Hi everyone, I’m Shrey Shukla, a Computer Engineering graduate currently looking for opportunities in AI Engineering, AI Automation, Generative AI, and AI Agent development — full-time, freelance, or contract. I have hands-on experience building real-world AI systems and automation workflows using: 🔹 Python, FastAPI & REST APIs 🔹 LLMs, RAG & AI Agents 🔹 n8n & AI Automation 🔹 Vector Search / Embeddings / FAISS 🔹 LLM-as-a-Judge & AI Evaluation 🔹 PostgreSQL & API integrations Some of the projects I’ve worked on include: • AI-powered HR Interview & Hiring Platform with RAG and LLM-as-a-Judge • AI Visual Similarity Search using embeddings + FAISS + FastAPI • AI automation for a real-world e-commerce platform, with 1200+ production workflow executions 🔗 Portfolio: https://shreyshukla.space 💻 GitHub:https://github.com/shrey3108 🔗 LinkedIn:https://www.linkedin.com/in/shrey-shukla-38410024b/ If you or someone in your network is building an AI product, wants to automate business processes, or is hiring for AI/ML/GenAI roles, I’d really appreciate an introduction or opportunity to connect. Thank you! 🙏

A lot of us here are great at learning AI automation, building workflows, testing agents, improving technically. But I’ve noticed something that doesn’t get talked about enough: Many people are doing the work… yet struggling to turn it into clear results or consistent income. It’s rarely a tools problem. More often, it’s a direction, positioning, or system problem — knowing what to build, for who, and why it matters. Curious to hear from others here: - What’s currently harder for you, mastering the automation itself, or turning it into something people actually pay for?

I've been using Claude Pro for a while and I want to build an "AI second brain" with it at the core. A few specific problems I'm trying to solve: - Remembering what I've already learned or researched - Speeding up how I consume and retain information - Getting help with writing and content — not just one-off prompts - Staying on top of tasks and projects without losing context I'm leaning toward combining Obsidian with Claude, and possibly using Claude Code to build automations around it (things like scripts to summarize notes, surface past research, or sync context). But I'm not sure how to connect these pieces in a way that actually works day-to-day. For anyone who has built something like this: → Where did you start — notes, tasks, writing, or something else? → Has anyone integrated Obsidian with Claude to auto-summarize notes or pull up past research? How did you set that up? → What's one thing you wish someone had told you before you started? Looking for real-world experience, including the parts that don't usually get talked about.

Hey guys, I am looking for 2 developers experienced in creating automations like Customer support, RAG, Lead gen systems, CRM automations, etc. You will be paid on a per project basis and as the firm grows, you can expect a steady monthly salary as well. If you are such a developer, feel free to DM, me here or on LinkedIn. (if you cannot do any of those, feel free to drop your socials in the comments so I can contact you) Here's the link to my profile- https://www.linkedin.com/in/meet-soni-ai/

First, I have to say it: Nate's video genuinely blew my mind. The roast skill changed the way I make decisions, and the whole "stop letting the model agree with you" idea is gold. If you haven't run it yet, do — it's that good. As I adapted it to my own workflow, I noticed two small additions that pushed it even further for me. Funny enough, they're the exact same two things that leveled up my multi-LLM council a while back: a second pass, and more than one brain. Tweak 1 — a second round (cross-examination). Round 1 stays exactly like Nate's: the six personas attack independently and score the idea. Then I added a round 2 where the personas look at each other's takes and pressure-test them: - Expansionist → Contrarian: is that "fatal flaw" really fatal, or are we over-worrying it? - Contrarian → Expansionist: is that upside actually reachable with the resources we have, or is it wishful? - Deep-researcher → everyone: flag any claim with no evidence behind it (anything unverified loses weight). - Buyer → everyone: does the real customer even care about this, or is it just an internal debate? - First-principles → everyone: separate solid logic from hope, and keep anyone from quietly redefining the product. Each persona revises its score after the pressure, and the judge synthesizes only from round 2. Anything that doesn't hold up in the cross-examination doesn't get to drive the verdict. It turned the output from a clean yes/no into a much deeper, debated call. Tweak 2 — bringing in other LLMs. Nate's version runs on Claude alone — one model playing all six personas. I wanted more than one point of view at the table, so I added other LLMs to the panel: Codex (GPT) and Gemini, alongside Claude. Now Codex and Gemini run the adversarial panel and cross-examine each other in round 2, while Claude handles the live web research and acts as the judge. Three different brains genuinely disagreeing gives me sharper feedback than one model talking to itself.