Happy thanksgiving!

If you attended my session at Boston Code Camp last weekend - I just posted my notes so you get now get the presentation pdf. https://t.co/US5pOsJXg0 #RAG #AI

This is an excellent book. @karpathy said: "Context engineering is the delicate art and science of filling the context window with just the right information for the next step." This book will help you stop thinking about "prompt engineering" and start focusing on "context

At the Boston Code Camp #boscc With @MetroShare @beth_wolfset @ababiec @bizdataviz @squdgy @richcrane @nhcloud @thearchitect452 @JohnMiner3 @kevinmwilder @basementprogra1 @bryanjhogan @haleyjason @veronika_dev1 @davidlozzi @mintzworld @liarjo @codingoutloud #boston #code

If you haven't registered yet, you have until 6pm today: https://t.co/5dlaJnFzcr Hope to see you there!

The Azure AI Search team just upgraded their agentic knowledge base feature: * Connect to Bing, SharePoint, multiple search indexes, and it will dynamically decide which sources to query * Optional reflection+iteration cycle https://t.co/tTRMYBUpNl

Join us today at the Nashua CLOUD .NET User Group! 🚀 Run LLMs Your Way: Deploying Ollama on Azure Container Apps. RSVP: https://t.co/6aKf7luPHH

dotNET blog: A step-by-step guide to modernizing .NET applications with GitHub Copilot agent mode

Whoah, Microsoft Foundry is adding Claude models! https://t.co/Wr0c607rkf That means that I now have a work-related excuse to try out Claude models from the API for my RAG and agent scenarios. I'm keen to run some evals.

Boston Code Camp is coming up one week from today (Saturday Nov 22) - free registration is open thru Wednesday at 6pm. This is our 39th offering of a free developer's conference offering deep dives into the latest software development conference. https://t.co/4tgwUq5F3g

Every company I know uses a CRM. Most of them suck. I know people whose only job is to feed data to a CRM. They spend hours filling out forms, logging meetings, and summarizing calls, and still end up missing follow-ups and deadlines. CRM applications were not built for the

Just used npkill to find 17GB of node_modules on my machine. And I'm a "Python developer" 😉 (17GB is actually a big deal for me to recover, as I literally had 20 MB left on my HD earlier today. I'll take all the gigs I can get.)

Unlock the hidden power of your data with graph databases! Traditional databases can't help you find relationships and patterns in your data, which could be crucial for your business's growth. Our latest blog reveals 7 core graphs your business needs: ▶️ Customer Graph ▶️

Everyone's building RAG systems. But most can't read a simple diagram. Traditional RAG only retrieves text. But what if your knowledge base includes PDFs with charts, technical diagrams, or infographics? That's where ✨Multimodal RAG✨ comes in. Here's what's happening:

Kudos to @AnthropicAI for a killer registry of Claude use cases. If you're struggling for inspiration for what to do with an LLM (any LLM) this is a great set of scenarios to sift through. https://t.co/GLJOxRz4oe

Chart OCR just got a major upgrade with our new experimental "agentic chart parsing" feature in LlamaParse 📈🧪 Most LLMs struggle with converting charts to precise numerical data, so we've created an experimental a system that follows contours in line charts and extracts

Thinking about building AI agents but not sure where to start? Our newest AI Agents for Beginners course is here, and this one is focused on AI Agentic Design Principles, which helps you learn how to implement simple, human-first approach to creating agents that: ✨ Boost

Robinhood, the financial services firm, is using generative AI to help analysts investigate financial crimes more effectively and efficiently. https://t.co/lhXxYp01eA

One of the biggest use cases for agentic document automation is insurance underwriting ✍️ Underwriting depends on processing *massive* volumes of unstructured documents, from medical reports, scanned forms, and way more. It's also historically been a massively manual process.

How to reduce token usage by 60% - 80%: Use memory with your LLM. A single line of code can reduce your token usage, improve context, and accuracy. With GPT-5 + memory: • From $11.25 down to $2.25 per 1M tokens • From $112.50 down to $22.50 per 10M tokens Pretty nuts!