot’s connector experience wins (especially multi-account)

    Claire describes why Grok Bot clicked for her: seamless connector setup and the ability to connect multiple accounts per plugin. For entrepreneurs managing many identities (emails, Slacks, calendars), this becomes a major quality-of-life advantage.

    • Bots often prompt for needed connectors; setup is lightweight via OAuth
    • Multi-account per plugin is a standout feature (multiple emails/Slacks/calendars)
    • Reduces friction for managing several businesses/contexts in one workspace
    • Makes agent workflows feel more integrated and “out of the box”
  4. 7:03 – 8:03

    What’s still missing: single-player limitation and desire for group chat bots

    Claire calls out Grok Bot’s current limitation: bots aren’t truly multiplayer and can’t join a shared group chat. While templates can now be shared, she argues it’s not equivalent to collaborating with the same bot in a team conversation.

    • Bots are currently single-player (not shared conversationally in real time)
    • Templates can be shared, but it’s not the same as a shared bot instance
    • OpenClaw/Eve-style multiplayer still has an edge here
    • Claire hopes for a future “bot in the group chat” feature
  5. 8:03 – 9:35

    Chief: the hourly chief-of-staff that replaced Polly (inbox, calendar, Slack)

    Claire introduces Chief, her new chief-of-staff bot that effectively replaced her beloved OpenClaw agent Polly. Chief runs frequent sweeps across multiple inboxes/calendars/Slacks and only escalates high-signal items, plus delivers briefings and weekend previews.

    • Hourly sweeps of inbox, calendar, and Slack across many accounts
    • Filters noise: archives/ignores low-importance items, escalates what needs action
    • Provides morning briefing and weekend plan-ahead summaries
    • Example: flags traffic spikes and advises when to investigate
  6. 9:35 – 12:36

    Tuning Chief: matching Claire’s voice + routine proactivity differences vs OpenClaw

    Claire explains how she trained Chief to write more like her, noting Grok’s clipped/over-compressed writing style by default. She also compares proactivity: OpenClaw felt more naturally proactive, while Grok Bot requires clearer routine scheduling and explicit setup.

    • Trained bot on her email voice (short, warm, funny; “hey”; signs “c”; no em dashes)
    • Grok model tends to be overly brief/token-efficient, sometimes unclear
    • She still prefers human-authored email for high-stakes messages
    • Grok routines are powerful but must be explicitly configured (less “heartbeat” by default)
  7. 12:36 – 17:10

    TradBot: the family operations agent that gets you off your laptop

    Claire shares her household agent, TradBot, designed to reduce screen time while keeping family logistics under control. It generates a “kitchen table newspaper” digest for kids and parents and drives just-in-time coordination around pickups and weekend chaos.

    • Goal: agent should reduce time on computer and increase family time
    • Creates a printed kitchen-table newsletter with schedule, reminders, and weather
    • Per-kid updates from school emails/homework; parent task list
    • Includes kid-friendly news/fun facts for breakfast conversation
  8. 17:10 – 19:41

    Just-in-time parenting coordination: pickup checks + weekend preview systems

    TradBot also runs routines timed to real life: a daily pre-pickup prompt and a Friday lookahead for weekend activities. These routines help coordinate who picks up, what gear is needed, and how to manage conflicting schedules across multiple sports.

    • 2:30pm daily prompt: who’s picking up, what to bring (gi, snacks), conflicts
    • Friday preview: consolidates Saturday/Sunday schedules, carpools, travel time
    • Handles frequent schedule changes and reduces last-minute surprises
    • TradBot template is shared for others to copy
  9. 19:41 – 22:14

    LGTM the PR Closer: keeping pull requests moving (and delegating work to Cursor)

    Claire introduces an engineering-focused bot that triages PRs daily, nudges reviews, and keeps the merge queue healthy—especially important under SOC 2 review expectations. It can also kick off Cursor cloud agent jobs to handle tasks like rebasing or fixes.

    • Daily PR scan: what to merge, close, rebase, or respond to
    • Acts like a persistent eng manager to reduce PR backlog
    • Supports stacked PR workflows and bot feedback tracking
    • Can trigger Cursor cloud coding jobs for automated changes
  10. 22:14 – 23:45

    Lockdown: SOC 2 control monitoring + vulnerability triage into PRs

    Lockdown automates daily checks of the SOC 2 control dashboard, ensuring monitors stay green and issues are addressed within SLA. When vulnerabilities appear, it can triage, generate remediation PRs, and route approvals to humans.

    • Logs into SOC 2 dashboard and checks control status daily
    • Escalates only controls that need human attention or are outside SLA
    • For code-related findings, triages vulnerabilities and opens PRs
    • Covers operational controls too (audits, offboarding reminders)
  11. 23:45 – 26:48

    Holly Helpdesk: customer support agent with approval-gated actions (refunds, fixes, community)

    Claire describes migrating her helpdesk agent to Grok Bot and seeing a noticeable boost in perceived support quality. Holly sweeps Intercom and email, uses a support playbook, can initiate bug fixes via Cursor, and requests explicit approvals for sensitive actions like Stripe refunds.

    • Hourly sweep of Intercom + email; handles refunds and technical support
    • Uses playbooks/tools; can trigger Cursor cloud agents to fix bugs
    • Approval-gated “agent action” flow for Stripe refunds (human-in-the-loop)
    • Weekly review: update docs/support playbook to increase self-serve
    • Also manages/energizes the community Slack with prompted engagement
  12. 26:48 – 32:51

    Personal bots for money + shopping: Penny Pincher, ShopZilla, and Sylvie Style

    Claire closes with personal agents that save time and (sometimes) money: Penny Pincher audits subscriptions and negotiable renewals, ShopZilla finds hard-to-search items, and Sylvie Style builds a wardrobe plan from a Pinterest board and weekly sale scouting.

    • Penny Pincher: finds subscriptions to cancel, trials ending, and negotiation opportunities
    • Insurance rate shopping + reminders; identifies unused services (e.g., Audible)
    • Can even shop/price-check luxury items and negotiate with sellers
    • ShopZilla: browser-based shopping for specific dimensions and constraints
    • Sylvie Style: analyzes Pinterest style, learns from expert advice, builds a shoppable wardrobe plan + Monday sale haul routine
  13. 32:51 – 34:22

    Migrating (and retiring) OpenClaw agents: Lifeguard export + “brain transplant” into Grok Bot

    Claire explains her migration workflow using a “Lifeguard” rescue bot to export a secrets-free package of agent identities, schedules, and configuration. She then uploads the bundle into Grok Bot to recreate personalities and routines, and finally shuts down the old agents cleanly.

    • Lifeguard bot exports agent setup (identities, crons, rules) as a zip
    • Upload subfolders into Grok Bot to transfer behavior and structure quickly
    • Removes/turns off old crons and gateway configs to retire agents safely
    • Highlights OpenClaw maintenance burden as the key driver for switching
  14. 34:22 – 36:20

    Final take: UX and “works out of the box” simplicity beat maximum power (for now)

    Claire concludes that OpenClaw set a high bar for autonomous teammates—especially multiplayer—but was too hard to maintain, even for a technical user. Grok Bot’s simple UX and reliable default experience make it a strong “90% coworker agent” solution she’s now running at scale.

    • OpenClaw: powerful, great multiplayer and autonomous teammate patterns
    • But maintenance overhead was too high (even with technical setup)
    • Grok Bot: simple, functional, fast to configure, strong default behaviors
    • Claire is running ~30 bots and invites viewers to share use cases

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.