My Blog

Category: Jev

  • Grok Bot: Claude AI + Grok Bot = $61,000/month

    Channel: Ritesh Verma

    Introduction

    Ritesh Verma’s video explains how he combines Claude AI as the strategic “brain” with Grok Bot as an operational “computer‑using” employee to run an AI‑driven consulting business. He claims the setup generated roughly $61,000 in revenue over the last 30 days while he traveled to four countries.

    What the video covers

    The presentation walks through the architecture of the AI employee team, the specific roles Claude and Grok Bot play, how the team is built and trained, and the concrete workflows used for lead generation, advertising, and content creation. It also shares the tools involved, example numbers, and a set of action items for viewers who want to replicate the model.

    Step‑by‑step walkthrough

    • Claude as the brain – Claude designs the overall strategy, creates system prompts, and defines the organizational structure. In the video Claude writes a COO‑builder prompt for Verma’s consulting company, Agent Rise.
    • Grok Bot as the operator – Grok Bot runs a personal computer and executes tasks inside the business (WhatsApp messaging, Meta Ads management, content repurposing, etc.) rather than relying solely on API‑only chat.
    • Building the org chart – Using Claude’s COO prompt, Grok Bot proposes a structure with managers and individual contributors (ICs) across sales, client acquisition, content, and scaling. Verma mentions an example org chart of roughly 4 managers and 11 ICs (about 16 seats). He removes an AI “closer” role and adds a short‑form script writer.
    • Training Grok Bot employees – Skills are sourced from a Claude Skills zip file (script writing, repurposing, director, id8). Additionally, a Google Drive voice profile built from the highest‑converting YouTube scripts is used to align the bots’ tone with proven messaging.
    • Speedy SDR on WhatsApp – Grok Bot monitors a raw lead sheet. If a lead appears only in the raw data and has not yet been booked (i.e., not on the lead tracker), Grok Bot sends a WhatsApp message. Leads that already have a booked call are skipped to avoid duplicate outreach.
    • Ads manager workflow – A Meta Ads MCP/developer app with a system‑user token (ads_read, ads_management) lets Grok Bot audit campaigns daily. Under‑performing ads are paused or killed. Verma cites an example where the cost per acquisition (CPA) hovered around $30.
    • Scaling rule – Before adding any new hire, Verma asks whether the task could be performed by a Grok Bot employee. If yes, the role is filled by a bot; if not, a human is required. He notes that creative/design work still relies on humans for now, while growth is driven by more content, higher ad spend, and fresh creatives.

    Tools and numbers mentioned

    • Revenue claim: $61,000 in the last 30 days (as stated by Verma).
    • Travel: Business operated while Verma visited 4 countries.
    • Claude usage: Since February (approx. timeline).
    • Grok Bot usage: Roughly 45 days at the time of the video.
    • Claude model referenced: Claude Fable 5.1 medium (as spoken).
    • Org chart example: 4 managers, 11 ICs (~16 seats).
    • Ads performance: Example ~$30 CPA on Meta ads.
    • Free offers: 15 free roadmap strategy calls; claims clients can grow from $1k to $20k+/mo.
    • Tools list: Claude, Grok Bot, Google Drive/Sheets, WhatsApp, Meta Ads (developers.facebook.com apps), Agent Rise, Slyte, Skool WiFi Life.

    Notable prompts and quotes

    Claude becomes the brain that designs the system, and Grokbot becomes an operator that runs it entirely.

    If a raw lead appears on lead tracker and they have booked a call, do not WhatsApp them. If they’re only in raw lead data and not on lead tracker… those are the only people to message.

    Can this hire be a Grockbot employee? If so… If not, you need a human employee.

    Caveats / hype check

    The video presents a large revenue figure without showing a profit‑and‑loss statement or detailed financials on screen. The claim of a seven‑figure business relies on the stated $61k/month extrapolated over a year. The presentation includes a strong call‑to‑action for a free community, 15 strategy calls, and a done‑for‑you offering (Slyte). While the WhatsApp and Meta Ads automations appear to be real workflows demonstrated in the video, the results shown may be cherry‑picked. Viewers should treat the income claim as aspirational rather than guaranteed.

    Concrete next actions

    • Draft a COO‑style organizational prompt for Grok Bot that outlines workstreams such as content, lead handling, and operations before launching any bots.
    • Export reusable Claude Skills (script writing, repurposing, etc.) as Markdown files and use them to train matching Grok Bot employees in the same way Verma describes.
    • If testing a WhatsApp‑based SDR, replicate the “raw lead vs booked lead” gate in Google Sheets: only message leads that exist in the raw sheet but are absent from the lead tracker.
    • Set up a Meta Ads developer app with the required system‑user token (ads_read, ads_management) and create a daily audit routine that pauses campaigns exceeding a target CPA threshold.
    • Apply the scaling heuristic: for any new role or task, ask whether a Grok Bot employee could perform it; if the answer is no, plan to hire a human for that function.

  • AI Receptionist: Claude Opus 5.5 Just Replaced GHL $297 to $0 (No Subscription)

    Channel: ambITious | AI

    Introduction

    The video from ambITious | AI demonstrates how to replace GoHighLevel’s $297‑per‑month subscription with a self‑hosted agency CRM and website builder that can be assembled in roughly one hour using Claude Opus 5.5, Claude Code, and Firebase. The presenter frames the approach as a way to eliminate recurring software rent while retaining full ownership of client data and workflows.

    What the Video Covers

    The presentation walks through the end‑to‑end process of provisioning a CRM, branding it, connecting communication channels, and generating client‑ready websites. It also outlines a pricing model for selling the solution to local SMBs and highlights the risks associated with staying on a platform like GoHighLevel.

    Step‑by‑Step Walkthrough

    • Initial CRM deployment (≈15 minutes) – Using a single prompt, Claude Opus 5.5 reads the repository’s claude.md file and instructs Claude Code to scaffold the CRM inside VS Code. This step configures Firebase as the backend, imports brand assets (logos, colour palette), and sets up the core database schema.
    • Full operational setup (≈60 minutes total) – After the base CRM is live, the presenter adds API keys for AI services (Claude Opus 5.5 for chat), SMS providers, voice‑call platforms, and payment gateways. Each integration is triggered through additional Claude Code commands that update the Firebase functions and frontend components.
    • Website builder (≈20 minutes per site) – A separate Claude‑driven workflow generates a custom website for each client. The output includes a video hero loop, dark‑mode UI, auto‑generated SEO metadata, and favicons. The builder also provisions a contact form, an AI‑powered chat widget, a voice‑AI agent, and a knowledge base trained on the client’s business information.
    • Data routing – Submissions from contact forms, transcripts from chat widgets, and logs from voice calls are automatically written to the appropriate sub‑account within the CRM, ensuring a unified lead‑management view.

    Tools, Numbers, and Metrics Mentioned

    • Software: Claude Opus 5.5, Claude Code, VS Code, Firebase, Go High Level (GHL)
    • Cost comparison: GHL charges $297/month; the self‑hosted setup eliminates that fee, saving over $3,500 per year per agency.
    • Time estimates: 15 minutes for base CRM, 60 minutes for full deployment, 20 minutes per client website.
    • GHL platform risks: workflows stop after 14 days of non‑payment, sub‑accounts lock on day 1, and all data/funnels are permanently deleted after 90 days.
    • Revenue model: Charge SMBs $297/month for a managed website and lead delivery. Example outcomes: 3 clients → $10,692/year; 30 clients → $106,920/year.

    Caveats and Hype Check

    “That’s not software, that’s rent on your own business.”

    While the video markets the solution as a $0 subscription, it notes that variable costs remain for hosting (Firebase), LLM usage (Claude Opus 5.5), voice services, and SMS. The presenter also promotes a specific repository (“Lead Stack”) and a paid community (“AI Plus”), which may involve additional fees or access requirements. The claim that Claude Opus 5.5 replaces GHL should be understood in the context of the demonstrated workflow; it does not guarantee feature‑parity with every GHL module, especially advanced automation or marketplace integrations.

    Concrete Next Actions

    • For AI Receptionist: Adopt the auto‑provisioning model shown to bundle voice AI chat, web chat widgets, and CRM auto‑logging into turnkey client sites.
    • For Jev/Claude Automation: Standardise project setup around a claude.md file so Claude Code can automatically install dependencies, brand assets, and database schemas.
    • Evaluate the ongoing variable costs (Firebase read/write, Claude token usage, voice/SMS APIs) to ensure the $297/month client price covers expenses and delivers a target margin.
    • Test the end‑to‑end flow with a pilot client: deploy a sample website, submit a lead via the form, verify that the lead appears in the CRM sub‑account, and confirm that chat and voice interactions are logged.
    • Document the specific API keys and quota limits required for each integration to create a repeatable onboarding checklist for new clients.

  • The Drop Drive: How I create viral animated reels using HyperFrames + Claude Code

    Channel: Science Based AI

    Introduction

    The Science Based AI channel presents a practical workflow for creating short‑form animated reels by combining HyperFrames (a free animation tool) with Claude Code (the coding‑assistant interface for Claude). The presenter, Ben from Stack Health, shares how his team generated over 200 k short‑form views in 30 days using this approach, and outlines three concrete use cases: animated charts, text‑plus‑visual explainers, and liquid‑glass title effects. The video also offers six quality‑focused tips and a brief hype check.

    What the video covers

    • Claimed results: Stack Health achieved >200 000 short‑form views in the last 30 days using HyperFrames; Ben is the head of content and previously worked on growth at a YC‑backed startup.
    • Use case 1 – animated charts: starting from a Pinterest reference board, using Claude to extract or generate data, then feeding that data into Claude Code/HyperFrames to produce a ~7‑second 9:16 bar chart with safe‑zone edits.
    • Use case 2 – text + visual explainers: providing a full script to Claude, asking where animations should appear, then requesting standalone prompts so multiple Claude Code chats can render individual clips in parallel (rather than generating the whole video at once).
    • Use case 3 – liquid‑glass titles: pointing Claude at Apple’s liquid‑glass design documentation, optionally adding green‑screen bubble overlays or PNG logos.
    • Six production tips: use reference images; limit each AI‑generated shot to 4–10 seconds; specify camera motion (push, pan, static, fade); iterate one variable at a time; leave music, captions, and timing cuts to a human editor; borrow visual languages from sources such as Vox, Apple, luxury, tech, or documentary styles.
    • Additional applications: launch videos, product demos from screen recordings, explainers, and social‑ad overlays.
    • Sponsorship note: the video is sponsored by Typeless, which offers a $5 discount on its paid plan.

    Step‑by‑step walkthrough

    Animated charts

    1. Create a Pinterest board with chart styles you like (e.g., Vox‑style bar charts).
    2. Ask Claude to interpret the board and output the data series you need (labels, values, colors).
    3. Pass that data to Claude Code together with a HyperFrames prompt that specifies a 7‑second, 9:16 aspect ratio chart.
    4. Run the prompt; HyperFrames generates the animation. Review the output and apply a safe‑zone pass (ensuring key elements stay within the central 90 % of the frame).
    5. If needed, tweak one variable (e.g., bar color or speed) and re‑run, keeping everything else constant.

    Text + visual explainers

    1. Write a complete voice‑over script for the explainer.
    2. Feed the script to Claude and request: “Identify moments where a visual animation would reinforce the narrative.”
    3. For each identified moment, ask Claude to produce a standalone prompt that describes the animation (duration, camera motion, visual elements).
    4. Open separate Claude Code chats (or tabs) and run each prompt in parallel to generate 4–10‑second clips.
    5. Collect the clips and hand them to a human editor for sequencing, music, captions, and final timing cuts.

    Liquid‑glass titles

    1. Locate Apple’s liquid‑glass design guidelines (publicly available design notes).
    2. Prompt Claude with those guidelines and ask for a HyperFrames prompt that recreates the liquid‑glass look for a title card.
    3. Optionally, add a green‑screen bubble overlay or import a PNG logo to composite later.
    4. Generate the title clip, review for fidelity to the liquid‑glass aesthetic, and iterate on one parameter (e.g., refraction intensity or background blur) at a time.

    Tools & numbers

    • HyperFrames – free animation tool used for all three use cases.
    • Claude / Claude Code – the AI assistant; Claude Code subscription starts at ~$20 / month.
    • Codex – mentioned as an alternative plan around $8 / month.
    • Pinterest – source for reference boards.
    • Typeless – sponsor offering $5 off a paid plan.
    • Demo chart specifications: ~7 seconds length, 9:16 vertical aspect ratio.
    • Claimed performance: Stack Health >200 000 short‑form views in the preceding 30 days.

    Caveats / hype check

    “View count is company claim without public breakdown. Typeless sponsorship. Emphasizes many online HyperFrames demos aren’t mostly HyperFrames—his demos look stronger, still curated.”

    The presenter notes that the view‑count figure is an internal claim and lacks independent verification. The video is sponsored by Typeless, which may influence the tone toward the promoted discount. While the workflow produces polished results, the creator acknowledges that many publicly shared HyperFrames examples rely heavily on post‑production editing; his own demos appear stronger but still involve curation and human oversight.

    Concrete next actions

    • Drop Drive pilot: Select one data‑driven or explainer reel idea. Gather a Pinterest reference board, use Claude to extract or generate the needed data, then run a Claude Code/HyperFrames pass to create a safe‑zone‑checked 7‑second 9:16 clip.
    • Jev / Claude Code style pack: Develop a reusable prompt template (e.g., a “noir” or brand‑specific style) that includes camera motion descriptors, lighting notes, and duration limits. Store this template for parallel clip generation across future projects.
    • Iterative testing: For each generated clip, change only one variable (color, speed, blur) at a time, compare outputs, and keep the version that best matches the reference visual language.
    • Human‑editor hand‑off: After collecting AI‑generated shots, bring them into a traditional editing timeline to add music, captions, and final timing cuts, ensuring the final reel meets platform‑specific requirements.

  • The Drop Drive: How to Turn One Piece of Content Into a Week’s Worth of Posts

    Channel: Luxe Automation

    Introduction

    The Luxe Automation video demonstrates a systematic way to stretch a single long‑form piece of content into a full week’s worth of social‑media output. By creating a Claude Skill called “long‑form social repurposer,” the presenter shows how any source—blog post, newsletter, podcast transcript, case study, webinar, etc.—can be turned into a ready‑to‑review set of 30 social posts that are automatically written into a Google Doc.

    What the Video Covers

    The walkthrough begins in Claude’s “Customize” interface, where a new skill is built. The skill’s prompt defines its responsibilities, lists the types of long‑form inputs it accepts, and outlines platform‑specific rules for each social network. Once the skill is saved, running it on a source document produces a predefined output pack:

    • 5 LinkedIn posts
    • 10 Twitter/X posts
    • 5 Twitter/X threads
    • 5 Instagram captions
    • 5 short‑form video hooks

    The skill writes the results directly into a Google Doc and includes review links so a team can edit or approve the content before publishing. The video demonstrates the workflow with four different sources:

    • A Stripe × Marc Andreessen interview
    • An Airbnb founder letter
    • An AI customer‑service strategy article
    • An Asana meeting‑management article

    Each demo ends with a Google Doc containing the full 30‑piece set, ready for review.

    Step‑by‑Step Walkthrough

    1. Open Claude and navigate to the Customize section.
    2. Click to create a new skill and give it a name (e.g., “long‑form social repurposer”).
    3. In the skill editor, paste a detailed prompt that:
      • States the skill’s goal: take any long‑form source and generate social media copy.
      • Lists allowed input formats (blog, newsletter, podcast/interview transcript, case study, webinar, etc.).
      • Specifies the exact output quantities for each platform (as shown above).
      • Instructs the skill to write the results into a Google Doc and provide review links.
    4. Save the skill and optionally preview its contents to confirm the prompt is correct.
    5. Run the skill against a chosen long‑form document (the video shows uploading the source file or pasting its text).
    6. Claude processes the input and returns a Google Doc link containing the 30 prepared posts.
    7. Open the Doc, review the copy, make any needed edits, and then schedule or publish the content across the respective platforms.

    Tools and Numbers Mentioned

    • Claude Skills – the automation engine that holds the repurposing prompt.
    • Google Docs – the destination for the generated copy, enabling easy review and collaboration.
    • Output pack: 30 pieces per long‑form input (5 LinkedIn + 10 Twitter/X + 5 threads + 5 Instagram captions + 5 short‑form video hooks).
    • Demo sources: Stripe/Andreessen interview, Airbnb founder letter, AI customer‑service strategy article, Asana meeting‑management article.

    Caveats / Hype Check

    “Take a long‑form content, generate social media content, and add it to Google Docs for review.”

    The video’s title suggests a “week’s worth” of posts, but the demonstrated output is a fixed 30‑piece pack rather than a variable daily schedule. The full prompt is not shown in the video; viewers must comment the word “prompt” on the YouTube page to receive it (a comment‑gated approach). No independent quality metrics are presented—only the scrolling Google Docs are shown as proof of output. The description also contains an affiliate Apify link, which may influence the presenter’s recommendations.

    Concrete Next Actions

    • Create a Claude Skill that mirrors the “long‑form social repurposer” described in the video, using the same input allowances and output quantities.
    • Store the skill’s markdown (or prompt text) in a shared vault so that both the Drop Drive team and any content bots can reference a single repurposing standard.
    • Set up an automation trigger (e.g., when a new Business‑playlist blog note is added) that runs the skill and deposits the resulting Google Doc into a designated review folder.
    • Schedule a brief review meeting after each generation to verify tone, brand compliance, and platform‑specific formatting before publishing.
    • If interested in the exact prompt used by the presenter, leave a comment with the word “prompt” on the YouTube video to request access.