Build With AI

Claude Code just dropped routines, and when I first saw the three options — routine, schedule, and loop — I had no idea when to use which. In this video, I break down all three modes in plain language and then demo building a routine from scratch using an X trend scanner I already had in my skill library. You'll see the full setup: GitHub connection, system prompt config, trigger options, and connector permissions. By the end, you'll know exactly which mode to use for any automation you want to build and how to get your first routine live.

Links Mentioned:
Claude Code Routines: https://claude.ai/code/routines
GitHub: https://github.com

Timestamps
00:00 – Intro: The confusion with Claude Code's new features
00:20 – The three modes: routine, schedule, and loop
00:50 – When to use each mode (simple breakdown)
01:10 – Using Claude Code to find a skill to demo
01:45 – Selecting the X scan routine
02:00 – GitHub requirement for routines explained
02:18 – Creating a new routine at claude.ai/code/routines
02:35 – Naming your routine and connecting your GitHub repo
02:50 – Dropping in your system prompt
03:05 – Setting the schedule trigger (10am Eastern daily)
03:20 – Configuring connectors and permission sets
03:40 – Running on demand and reviewing the output
04:10 – Full recap of all three modes

Key Points

* Claude Code has three automation modes — routine (runs on Anthropic's cloud, set it and forget it), schedule (needs local access, also available in Cowork), and loop (immediate execution in the CLI). Picking the wrong one means your automation won't work the way you expect.

* Routines require a GitHub repository. You can't create one without it, so get your repo connected before you start.

* The whole setup happens at claude.ai/code/routines — no coding required beyond having a system prompt in markdown format ready to paste in.

* Routines support three trigger types: time-based schedule, GitHub event, or API call. That gives you flexibility depending on whether you want it cron-based, push-based, or fired from another system.

* The X trend scanner ran automatically and surfaced several trending topic candidates with suggested content angles — zero manual research, just results ready to use.

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

FIND NICK ON SOCIAL
X: https://x.com/NickSpisak_
LinkedIn: https://www.linkedin.com/in/nicholasspisak/
YouTube: https://www.youtube.com/@UCusMlMDWZS0uOlhgL0M_q-A

Grab the free Google Doc to build and deploy your first Claude Managed Agent in 60 seconds: https://return-my-time.kit.com/2872b904f5

I sit down with Nick Spisak, an AI agent builder who deployed his first Claude Managed Agent the same week Anthropic released the capability, to break down exactly what this platform is, who it's for, and when it makes financial sense to use it. We walk through the four user personas Claude Managed Agents is built for.

Links Mentioned:
Corey's X article: https://x.com/coreyganim/status/2042286607449874527
Nick's X article: https://x.com/NickSpisak_/status/2041949191887262164

Timestamps
00:00 – Intro
00:05 – What is Claude Managed Agents?
00:29 – Architecture: decoupling tools, sessions, and orchestration
01:15 – Who managed agents is and isn't for
01:33 – The four user personas breakdown
03:58 – Why AI Tinkerers should stick with Claude Code subscription
04:21 – Free Google Doc: build your first agent in 60 seconds
05:28 – Platform-as-a-service model explained
05:43 – Cost comparison: Managed Agents vs Agent SDK
06:09 – Live look inside platform.claude.com
06:23 – Workbench, sessions, and output walkthrough
08:16 – Sessions: tool calls vs. finished output explained
08:31 – Analytics dashboard and real cost breakdown
09:36 – When the ROI math works (and when it doesn't)
11:18 – Next steps: articles on X, how to get started
12:04 – Outro

Join the Build With AI community - weekly AI implementations, live coaching, and templates built for non-technical entrepreneurs: https://www.skool.com/buildwithai/about

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

FIND NICK ON SOCIAL

X: https://x.com/NickSpisak_

LinkedIn: https://www.linkedin.com/in/nicholasspisak/

YouTube: https://www.youtube.com/@nickspisak_

Download Nick's free second brain skill -- one-click install that sets up your entire Obsidian vault and ingestion workflow inside Claude Code: https://return-my-time.kit.com/286e11f7e6

I brought on Nick Spisak to build a complete second brain live -- start to finish, in under 20 minutes. By the end of this episode, you'll know exactly how to build your own second brain -- and you can grab Nick's free skill to do it in one click.

Timestamps

00:00 - Intro and Karpathy's viral second brain tweet

00:24 - What the second brain concept is

03:28 - Obsidian Web Clipper: scraping pages into your vault

04:41 - Nick's free skill: wizard, ingest, query, and lint commands

05:53 - Live demo: running the setup wizard in Claude Code

08:38 - How many vaults to manage: personal vs. business

10:30 - Opening the vault and exploring the file structure

12:21 - Graph view: seeing connections between your data

15:38 - Ingest command: raw data into organized wiki

16:29 - Automating ingestion on a cron schedule

19:12 - Compounding value and syncing the vault across devices

20:19 - Pruning the vault with the lint command

21:53 - Your data set as a moat in the AI age

Key Points

* Karpathy released a framework for building an LLM knowledge base. Nick turned it into a free Claude skill with a guided setup wizard, ingest, query, and lint commands -- works across Claude Code, Codex, Gemini CLI, and more. One-click install, no coding required.

* The system runs on three tiers: raw (brain dump), wiki (AI-organized knowledge base), and outputs (answers from querying). Drop files into raw, run ingest, and the AI maps everything into structured wiki entries with relationship graphs.

* You can automate ingestion using Claude Code's loop feature so the vault stays current without manual work. Pair with Obsidian's paid sync tier and a note captured on your phone is indexed before you're back at your desk.

* The lint command health-checks your wiki for outdated entries and missing connections -- and tells you exactly what to clip next to close the gaps. The wiki tells you what it doesn't know yet.

* Day zero this thing is basic. Day 90 it's a company asset no competitor can copy. Your private knowledge base is the foundation for every agent and skill you build -- and nobody else will have it.

Join the Build With AI community - weekly AI implementations, live coaching, and templates built for non-technical entrepreneurs: https://www.skool.com/buildwithai/about

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

FIND NICK ON SOCIAL

X: https://x.com/NickSpisak_

LinkedIn: https://www.linkedin.com/in/nicholasspisak/

YouTube: https://www.youtube.com/@nickspisak_

Eliot Prince is an SEO specialist with 10+ years of experience ranking businesses at the top of Google. He's now deep in the AI world, coaching businesses on how to do SEO faster and better using AI tools. In this episode, Eliot walks through how he's using Perplexity Computer to build repeatable SEO machines — systems that audit websites, generate deliverables, and even push changes live to WordPress, all from a single conversation.

We run a live audit on ReturnMyTime.com, watch three audit modules execute in parallel, and dig into the results — competitive analysis, keyword gaps, technical fixes, and auto-generated page copy. Eliot also demos a LinkedIn lead machine he built that reads DMs, scores leads, and drafts replies automatically using Perplexity's Linkup API connector.

The big takeaway: Perplexity Computer runs 19 LLM agents in the cloud simultaneously, meaning you can build systems that would traditionally take weeks of manual work or expensive SEO tool subscriptions - and you don't need to write a single line of code to do it.

Find Eliot YouTube's channel here:@princeeliot

Join the Build With AI community here: https://www.skool.com/buildwithai/about

James Dickerson (AKA The Boring Marketer) has been consulting businesses on marketing and growth since 2012 — and he's now using Claude Code to do what used to require a $5-10K/month agency. In this episode, James goes screen-share and builds a complete marketing funnel live from scratch: a landing page, a quiz funnel, a 14-day email nurture sequence, and dozens of social and SEO content assets — all inside Claude Code with zero coding.

We break down the psychology behind high-converting email sequences (micro commitments, reciprocity, objection handling), how James's "skills" system encodes expert marketing knowledge into portable AI instruction files, and why anyone with these tools can immediately outperform 80% of marketers. If you've been procrastinating on Claude Code, this is your sign to just download an IDE and start.

X: https://x.com/BoringMarketer
Website: https://vibemarketer.com

Youtube: @theboringmarketer

Grab the free one-page OpenClaw setup guide with every step and command listed out: https://corey-ganim.kit.com/c93f43577e

I walk through the complete OpenClaw setup process from zero to a working AI agent connected to Telegram — all in under seven minutes. You'll see every step: running the installer, configuring your Anthropic API key, creating a Telegram bot through BotFather, pairing it to your OpenClaw instance, and enabling web search with DuckDuckGo. One prerequisite, one terminal command, and you're live.

Key Takeaways:

• OpenClaw installs with a single terminal command — the only prerequisite is having Node.js installed, which is also a one-command setup
• The guided onboarding handles every configuration decision (model, API key, channel, search) through simple yes/no prompts — no manual config files
• Creating a Telegram bot through BotFather takes about 60 seconds: message BotFather, run /newbot, choose a name ending in "bot," and copy the token
• DuckDuckGo is the fastest search provider to start with because it requires zero additional API keys or setup
• Skills and hooks can be added after the initial install — you don't need to configure everything before getting your agent running
• The OpenClaw control panel gives you a browser-based chat window plus access to channels, sessions, usage stats, cron jobs, files, skills, and nodes

Timestamps:

00:00 - Introduction 

00:02 - Running the OpenClaw installer from the terminal 00:30 - Node.js prerequisite (quick install)

00:45 - Guided onboarding: Quick Start setup 

01:05 - Choosing Anthropic as your model provider 

01:20 - Entering your Anthropic API key 

01:35 - Selecting Claude Sonnet 4.6 

01:52 - Creating a Telegram bot with BotFather 

02:45 - Naming your bot and choosing a username 

03:15 - Connecting the bot token to OpenClaw 

03:30 - Enabling DuckDuckGo web search 

03:45 - Skipping skills and hooks (configurable later) 

04:06 - OpenClaw control panel overview 

04:30 - First chat with your bot in the browser 

05:15 - Pairing the bot with your Telegram account 

06:10 - First Telegram message confirmed 

06:30 - Setup complete — next steps for personalization

Links Mentioned:

• OpenClaw: https://openclaw.ai
• Anthropic API Console: https://console.anthropic.com
• BotFather (Telegram): https://t.me/BotFather
• DuckDuckGo: https://duckduckgo.com
• Node.js: https://nodejs.org

Enjoyed this episode?

-> Subscribe and leave a review 

-> Join the community waitlist: https://return-my-time.kit.com/1bd2720397

What if you could describe an automation in plain English and get a fully functional web app back in 15 minutes? In this episode, Kevin Fernando walks through exactly how he built a daily social media post generator using a tool called Appy. The agent researches trending stories in your niche every morning at 7 AM, writes platform-specific posts in your voice (not generic AI slop), generates properly sized images for each platform, and emails you the drafts. Kevin built it live, deployed it to the web, and even had Corey sign up and generate posts in real time during the episode. If you've been building automations in Make.com or N8N, this is the next evolution.

Guest Introduction

Kevin Fernando a 20-year entrepreneur, former head of marketing for multiple SaaS companies, e-commerce store builder/seller, and former agency owner (six years). Kevin now runs the Solopreneur YouTube channel where he teaches entrepreneurs how to get more leverage from AI tools and software without needing a team.

• YouTube: youtube.com/solopreneur

  Kevin just dropped the full step-by-step Appy tutorial on his channel. Watch it here and grab the exact prompt he used:
  Full Tutorial: https://youtu.be/eOkSQgh5UJo
  Grab the Prompt: https://solopreneur2020.kartra.com/page/appy-prompt

Corey puts two leading agentic AI tools head-to-head in a real-world showdown. He tests Perplexity Computer ($200/month) against Manus ($20/month) across three practical use cases: multi-source research with website deployment, connected app integrations with Google Workspace, and data collection with visualization. You'll see exactly how each tool performs on speed, accuracy, output quality, and which one earns Corey's recommendation for 2026.

Join the Build With AI community waitlist: https://return-my-time.kit.com/1bd2720397

• Perplexity Computer completed tasks 5-10x faster than Manus across most tests — finishing in 60 seconds what took Manus 10 minutes 

• Both tools nailed data accuracy when researching AI startup funding, pulling identical figures from TechCrunch 

• Perplexity's Google Workspace integration produced cleaner, properly formatted deliverables (tables, headers, structured docs) while Manus output jumbled text

• For website deployment, Manus actually had slightly better UI design — but both successfully created shareable public URLs 

• When stuck, Perplexity self-corrected and found the data; it recovered gracefully from errors 

• ClickUp was recommended by both tools as best value for project management pricing ($12/user/month for Business plan) 

• Perplexity Computer wins overall for speed, output quality, and cleaner UI despite the 10x higher price tag

Timestamps:

00:00 - Introduction and test overview 

00:30 - Pricing comparison ($200 vs $20 plans) 

01:00 - Test 1: Multi-source research + website deployment

14:04 - Test 1 results: Speed comparison (2 min vs 10 min)

16:25 - Website design comparison

18:30 - Test 2: Gmail + Calendar + Google Docs integration

27:14 - Test 2 results: Output quality comparison 

29:40 - Perplexity's formatted table vs Manus' jumbled text 32:00 - Test 3: Data collection, analysis, and visualization 39:30 - Test 3 results: Bar charts and pricing spreadsheets 41:52 - Final verdict and recommendation

Links Mentioned:

• Perplexity Computer vs Claude Cowork: https://youtu.be/_s0ymvl6vNc

• Perplexity Computer: https://perplexity.ai/

• Manus: https://manus.im/

What if you could go from a blank folder to a fully functional competitive research tool complete with scoring rubrics, interactive dashboards, and repeatable skills—in under an hour? In this episode, marketing veteran Adam Sandler (yes, that's his real name) shares his screen and builds the entire workflow live using a real-world use case: finding distressed wedding venues in North Carolina for a friend's acquisition business. No coding. No technical background. Just Claude Code, plain English, and a process that any knowledge worker can replicate.

Check Adam's youtube channel:https://www.youtube.com/@ViableEdge

Nick Spisak, a 15-year software veteran turned AI entrepreneur, walks through the complete OpenClaw setup for non-technical users. You'll learn how to install your first instance, give it skills that read documentation for you, and troubleshoot any issue using natural language. Nick even gives away his "OpenClaw Prime" skill that turns any coding agent into an OpenClaw expert, plus a visual step-by-step diagram.

• OpenClaw Prime Skill: https://corey-ganim.kit.com/f1f13dee60

• Excalidraw Setup Diagram: https://corey-ganim.kit.com/ab1cc7ab21

Key Takeaways:

• Build a skill that reads the docs so you don't have to. Nick's "OpenClaw Prime" skill makes Claude Code or Codex an instant OpenClaw expert.

• Troubleshooting works 100% of the time. Point your coding agent at your OpenClaw files, describe the issue in plain English, and let it fix itself.

• Skills are portable across models. Write it once for Codex, ask AI to convert it for Claude Code or Gemini.

• Spend 90% of your time in planning mode. Use Shift+Tab to enter plan mode and remove assumptions before execution.

• Real business use case: AI receptionist. Set up OpenClaw on WhatsApp to respond to leads while you're on a job site. One extra $10K roofing lead pays for the whole system.

• Telegram is the easiest platform to connect. Message the Bot Father, get your token, plug it into OpenClaw.

• Customize your agent's personality via the Soul file. Make it concise, opinionated, and aligned with how you work.

Timestamps:

00:00 - Introduction and what you'll learn

01:02 - Using Claude Cowork + Excalidraw for planning

03:46 - WhisperFlow: talk to your terminal with natural language

06:30 - OpenClaw Prime skill explained

08:41 - Why skills teach AI to "fish" (not just follow tutorials)

11:02 - Live troubleshooting demo: bringing Annie back online

13:44 - Claude Code vs Codex (skills are portable)

16:44 - Planning vs execution mode (the 90/10 rule)

19:21 - Real business use cases: AI receptionist for contractors

23:28 - 100% success rate troubleshooting (even with no code experience)

25:13 - Walkthrough of the Excalidraw setup diagram

27:16 - Setting up Telegram (easiest platform)

28:51 - Soul file and agent identity customization

30:26 - Wrap up and where to get free resources

Links & Resources Mentioned:

• OpenClaw Docs: https://docs.openclaw.ai

• Claude Cowork: https://claude.ai

• WhisperFlow: https://whisperflow.com

• Ghost TTY (Terminal): https://ghostty.org

Enjoyed this episode?

→ Subscribe and leave a review to help others discover the show

→ Join the Build with AI Community waitlist: https://return-my-time.kit.com/1bd2720397