Skip to content
How I AIHow I AI

Grok Bot + Grok 4.6 + Cursor Origin - is Claude Code dead?

This week I’m doing a solo breakdown of everything xAI and Cursor have shipped recently, including Grok Bot, Cursor Origin, and the Grok 4.6 model. I set up five Grok Bots, ran Grok 4.6 through my Claire Weighted Index against GPT-5.6 Sol, Claude Sonnet 5, and Opus 5, and spent time actually using Origin as a GitHub replacement. Here’s what’s worth your attention, what’s overhyped, and where I’m personally putting my time. *What you’ll learn:* 1. The one Grok Bot feature no other agent platform has shipped yet, and why it made me actually use the product 2. What a week of real Grok Bot use revealed, and why I still reach for my OpenClaws 3. Whether Cursor Origin is a GitHub replacement or just a pretty redesign 4. Where Grok 4.6 landed on the Claire Index, and the one category where it genuinely surprised me *Brought to you by:* Bolt.new—Turn your idea into a real product: https://bolt.new/partner/howiai Jira AI SDLC—Get your tokens’ worth with Jira: https://jira.dev *In this episode, we cover:* (00:00) Why everyone’s quietly switching to Grok (01:52) Grok Bot overview and setup (03:22) My 5 Grok Bots (04:30) The killer feature: multi-account connectors (06:07) Grok Bot’s virtual machine and how it actually works (06:41) Experience overview (07:35) What I don’t love about Grok Bot (10:08) Grok Bot use cases and my honest verdict (12:20) Cursor Origin: the agent-native GitHub replacement (13:47) What Origin actually looks like in practice (14:59) Why I’m not switching from GitHub yet (17:42) What would get me to move over (18:52) Grok 4.6 and the How I AI Vibe bench (20:41) Claire Index results: where Grok 4.6 ranked (23:03) Design evals: where Grok surprised me (25:00) My conclusion and how I’m splitting my time now *Tools referenced:* • Grok Bot: https://x.ai/bot • Cursor: https://cursor.com/home • Cursor Origin: https://cursor.com/origin • OpenClaw: https://openclaw.ai/ • GitHub: https://github.com *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
Aug 18, 202627mWatch on YouTube ↗

At a glance

WHAT IT’S REALLY ABOUT

GrokBot, Cursor Origin, and Grok 4.6: practical hype check

  1. GrokBot is positioned as a simple, hosted, multi-agent “knowledge work” app whose standout value is its strong connector/MCP plugin system.
  2. The killer GrokBot feature is multi-account support per connector (e.g., several Gmails/Slacks at once), which Claire says competitors like Codex and Claude still don’t handle well.
  3. GrokBot’s tradeoff is lack of hackability and limited configuration (no model choice, less transparent tuning), plus an assistant “voice” she finds low-vibe and generic.
  4. Cursor Origin is an agent-native GitHub alternative that currently feels like a thinner wrapper around GitHub via sync/import, with too few differentiators to justify migrating yet.
  5. On Claire’s weighted benchmark, Grok 4.6 ranks surprisingly high—especially for design when given autonomy—suggesting Grok is a real competitor even if she still prefers other models for certain tasks.

IDEAS WORTH REMEMBERING

5 ideas

Multi-account connectors are GrokBot’s most defensible feature.

Claire highlights being able to attach multiple identities to the same connector (several Gmails, multiple Slack workspaces) as a daily-work unlock that other agent tools still routinely miss.

GrokBot wins on onboarding and reliability over customization.

Creating a bot is fast and straightforward, but you give up deep control (no model selection, less transparent configuration), making it better for “employee agents” than tinkerer setups.

The built-in VM makes GrokBot closer to ‘agent + computer’ than a chatbot.

Each bot gets a virtual machine that can browse, run terminal commands, and handle files, enabling lightweight OpenAI/Computer-Use-style workflows without heavy setup.

Personality and voice matter more in multi-agent systems.

Because users name bots and assign roles, Claire argues the “vibe” becomes a core UX feature; she finds GrokBot’s tone too generic/“sloppy” compared to her tuned custom agents.

Origin’s promise is clear, but the current product doesn’t beat GitHub inertia.

Agent-native primitives (agents as reviewers, commenting, integrations) are interesting, yet early access feels like fewer features plus a GitHub sync layer—insufficient to replace entrenched Actions/automations/codeowners.

WORDS WORTH SAVING

5 quotes

I don't know if you know this, but the whole OpenAI versus Anthropic thing is old news. Everybody I know is secretly becoming a Groq boy.

Claire Vo

So I think the magic of GroqBot, if I had to tell you one thing that is the magic of GroqBot, it is plugins.

Claire Vo

This experience of setting up multiple accounts per connector, huge, huge, huge benefit.

Claire Vo

I will tell you, GroqBot has not challenged me because it works simply and it works out of, out of the box.

Claire Vo

I can just spot GPT and Claude slop a mile away. A mile away.

Claire Vo

GrokBot multi-agent workflow and UIMCP/plugins and connector ecosystemMulti-account connectors (Gmail/Slack)Virtual machine per bot (web + terminal + files)Limits: model choice, tuning, “vibes,” controlCursor Origin: agent-native Git hosting and PR workflowGrok 4.6 results on the How I AI Vibe/Claire Index

High quality AI-generated summary created from speaker-labeled transcript.

Get more out of YouTube videos.

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