← Back to Playbook
FREE SAMPLE
Claw's Monthly Playbook

Vol. 1 — February 2026

Every month we document exactly what we built with AI — what worked, what didn't, and how to replicate it. No technical degree required. If you can copy and paste, you can do all of this.

10insights
1deep-dive
3hard lessons
beginnerfriendly
📚 Free sample — subscribers get the full issue every month
📋 What's inside
✅ Deep Dive
01
Workflow of the Month · Deep Dive
Manage 5 AI Projects From One Telegram Group — Without Losing Your Mind
The short version

Telegram has a hidden feature called "Topics" that turns one group chat into separate project channels. Add your AI bots once. Each project gets its own thread. Free, built-in, takes 5 minutes to set up.

We were running 5 active projects with 2 AI assistants. Homepage redesigns, iOS app development, video production, shop, social media — all in one Telegram chat. Every day the same problem: "Wait, which project are you answering about right now?"

Then we found the fix already built into Telegram. It took 5 minutes.

What you need

Just Telegram. That's it. No extra apps, no subscriptions, nothing to install.

How to set it up — step by step

1
Create a new Telegram group

Tap the pencil/compose icon → New Group → give it a name like "My Projects HQ". Add yourself and your AI bots as members.

2
Turn it into a "Forum" group

Open the group → tap the group name at the top → Edit → scroll down until you see "Topics" — turn it on. The group now has separate threads. A "General" topic appears automatically.

3
Create one topic per project

Tap the ✏️ icon → New Topic. Create one for each project. Examples: "Homepage", "iOS App", "Videos", "Shop", "Finance". Pick an emoji and color for each so they're easy to spot.

4
Find your topic ID (needed for automation)

Open web.telegram.org in a browser → click your group → click on a topic. Look at the URL in your browser. It will look like: web.telegram.org/k/#-1001234567890_15 — the number after the underscore (15 in this example) is your topic ID. Write these down — you'll need them when setting up cron jobs or asking your AI to send messages to specific topics.

5
Tell each bot which topic is "theirs"

In your AI setup, assign roles clearly. Example: "You only respond in the Homepage topic. When someone messages in iOS App, stay silent unless directly asked." Without clear role rules, both bots answer everything and it becomes noise.

What this looks like in practice

You open Telegram. You see your group. Inside: Homepage, iOS App, Videos, Shop. Each one is a clean, separate conversation with its own full history. You tap "Homepage" and immediately see every decision, every result, every piece of work — perfectly organized, searchable, timestamped.

When your AI sends you a report, it goes to the right topic. When you ask a question, your bot knows exactly which project you're in. No more confusion.

💡 Bonus: It's also your project history

Every decision you and your AI made is in that topic thread. When you come back to a project after two weeks away, you don't need to remember anything — just scroll up. It's better documentation than most companies keep, and it costs nothing.

Watch out for this

If your AI bot replies to every message in every topic, it becomes annoying fast. Make sure you tell it: "Only reply when I'm directly asking you a question, or when you have something important to report. Otherwise, stay quiet." This one rule makes the whole setup work.

⚡ Hacks
02
Hack
Upload Videos 20× Faster — Without Changing Your Internet Plan
The short version

Instead of uploading from your home computer, trigger the upload from your web server. Your server has datacenter internet — it's 20–100× faster. A 40MB video that takes 10 minutes from home? Done in 4 seconds from the server.

Here's something most people don't think about: your home internet is fast for downloading things but slow for uploading them. When you upload a video to YouTube from your laptop, you're limited by your home upload speed — usually 5 to 20 Mbps.

Your web hosting server lives in a datacenter. Datacenter connections are 100 to 1,000 Mbps in both directions. If you store your video on the server first, and then trigger the upload from the server — the video goes from server → YouTube at full datacenter speed. You're not involved at all.

How we set this up (simplified)

1
Store your video on the web server first

Instead of keeping videos on your laptop, upload them to your server via FTP or your hosting file manager. Most shared hosting plans give you plenty of storage. This is your "video library."

2
Build a simple "Share" button in your admin panel

A button that calls your server with the video filename and target platform. Your server handles the actual upload. You just click a button — from your phone, from a café, from anywhere.

3
Ask your AI to build the upload handler

Tell your AI: "I have a PHP web server with a video file at /video/myvideo.mp4. I want a button in my admin panel that, when clicked, uploads that video to my YouTube channel using the YouTube Data API. Here are my API credentials: [paste credentials]." It will build the full thing for you.

✅ Real numbers from this month

Video file size: ~39MB
Upload from home laptop: estimated 3–5 minutes
Upload from web server: 4 seconds
Method: one button click in our video manager

💡 The bigger idea here

Think of your web server as your always-on, always-fast production machine. Your laptop is just the remote control. Anything that moves large files — video uploads, image batch processing, sending newsletters — should happen from the server, not through your home connection.

03
Automation
Your AI Checks Your YouTube & Social Stats Automatically — Twice a Day
The short version

We built a script that pulls view counts from YouTube, X (Twitter), and TikTok every morning and evening, and sends a neat summary to Telegram — including what changed since last time. Set up once, runs forever.

Checking three platforms manually takes time and honestly never happens consistently. We automated it. Every day at 9 AM and 6 PM, a Telegram message arrives with a summary like this:

📷 Sample message (you receive this automatically)

📊 Video Stats — Feb 22, 18:00

▶️ YouTube — 12,600 total views, 42 subscribers
• You are my SuperGirl — 185 views (+12 today) ❤️ 3 likes
• Warm Spin Dry Repeat — 175 views (+8 today) ❤️ 2 likes

𝕏 Twitter / X
• "My neighbor said..." — 14 views (+3) ❤️ 1 like
• "Tonight 8PM" — 10 views (no change)

How to set this up yourself

1
Get your API credentials (one-time)

YouTube: Go to Google Cloud Console → Create a project → Enable "YouTube Data API v3" → Create OAuth2 credentials → Follow the authorization flow to get a refresh token. (Ask your AI: "Walk me through getting a YouTube Data API v3 refresh token step by step.")

X/Twitter: Go to developer.twitter.com → Create an app → Get your API Key, API Secret, Access Token, and Access Token Secret.

2
Ask your AI to write the stats script

Give your AI this prompt exactly:

"Write a Node.js script that: (1) fetches my top 5 YouTube video stats using my refresh token, (2) fetches my last 10 tweets with impression counts using my Twitter bearer token, (3) compares the numbers to a saved history file and shows the difference, (4) sends the results as a Telegram message. Use dotenv for credentials."

It will write the complete script. Save it as video_stats.js.

3
Add your credentials to a .env file

Create a file called .env in the same folder. Add one line per credential:

📋 Copy this format into your .env file
YOUTUBE_CLIENT_ID=paste-your-id-here
YOUTUBE_CLIENT_SECRET=paste-your-secret-here
YOUTUBE_REFRESH_TOKEN=paste-your-token-here
TWITTER_BEARER_TOKEN=paste-your-bearer-token-here
TELEGRAM_BOT_TOKEN=paste-your-bot-token-here
TELEGRAM_CHAT_ID=your-chat-id
4
Schedule it to run automatically

If you use OpenClaw, ask your AI to add a cron job. If you use a regular server, ask your AI: "Add a cron job that runs 'node /path/to/video_stats.js' at 9 AM and 6 PM every day in the Europe/Berlin timezone."

💡 Why "change since last check" matters more than total views

Seeing 12,600 total views tells you nothing new. Seeing +12 since yesterday morning tells you which video is gaining traction right now. That's your signal to double down — post more like that, engage with those comments, maybe boost it. Track velocity, not just totals.

04
Workflow
Upload to YouTube With One Click — From Your Phone, From Anywhere
The short version

Add a "Share to YouTube" button to any admin panel. Your server does the upload. One click from your phone = video live on YouTube in seconds. No laptop. No waiting.

If you already have a video manager or admin panel (even a simple one), adding a YouTube upload button is easier than it sounds. The heavy lifting is done by Google's YouTube API — you just need a few credentials and a short script.

What to tell your AI

Copy this prompt and send it to your AI assistant:

📋 Paste this prompt to your AI
"I have a web server running PHP. I have videos stored at /public_html/video/. I want to add a button to my admin page that, when clicked, uploads a chosen video to my YouTube channel.

I have these credentials: YOUTUBE_CLIENT_ID, YOUTUBE_CLIENT_SECRET, YOUTUBE_REFRESH_TOKEN stored in a .keys file above web root.

Please write a PHP file called upload_video.php that: (1) reads credentials from .keys, (2) uses the refresh token to get a fresh access token from Google, (3) uploads the video file to YouTube using the resumable upload API in 5MB chunks, (4) returns the YouTube video URL as JSON. Also show me how to call it from a button."
Replace the paths and credential names with your own. Your AI will write the complete code.

How to get your YouTube credentials (one-time)

1
Go to console.cloud.google.com

Create a new project. Name it anything — "My YouTube Uploader" works.

2
Enable the YouTube Data API v3

Search for "YouTube Data API v3" in the API library. Click Enable.

3
Create OAuth2 credentials

Credentials → Create Credentials → OAuth Client ID → choose "Desktop app". Download the JSON file. Your Client ID and Client Secret are inside it.

4
Get your refresh token

Ask your AI: "I have a YouTube OAuth Client ID and Secret. Walk me through getting a refresh token that allows uploading videos to my YouTube channel." It will give you a step-by-step process you do once. The refresh token never expires (unless you revoke it).

✅ What happens when it works

You click "Share to YouTube" on any video in your manager.
A spinner appears. After 4–8 seconds:
✅ Done — https://www.youtube.com/watch?v=yourVideoId
The URL is automatically saved in your video record.

💥 Hard Lessons
07
Hard Lesson
Why AI-Generated Images Look Wrong on Social Media (and the Easy Fix)
The short version

Images generated directly by AI tools often look slightly "off" when posted to social. Videos look dramatically better. Fix: generate a short video instead, extract one frame from it, use that frame as your image.

We were generating character images with Grok's image generator and posting them directly to social channels. The images were technically fine but something felt wrong. People couldn't name it but engagement was noticeably lower.

When we switched to generating short video clips and extracting frames, the quality difference was immediately obvious — even to us. The same character, same prompt, but the video-extracted frame looked like a still from an animated film. The image-generated version looked like... an AI image.

The simple fix

1
Generate a short video instead of an image

Use your AI video generator (Grok, Runway, Kling, etc.) with the same prompt you'd use for an image. Even 3–5 seconds is enough. The video renderer produces much better textures, proportions, and lighting.

2
Extract the best frame

If you have ffmpeg installed, ask your AI: "Give me an ffmpeg command to extract the single best/sharpest frame from myvideo.mp4 and save it as thumbnail.jpg." If you don't have ffmpeg, just pause the video at a good moment and screenshot it — it works too.

3
Use the frame for images, the full video for video platforms

Post the extracted frame to Instagram, X, Facebook. Post the full video to TikTok, YouTube Shorts, Instagram Reels. You get two assets from one generation.

🔥How we learned this

Posted 3 AI image-gen character images in one week. Engagement was noticeably lower than previous posts. Switched to video-extracted frames the next week. Engagement recovered immediately. We never went back.

08
Hard Lesson
How to Give AI Agents Instructions That Actually Stick
The short version

If you tell your AI "follow the instructions in that file", it often ignores them halfway through. Put your important rules directly in the message, not in a separate file. It takes an extra minute and saves hours.

We have a detailed "character bible" — a document with visual specs, personality rules, and production guidelines for our animated characters. For weeks we were telling sub-agents: "Read the character bible and follow it exactly."

Sometimes it worked. Sometimes they'd skip key rules. We couldn't figure out why it was inconsistent — until we realized: AI agents process instructions from most-to-least recent. Rules in a file they read early in the process get "pushed back" in memory as the task continues. Rules stated directly in the task prompt stay front of mind throughout.

The fix

Instead of: "Read rules.md and follow it."

Do this: Copy the most important rules directly into your message.

❌ This often gets ignored
"Generate a video for our character. Follow the character bible at /docs/bible.md"
✅ This works reliably
"Generate a video for our character. Important rules:
- Character has a red color scheme, golden crown, two big claws
- Background is always a neon city at night
- Style is Pixar/Dreamworks animated, colorful, full of personality
- Never show the character looking sad or defeated
[paste your other key rules directly here]"
Yes, it makes your message longer — that's fine

Longer messages cost slightly more in AI credits. But a sub-agent that produces wrong output because it forgot a rule costs you: the generation fee, your time reviewing, and the re-run fee. Inline rules win on economics every time, every project.

09
Hard Lesson
Never Get Locked Out of Your Own System — The 3-Step Rule
The short version

When moving or changing login credentials, always confirm the new ones work BEFORE removing the old ones. We skipped this step and got locked out of our admin panel for 45 minutes.

We were moving our API tokens to a safer location. We asked our AI agent to handle the migration. Being thorough, it deleted the old tokens as part of "cleaning up." But it hadn't confirmed the new location actually worked yet. We were immediately locked out.

Recovery meant digging up credentials from another device, reconstructing the auth config, and 45 minutes of stress that didn't need to happen.

The 3-step rule we now follow every time

1
Copy credentials to the new location

Add them to the new file, new format, new place — whatever the change is. Don't touch the old ones yet.

2
Test that the new location works

Actually log in. Actually make a real request. Confirm with your own eyes that it works. Don't assume — verify.

3
Only now: remove or archive the old credentials

Don't delete — rename to .bak or add _OLD to the filename. Keep it for a day or two before permanent deletion. Recovery is free. Getting locked out is expensive.

💥 When using AI for security changes — say this explicitly

Add this to your prompt: "Important: do NOT delete or remove the old credentials until after you have confirmed the new ones work with a successful test. Step 3 only happens after step 2 is verified." AI agents are helpful and will "clean up" without being asked. Make the sequence non-negotiable.

🛠 Stack
10
Monthly Stack
Our Exact AI Tool Stack — What We Use, What We Pay, What We'd Pick Today

AI assistants

Claude Sonnet (Anthropic) — our main AI for almost everything. Code, writing, decisions, planning. Fast, accurate, great at following instructions. This is what writes most of the code in this playbook.

Claude Opus — the "thinking" version of Claude. Slower and more expensive, but better at nuanced decisions, creative direction, and complex architecture. We use it for important design choices only.

Grok (xAI) — great for social media posts, character dialogue, story ideas. Has a distinct personality that works well for entertainment content.

GPT-4o — reliable fallback. If Claude is busy or a task isn't working, GPT-4o usually handles it fine.

For video and image generation

Grok video generator — best results we've found for animated character content. We use this for all CTRL & CLAW episodes.

Luma Ray 2 — alternative video generator, good for realistic scenes.

DALL-E 3 (via ChatGPT) — quick concept images when we need them fast. Not for social posting (see Insight 07).

Infrastructure (monthly cost: ~€15)

Namecheap shared hosting (~€5/month) — website, video storage, PHP scripts, admin panel. More powerful than people think.

OpenClaw — AI agent orchestration. Handles cron jobs, Telegram integration, spawning sub-agents. Free self-hosted.

Mac Mini M4 Pro — local development, iOS app builds, running local AI models when we don't want to pay API costs.

What we added this month

✅ Automated video stats tracking (YouTube + X, twice daily)
✅ YouTube upload direct from server via one button
✅ Telegram forum topics for multi-project management
✅ This newsletter / playbook (you're reading it)

What we'd pick if starting from scratch today

Start with: Claude Sonnet + OpenClaw + any web hosting plan. That's the minimum viable setup to do everything in this playbook. Total cost: the web hosting (~€5/month). OpenClaw is free. Claude API credits for a small setup are ~€10–20/month. Under €30/month total to run a full AI-powered content and automation system.

💡 The philosophy

Don't use the most expensive AI for everything. Use fast, cheap models for simple tasks (formatting data, writing captions, checking stats). Use smart, expensive models only for decisions that actually matter. Most tasks don't need the top model. Save the budget for when it counts.

🚨 Coming in Vol. 2 — March 2026

Build your own email list — zero monthly fees

No Mailchimp, no Substack. Your own subscriber list on your server. Complete setup guide.

Building an iOS app with AI as your coding partner

How we're building MDX_ with Claude on Mac Mini. The exact workflow from idea to running on a real phone.

Cron jobs for beginners — automate your boring tasks

What a cron job is, when to use one, how to set one up in plain English. With 10 real-world examples.

Ready-to-use prompt library

30 prompts we actually use every week. Copy-paste ready. Director agent, morning briefing, social posts, code review, content generation.

📚 Get every issue as it comes out

First of every month. Plain language. Step-by-step.
Real stuff that works — not theory.

Monthly
€9
per issue · cancel anytime
⭐ Best value
€49
full year · save 55%
Subscribe Now →