No-Code Agentist

This is EVERYTHING you need to know about building a Company Brain in 28min. From connecting all your tools into one intelligence layer to the new org chart around it. This is the new way to work in the AI era. Here's the full breakdown: 00:00 Introduction & AI Adoption 01:45 The Four Levels of AI Maturity 02:30 The Single Brain Concept 05:30 Building an AI-Powered Org 07:20 Specialist Agents & Agent Fleets 11:20 Workflows & Closed Loops 14:30 Real Agent Examples in Slack 18:00 AI ROI & Token Economics 20:45 Business-to-Agent Commerce 24:10 Action Steps & Future of Work

n8n just crossed 193K stars — and it's quietly becoming the most practical AI workflow engine on GitHub. Here's what nobody tells you about it: n8n is NOT just another low-code automation tool. The AI-native architecture is what sets it apart. You get: → 400+ integrations (OpenAI, Anthropic, HuggingFace, Qdrant, everything) → Native MCP client AND server support — your agents talk to your workflows → Self-hosted or cloud — your data, your infra → Visual builder that exports to real TypeScript code → CLI-first deployment for CI/CD pipelines The use cases I keep seeing: 1. AI-powered document processing pipelines — ingest PDFs → LLM extraction → Qdrant vector store → Slack notification 2. Multi-agent orchestration — route tasks between GPT, Claude, and local models based on cost/quality thresholds 3. Real-time data enrichment — webhook in → enrich with AI → write to database The MCP support is the sleeper feature. n8n can act as both an MCP server (exposing workflows as tools for agents) AND an MCP client (consuming external tools). This makes it the missing middleware between your agents and your infrastructure. Self-hosted on a $10 VPS. No vendor lock-in. Real code underneath. https://t.co/igRFmfYYnZ

Fastest teams on Dodonai build templates once, reuse across cases. Dates, providers, diagnoses, billing — extracted in the same structure every time, scoped to your firm. Not 'AI summarizes.' Reusable workflows. http://dodon.ai https://x.com/Dodon_ai/status/2067752223417721002/photo/1

In Episode 1 of Invest with AI, Brett Caughran and Khe Hy discuss what has changed, why AI felt overhyped before, and why the move toward agentic workflows is starting to matter for investors. We cover: > What changed from chatbots to agents > Where AI is useful in investment research today > Why data accuracy and validation still can’t be ignored > Why many investment processes are harder to automate than they look > How investors should think about adopting AI without overhauling everything at once > Why there is no final state for AI in investing The goal of Invest with AI is simple: Bring investors along as we test the tools, discuss what matters, and figure out how you can use AI in fundamental investing. Episode 1 is now live. Highlights: 00:00 Intro to Invest with AI 00:21 Khe Hy’s background in hedge funds, training, and AI consulting 02:06 Brett Caughran’s background as a fundamental investor and founder of Fundamental Edge 03:30 Why the agentic shift catalyzed the podcast 04:17 Khe’s “AI-pilled” moment 07:24 When AI shifted from Q&A to real work 10:45 Why agentic tools changed the conversation 12:09 What “agentic” means in an investment workflow 17:19 Using AI agents for validation and accuracy checks 19:57 Why investors struggle with a “failure of imagination” around AI 23:16 Why much of investment work is still “vibes and spreadsheets” 24:00 Turning investment judgment into explicit workflows 26:44 Why overpromising AI creates disappointment and churn 28:39 Why AI adoption will be a 9 to 18 month journey 35:14 Why there will be no final “AI is ready” moment 36:09 What Invest with AI will explore going forward https://www.youtube.com/watch?v=AyfDBA977QE&t=3s