CHAPTERS
- 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
- 2:00 – 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
- 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”
- 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
- 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
- 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)
- 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
- 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
- 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
- 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)
- 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
- 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
- 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
- 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
