Build With AI

🔗 Deploy your own Hermes agent on Hostinger -10% off any plan with code COREY10: http://hostinger.com/corey10 (use code COREY10)

Grab the free step-by-step Hermes Second Brain setup guide here: https://corey-ganim.kit.com/60fc0fe6d9

In this solo episode, I walk through exactly how I built the ultimate AI second brain using Hermes and its built-in LLM Wiki skill — inspired by Karpathy's wiki setup. I break down the three core operations of the Hermes agent (ingest, query, lint), the three layers of the knowledge base (raw sources, the wiki, schema/tags), and why I chose Hermes over Claude Code, OpenClaw, or Obsidian for this build. From there, I show the full one-click deploy on a Hostinger VPS, the OpenAI model setup, the Telegram bot integration via BotFather, and the Markdownload Chrome extension trick I use to feed any tweet, article, or webpage straight into the wiki. By the end of this episode, you'll have a clear, step-by-step path to deploy your own self-improving second brain that gets smarter the more you use it.

Key Points
Hermes ships with a built-in LLM Wiki skill that handles the second brain function out of the box — your job is to curate sources, the agent's job is to summarize, tag, and file them away.

The knowledge base has exactly three layers: raw sources you give it (read-only), the agent-owned wiki of markdown files, and the schema/tags Hermes builds to make querying low-friction.

Run the Lint command roughly once a month — it audits your wiki for contradictions, sources older than 90 days, and oversized files that should be split for more accurate retrieval.

Deploy on a Hostinger VPS instead of locally — it's a one-click install with no terminal, cheaper than a Mac mini, always-on, and your data stays private.

The simplest workflow for feeding the wiki: use the Markdownload Chrome extension to clip any tweet, article, or webpage to markdown, drag it into your Telegram chat with Hermes, and tell it to add it to the wiki.

This is a compounding asset — on day 1 the knowledge base is the dumbest it'll ever be, but feed it consistently and by day 90 it becomes incredibly useful for retrieval.

Hermes agent VPS deployment on Hostinger (use code COREY10 for 10% off) - https://www.hostinger.com/vps/hermes-agent-hosting

Markdownload Chrome extension - https://chromewebstore.google.com/detail/markdownload-markdown-web/pcmpcfapbekmbjjkdalcgopdkipoggdi

Telegram BotFather - https://t.me/BotFather

OpenAI Codex - https://openai.com/codex

FIND ME ON SOCIAL X/Twitter: https://x.com/coreyganim Instagram: https://www.instagram.com/coreyganim/ LinkedIn: https://www.linkedin.com/in/coreyganim/ YouTube: https://www.youtube.com/@coreyganim

Tom Crawshaw (8+ years in automations, $25M+ in attributed e-com revenue) cracks open the content system that's pulled him millions of views. We walk through the Claude Code skill he built that handles voice profile, copywriting principles, hook scoring, image prompts, and a humanizer pass from one slash command. He also surfaces a hidden Claude Code feature called /insights that audits your full usage history and tells you what to build next. You'll learn how to turn messy ChatGPT workflows into a real skill, why Whisperflow is non-negotiable, and the one slash command 99% of Claude Code users are sleeping on.
Timestamps
00:00 Intro
00:30 Tom's automation background
03:30 Skills vs. Projects on context
08:30 Auto-updating voice profile from X
11:00 Nano Banana plus Canva workflow
23:30 Live demo: a Whisperflow post
34:30 Hook scoring with copywriting principles
46:30 The hidden /insights command
54:30 Skills vs. n8n vs. Lovable
Key Points
Skills beat Claude Projects on context. Projects load every reference file on every message. A skill works like a book: Claude pulls only the chapter it needs, so a full pipeline runs in one chat.
Tom's skill auto-updates his voice profile weekly. The X API pulls his last 7 days of posts, ranks by engagement, and rewrites the profile so the skill keeps drifting toward what's working.
/insights is the most slept-on feature in Claude Code. It audits your full session history and hands back a real report: what's working, where you're breaking your own rules, skills to build, and prompts to run.
Image gen is 80% Nano Banana, 20% Canva. Generate fast in the AI tool, then finish in Canva with magic grab and magic erase.
Whisperflow changed how Tom and Corey think, not just type. Speaking forces tighter thinking and makes prompts richer because adding context costs almost nothing.
Links
Claude Code: https://www.anthropic.com/claude-code
Whisperflow: https://wisprflow.ai/
Nano Banana: https://gemini.google.com/
Canva: https://www.canva.com/
n8n: https://n8n.io/
Tom's site: https://learnn8nautomation.com/
Build With AI: https://www.skool.com/buildwithai/about
FIND ME ON SOCIAL
X: https://x.com/coreyganim
Instagram: https://www.instagram.com/coreyganim/
LinkedIn: https://www.linkedin.com/in/coreyganim/
YouTube: https://www.youtube.com/@coreyganim
TOM ON SOCIAL
X: https://x.com/TomCrawshaw01
YouTube: https://www.youtube.com/@TheAIGrowthLab
Website: https://learnn8nautomation.com/

Free audit template Corey is giving away — https://audittemplate.ai

In this episode, I sat down with Chris Koerner and outlined how I sell AI assessments to small businesses.

Timestamps
00:00 – Intro
00:33 – The $1,000 AI audit pitch
01:10 – The lunch conversation that started it all
02:23 – Why 99 out of 100 owners need this
02:57 – Why Loom screen recording failed
04:25 – From Zoom calls to a voice agent
05:31 – Meet Annie, the AI interviewer
06:17 – Live demo of the voice agent
08:06 – How the voice agent was built (Retell + skills)
10:18 – Walking through a real assessment in Gamma
12:00 – The effort vs impact matrix
13:00 – Wedding venue saves 8 hours with Dash This
15:16 – Pricing journey: free to $1,000
17:30 – Why charging more makes upsells easier
18:02 – The full upsell menu breakdown
22:00 – Custom GPT knowledge system for a business broker
24:46 – Which industries this works best for
25:53 – Seven ways to find clients with no followers
26:39 – Hosting a local AI meetup
27:30 – Door-knocking businesses in 2026
29:25 – Using free audits to land warm contacts
30:30 – Running free AI office hours
31:30 – Hard-won lessons and the speed-to-lead upsell
34:36 – The simple Claude prompt that builds the audit
35:33 – Where to find Corey

Key Points

The business started from one lunch where a friend said he'd pay $1,000 just to be followed around for a day. After validating with 50–100 owners, Corey found 99 out of 100 small business owners need this — they just don't know which AI tools to use.

The upsell menu is built into the report. Common follow-ons: process optimization ($3K–$5K), Zapier or Make automation builds ($1K–$3K), custom GPT knowledge systems, CRM setups (high-level CRM at $3K–$5K), and speed-to-lead AI agents tied directly to revenue.

The seven-way client acquisition playbook works with zero followers: host a local AI meetup on Luma or Meetup.com, door-knock local businesses, run free audits for your network, host free AI office hours at coworking spaces or realtor offices, partner with well-connected locals, and lean on warm intros from your CEO peer group.

You don't need to be an AI expert. As Corey puts it, you just need to be one step ahead of your average client — which is about seven days of studying. The realtor's office where he hosted his free AI meetup turned into paying assessment work.

The Claude prompt to generate an audit is dead simple: attach the transcript, tell Claude to find off-the-shelf tools that fix the pain points, and point it at directories like Futurepedia or There's An AI For That.

FIND ME ON SOCIAL
X/Twitter: https://x.com/coreyganim
Instagram: https://www.instagram.com/coreyganim/
LinkedIn: https://www.linkedin.com/in/coreyganim/
YouTube: https://www.youtube.com/@coreyganim

In this solo episode, I walk through the exact process of setting up Claude Cowork from scratch — the right way — using the free Cowork Onboarding plugin I built and made open source. I go step by step through the full onboarding flow, from picking your workspace folder and connecting tools, to building three core context files (About Me, Brand Voice, and Working Style), generating global instructions that tie everything together, setting up scheduled tasks like a daily morning briefing and quarterly context review, and running an optional security review to lock in sensible rules.

Timestamps
00:00 – Why Cowork is useless out of the box
02:22 – Starting the onboarding flow from scratch
03:30 – Choosing workspace folder and onboarding path
04:37 – Workspace structure and file access permissions
05:45 – Connecting Google Workspace tools (Gmail, Drive, Calendar)
06:56 – Building context files: About Me, Brand Voice, Working Style
10:58 – Linking existing brand materials from Google Drive
12:44 – Generating global instructions from your context files
15:00 – Skills and plugin recommendations from the marketplace
17:24 – Setting up scheduled tasks: morning briefing and quarterly review
19:46 – Running the optional security review
23:23 – Wrapping up: what we built and the two manual steps left

Key Points

Most people skip the onboarding and then wonder why Cowork feels generic. The entire point of setting it up properly — building context files and global instructions — is so Claude never has to ask who you are again. Every session loads with that context automatically.
The three context files (About Me, Brand Voice, Working Style) are the foundation of the whole setup. Without them, Cowork is writing responses for a stranger. With them, it knows your business, how you communicate, and how you like your deliverables structured.
Global instructions are the piece most people miss. Once you paste your generated global instructions into Cowork's settings, every single session loads that context from the start — no repeating yourself, no re-explaining your preferences.

Links Mentioned

Free Cowork Onboarding plugin — download it to run the full guided setup described in this episode: https://return-my-time.kit.com/f00d78554c

Build with AI community — get the full onboarding plugin including the self-assessment, workflow audit, and custom skill blueprints tailored to your business: https://www.skool.com/buildwithai/about

WisprFlow — the talk-to-text tool used during the onboarding to answer Claude's questions faster: https://wisprflow.ai

Find Me on Social
X/Twitter: https://x.com/coreyganim
Instagram: https://www.instagram.com/coreyganim/
LinkedIn: https://www.linkedin.com/in/coreyganim/
YouTube: https://www.youtube.com/@coreyganim

I sit down with Leon van Zyl, who ran a web design company for 10 years and now teaches over 700 people how to build real applications with coding agents. We walk through his exact workflow for building professional, client-ready websites using Google Stitch for the design system and Claude Code for the build — no coding skills required. Leon shows the difference between a one-shot AI-generated site and what you get when you front-load the design system before touching code. By the end, you'll have a repeatable workflow for going from design concept to finished website — including custom AI images that match your brand.

Links Mentioned:
Google Stitch: https://stitch.withgoogle.com
Claude Code: https://docs.anthropic.com/en/docs/claude-code
Cursor: https://www.cursor.com
Next.js: https://nextjs.org
Stitch MCP Server Docs: https://stitch.withgoogle.com/docs/mcp
Stitch Skills: https://stitch.withgoogle.com/docs/skills

Timestamps
00:00 – Intro
00:06 – What you'll learn: design systems for client-ready websites
02:04 – Jumping into the screen share
02:25 – The problem: one-shot AI websites look terrible
03:52 – The Stitch workflow result: side-by-side comparison
07:32 – Starting from a vanilla Next.js project
08:50 – What is Google Stitch and how to get started
10:00 – Prompting Stitch with brand details, fonts, and colors
13:00 – Why design systems matter for coding agents
16:00 – Iterating on the homepage before building more pages
17:44 – Sharing Stitch designs with clients for approval
21:23 – Setting up the Stitch MCP server in Claude Code
23:18 – What an MCP server actually is (simple explanation)
25:56 – Pulling the design system into your project
28:47 – Memory files: Claude.md vs Agents.md explained
33:24 – Converting the Stitch design into a working website
35:06 – Installing the Stitch React Components skill
41:11 – When to use this workflow: client work vs personal projects
44:27 – Viewing the finished website vs the Stitch mockup
48:27 – Downloading and converting images to WebP for performance
53:46 – Generating custom AI images with Nano Banana Pro
58:14 – Final result with branded AI-generated hero image
01:00:48 – Key takeaways and wrap-up

FIND ME ON SOCIAL
X/Twitter: https://x.com/coreyganim
Instagram: https://www.instagram.com/coreyganim/
LinkedIn: https://www.linkedin.com/in/coreyganim/

FIND LEON ON SOCIAL
YouTube: https://www.youtube.com/@leonvanzyl