In this video, I’ll show you how to build a powerful no-code AI agent using Firecrawl’s new /search endpoint. This agent can search the entire web for anything, with full control over filters, included/excluded sites, and time-based parameters. Then, it can scrape the content in markdown, HTML, JSON, or even take full-page screenshots. By the end of this tutorial, you’ll have a fully working system that can search, scrape, and screenshot the web automatically, no code required. Perfect for automations, research agents, and next-gen AI workflows. 🔥 Code HERK10 for 10% OFF Firecrawl for a Year

Hey everyone, I need your help. There are two fake X (Twitter) accounts impersonating me and TrueHorizon AI, and they're promoting something called “TrueHorizon Coin”, this is NOT real, and I have nothing to do with it. Please take a moment to report both of these accounts for impersonation: - https://x.com/TrueHorizonAI - https://x.com/NathanHerkelman I’m not active on X, which is why this happened. My real X account is @nateherk. Thanks so much for your support, really appreciate this community! 🙏

This lightweight n8n workflow converts any incoming chat text into a flowing MP3 recitation in authentic, classical-style Latin—something virtually unheard of in mainstream TTS tools, which default to the ecclesiastical accent. At runtime it takes your raw message, applies LLM-powered rules to reshape the text into a classical-pronunciation phonetic form, then sends that to OpenAI’s speech API to produce a polished audio stream with crisp consonants, rolled R’s and properly stressed vowels. In just a few streamlined steps, you get a ready-to-play MP3 that sounds as if a Roman orator were reading your words aloud—no heavy configuration required, and no more church-style Latin clichés.

I had a client that wanted to train sales people in real-time with different personas, and then evaluate their performance. I really thought about this for awhile, and knew it was possible, but expected it to be complicated. Turns out, the base functionality in n8n can be accomplished with just 3-4 nodes - way simpler than I initially thought. The breakthrough for me was the "generate HTML" node. This lets me call my webhook directly from any web app or link, which is pretty slick. In this setup, I configure a personality for the AI before doing the OpenAI request/Whisper: json{ "instructions": "{{ $json.ai_instructions }}", "model": "gpt-4o-realtime-preview-2024-12-17", "modalities": ["audio", "text"], "voice": "alloy", "input_audio_transcription": { "model": "whisper-1" } } Here's the cool part - the HTML template gets returned to the user, building the page on the fly. So the agent on the other end takes on the specified personality (like a roof salesman), and the conversation feels surprisingly real. When you wrap up, the AI evaluates the transcript and scores your performance based on your criteria. Some other interesting possibilities that came to mind: Interview preparation with AI playing tough interviewers Negotiation training with different difficulty levels Customer complaint handling with progressively angrier customers Medical students practicing patient consultations Language learning through realistic conversation scenarios Security training for social engineering attempts This approach cuts down development time dramatically while still delivering a powerful training tool. The applications are pretty much endless, and it's all easier than expected. Best, Brian

Hey everyone! Hope you're all doing great. I'm currently working on an AI voice solution for call centers and could use some guidance on the delivery side of things. Does the Nate paid community provide any practical tutorials or resources related to this? Would appreciate any pointers. Thanks in advance!