Activity
Mon
Wed
Fri
Sun
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
What is this?
Less
More
Memberships
AI Developer Accelerator
10.7k members • Free
3 contributions to AI Developer Accelerator
11d •
AI Video Generator coming soon!
Hey guys! I'll soon be releasing all the prompts and scripts in a new YouTube video so you guys can generate your own AI video shorts like this one! I've had so much fun getting this to work! If there are any other Pokemon, you guys would like to see, let me know!!
2 likes • 11d
So very cool! Always loved Groudon and Mew Two but probably will not have the $$$ to generate the likes of this video.
May 29 •
[New Video] MCP + Agent Development Kit (ADK) Crash Course
MCP is quickly becoming the go-to standard for integrating powerful tools with your AI agents. If you're serious about building real-world AI solutions, mastering MCP is a must. In my latest crash course, I'm breaking down exactly how you can level up your ADK agents with MCP integrations that actually work. Here's what you'll learn: ✅ What MCP is, how it works, and why it's essential for ADK agents. ✅ How to build your first MCP-powered ADK agent using remote tools. ✅ Step-by-step instructions to set up your own local MCP server and connect it seamlessly to your ADK agents. As a bonus, I'm giving away all the example MCP + ADK code featured in the video completely free, so you can follow along easily. 👉 https://github.com/bhancockio/adk-mcp-tutorial/tree/main This video is packed with practical insights designed to get you up to speed fast. If you’re looking to enhance your AI development skills, don't miss this one. Cheers, Brandon Hancock 🧑💻
0 likes • Jun 29
Very interesting setup. @Brandon Hancock can this run with a local LLM like Ollama? I usually skip ADK examples due to their strong coupling with GCP and paid models.
0 likes • Jul 27
@Vishu Tanwar What Ollama model is recommended?
Mar 17 •
Struggle with RAG and Crew
I have lots of structure json files with title and description (could be job listing, property listing etc.). I'm trying to get a crew to return the top matching items for a given query title. All the examples I've seen work on a small example set but fail to handle large collections of documents like above. I use local LLM and often get warnings that the input prompt token count exceeded the limit. Tried the pro tools approach vs. the noob, but still struggles. A working example would be nice.
1 like • Mar 23
@Bastian Venegas I tried your suggestion, see the simple code here: https://gist.github.com/mirono/31d05e1319f78cf411dcc0bc8526a4a0 It doesn't look like it's working. The final answer was hallucinated jobs, and not jobs from one of the JSON files the tool was supposed to use: # Agent: Senior Jobs Screener ## Final Answer: { "jobs": [ { "job_id": "1", "location": "New York", "title": "Cloud Architect", "company": "Tech Corp", "description": "Design and implement cloud solutions for our clients.", "link": "https://techcorp.com/jobs/1" }, { "job_id": "2", "location": "London", "title": "Senior Cloud Architect", "company": "Innovate Solutions", "description": "Lead cloud infrastructure projects and mentor team members.", "link": "https://innovatesolutions.com/jobs/2" }, { "job_id": "3", "location": "Remote", "title": "Cloud Architect", "company": "Global Tech", "description": "Work on cutting-edge cloud technologies and services.", "link": "https://globaltech.com/jobs/3" } ] }
0 likes • Apr 11
@Brandon Hancock It is about 4K files with short titles (<100 chars) and description (<1000 chars). All the examples I've seen use a small document base for the RAG/Crew which hides this context length issues.
1-3 of 3
Active 3d ago
Joined Mar 17, 2025
Powered by