Higgsfield just shipped an MCP server that lets Claude run every model in their catalogue from one connection. Soul, Flux, Kling, Seedance, Cinema Studio, Nano Banana, GPT Image 2. No per-provider API keys, no juggling tabs, no copy-pasting prompts. In the video, I walk through: Step 1: Connecting Higgsfield's MCP to Claude (Code or Desktop) in under 60 seconds. Step 2: Why the cost-approval gate matters. Higgsfield bills in credits, and credits cost real money. The skill I built makes Claude tell you the model, settings, and estimated cost before every generation. You confirm, then it fires. Step 3: Live demo. Generating a YouTube thumbnail end-to-end through the skill, with logos passed as proper reference images so they actually render correctly. Step 4: When to use Higgsfield vs fal.ai vs kie.ai. Honest framework, not a one-sided pitch. Each platform has a real strength. Here is the skill: **copy below this line** I'm giving you a skill called Higgsfield. Get the files with: git clone https://github.com/automatorsplus/higgsfield-skill Follow the README to set it up. Recommend how it would best apply to our setup in plain language, and ask me a few questions to clarify my intent before you install it.

In this video, I show how Claude Code can run an entire marketing campaign workflow using the Blotato MCP. One campaign idea goes in, and the system generates the content, visuals, and distribution plan across multiple platforms automatically. You’ll see how Claude orchestrates the prompts, connects to Blotato, and produces a full campaign with assets ready to publish. Perfect if you want to turn a single idea into a full multi-platform marketing push without doing everything manually.

Claude just unlocked a new way to build with AI using Agent Teams, and it changes how you create systems with code. In this video, I demonstrate how multiple agents can collaborate on planning, building, debugging, and iterating, rather than relying on a single, large prompt. You’ll see real examples of how to split tasks, route context, and keep projects organized inside Claude Code with Opus 4.6. I also explain how to design agent roles, pass memory between them, and use teams to move faster on apps, automations, and content systems without things breaking every step. 👉 I’ve attached my dashboard prompts for you, and I’ll also be adding a dedicated section inside the new Claude Code area in Classrooms so you can build along with me. 📚 Claude Agent Teams Docs:https://code.claude.com/docs/en/agent-teams If you’re serious about using Claude as a builder instead of just a chatbot, this update is a game-changer.

Part 2 dives into the backend that powers the voice agent. I show how Airtable handles leads, call logs, statuses, and follow-ups, while Supabase stores conversation data and agent memory. You’ll see the full data model, webhook routing, syncing logic, and how everything connects back into n8n so your AI agent can qualify, update records, and trigger automations in real time. Perfect for turning a simple caller into a real sales system.

Happy New Year, everyone! 🎉 Massive thank you for being part of this community and showing up, building, learning, and sharing wins. My goal for 2026 is simple: help you automate more, create faster, and make more money from the systems you build. What’s one thing you want to achieve this year? Drop it in the comments so we can keep each other accountable 👇