I really want to learn how to make and deploy my own apps can anybody help me pls

Hi everyone, I am working on building a multi-agent system using the Google ADK library (thanks to @Brandon Hancock's ADK video, I've been able to move forward quickly!). I am running into architectural questions and would appreciate input from the community. 1. Context Engineering Best Practices When integrating tool calling or Model Context Protocols (MCPs), the context can become very large due to the volume of tool calling information required for complex, multi-step tasks. What is the best practice for performing context engineering when using agents to manage large context windows filled with tool instructions and calling history? 2. MCP Architecture Regarding MCP architecture, if the system requires many tools, what is the recommended strategy? Should we group relevant tools together and deploy multiple MCP servers, or is it better to wrap all tools within a single MCP server? Thanks for your time and expertise on this topic. Shima

My system was running a bit slow/unrfesponsive and then i spotted this on my system monitoring page The box only has 4 cpu's so it should only really run 4 jobs with 4 queues to be 100% utilised. I might be a tad over that. it was up at 800% + but by the time i snapped it it had fallen back a bit. Glad these are just test systems. though gives me food for thought for live deployments.

Has anyone else used tools like Dokploy to deploy their NextJS hosts to the web, or are we all still using Vercel? I have been using Dokpkoy and found it to be great, and it gives me hosting options at the lowest cost without being dependent on any hosting platforms. https://dokploy.com/

Just plodding away with my littl app and I decided that it was time to get rid of the frontend making DB calls and the backend competing with it for database connections. So a little bit of thought, a bit of prompting and we now have a much more seperated application with clear demarcation of front and backend. All achieved with Cursoe, shipkit rules, a bit of knowledge and a cavalier attitude to software development ( all backed up and version controled through numerous git commits) As you can see from the spider-like diagram (the one with red) DB-Connectivity-pre-migration I had Drizzle-ORM on the frontend making DB calls, and then at a later stage added in SQL alchemy in the backend with the view to moving all db calls to the backend , thereby not exposing my DB connections to the Internet. The second diagram(The green one) DB-Connectivity-post-migration shows a much leaner and performant application. You can easily see where the front end starts and finishes and where the backend takes over. And then i just threw in some other 'interesting' facts. All in all an enjpoyable excercise, granted with a bit of teething problems, but hey, thats what make it fun.