If you work in a regulated data environment, you already know you can't just send your SQL Server query plans to a cloud LLM. After 18 months of building on a single RTX 3090, I'm excited to share the solution: Bob, an autonomous, locally-hosted AI agent for SQL Server self-healing that never lets your data leave the LAN. Today I'm releasing The Birth of Bob a completely free book detailing the architecture, the code, and why local inference is the only viable answer for DBAs drowning in 200-page health reports. Check out the article below to read it, join the AI-for-DBAs community, and drop your own 3 AM database war stories in the comments. https://minsondata.com/birth-of-bob

Here's a helpful research document describing the different types of memory that you can easily plug into Hermes Agent.

I really wanted to try my hand at creating my own agent builder, 🤖 with my own Nodes. so here is what i got. it was a kick, i used my method found in my first class about prompting for the full build. on "AI for DBAs" so this is the second class. Remember it starts with a great PRD.md file so here is my file. the rest of the files can be found in the free class. Give it a try, it was fun for me! 🔥 This was vibe coded with claude code, but Gemini cli or github copilot would do the same if done right! The PROMPT files are in the free class on "AI for DBAs"

I'll go first: Claude Code. Why (my POV): - It feels like the most reliable coding partner when you use it correctly: clear task framing, tight scopes, and constraints. - I’m treating my dev work like a product: versioned releases on Git, plus a personal learning.md for decisions + "memory context". - I started this product as vibe coding, but now it’s turning into a production product - and Claude Code helps me keep structure while still shipping fast. Tradeoff / reality check: Even with good hygiene, I’m seeing 50K context usage out of a 200K window just for it to scan and understand files sometimes. Worth it for speed, but the context budget is real. My take: Claude Code wins when you don’t treat it like magic—you treat it like an engineer: - give it a mini-PRD, - curate context (learning.md, changelog, release notes), - force small, testable steps. Now your turn 👇Pick ONE tool and defend it. If nothing comes to your mind just pick from these: what's your bottleneck - context budget, accuracy, refactors, tests, or review quality?

This video wound up being longer than I thought it would. 🤷‍♂️ 1. Most of you will be able to use the very first installation method and be done in 90 seconds. 2. If you don't see the extension available in your VS Code extension marketplace, use method two. 3. If you like doing things the hard way, stay with me to the end and use method three.