Just Five Mins!

So, where is all of this vibe coding taking us? Serious question, and I am not knocking the whole vibe coding thing - it does really does help anyone build apps, but what kind of apps? and how are they working in production/live?Some links from the show:LovableReplitGoogle Antigravity - actually, it is a downloadable app… I might have mixed up Google Firebase studio! :) which, in turn, is probably Windsurf now Google own it :)Hey, this is a free podcast. However, if you feel you want to support me, then check out Patreon. I will have some more detailed deep dives for Patreon members as well as one-to-one sessions. Or just buy a unicorn a coffee here! Oh, and yes, I have ended up on YouTube (doesn’t everyone eventually?):https://www.youtube.com/@justfifteenmins but don’t worry, no ugly face to worry about (yet!). Get full access to Just Five Mins! at www.justfivemins.com/subscribe

Here is the link from Anthropic about the topic being discussed.Hey, this is a free podcast. However, if you feel you want to support me then check out Patreon. I will have some more detailed deep dives for Patreon members as well as one-to-one sessions. Or just buy a unicorn a coffee here! Oh, and yes, I have ended up on YouTube (doesn’t everyone eventually?):https://www.youtube.com/@justfifteenmins but don’t worry, no ugly face to worry about (yet!) Get full access to Just Five Mins! at www.justfivemins.com/subscribe

Well, it is one of those rambling weekends again!Link to the research paper here about TRM (Tiny Recursive Model)Hey, this is a free podcast. However, if you feel you want to support me then check out Patreon. I will have some more detailed deep dives for Patreon members as well as one-to-one sessions.Or just buy a unicorn a coffee here!Oh, and yes, I have ended up on YouTube (doesn’t everyone eventually?):https://www.youtube.com/@justfifteenmins but don’t worry, no ugly face to worry about (yet!). Get full access to Just Five Mins! at www.justfivemins.com/subscribe

Well, more agent stuff then! but what are you all doing with these AI agents?Open AI just released agent builder. If you believe their documentation, codex (their coding AI offering) wrote 80% of the agent builder itself… if that is indeed true, it is rather amazing.However, building out agent solutions other than hobby projects or small PoC’s, is probably more involved. That is where A2A protocol comes in from Google. Along with MCP (model context protocol), it provides a complimentary protocol to handle the authorisation/authentication and so on between agents.Anyway, take a listen for more!Hey, this is a free podcast. However, if you feel you want to support me then check out Patreon. I will have some more detailed deep dives for Patreon members as well as one-to-one sessions.Or just buy a unicorn a coffee here!Oh, and yes, I have ended up on YouTube (doesn’t everyone eventually?):https://www.youtube.com/@justfifteenmins but don’t worry, no ugly face to worry about (yet!). Get full access to Just Five Mins! at www.justfivemins.com/subscribe

Who doesn’t like FREE ?Well, JetBrains (the folks who created WebStorm, PyCharm and Rider etc.) have now released one of my favourite database management tools free; DataGrip.Free for non-commercial use, but what a great tool to get across. So many different databases you can connect to not to mention a more lovely experience connecting to SAP HANA :)Read the blog post here and downloadHey, this is a free podcast. However, if you feel you want to support me then check out Patreon. I will have some more detailed deep dives for Patreon members as well as one-to-one sessions.Or just buy a unicorn a coffee here!Oh, and yes, I have ended up on YouTube (doesn’t everyone eventually?):https://www.youtube.com/@justfifteenmins but don’t worry, no ugly face to worry about (yet!). Get full access to Just Five Mins! at www.justfivemins.com/subscribe

Okay, a little experiment. Okay, I have been researching how LLMs work with vectors and how AI search works for a while now. But rather than me warble on for a while (and more than 5 mins!), I have tried an AI approach to explain the research ;)In fairness, I did listen back to this, and personally I was quite impressed. The explanation about quantization methods was particularly useful.If vectors, AI search and quantization mean nothing to you - take a listen :)Hey, this is a free podcast. However, if you feel you want to support me then check out Patreon. I will have some more detailed deep dives for Patreon members as well as one-to-one sessions.Or just buy a unicorn a coffee here!Oh, and yes, I have ended up on YouTube (doesn’t everyone eventually?):https://www.youtube.com/@justfifteenmins but don’t worry, no ugly face to worry about (yet!). Get full access to Just Five Mins! at www.justfivemins.com/subscribe

🧠 What RAG Actually DoesRAG enhances LLMs by retrieving relevant external information (e.g. from documents or databases) at query time, then feeding that into the prompt. This allows the LLM to answer with up-to-date or domain-specific knowledge without retraining.💸 Is RAG Expensive?Yes, it can be — especially if:* You repeatedly reprocess large documents for every query.* You use high token counts to include raw content in prompts.* You rely on real-time parsing of files (e.g. PDFs or Excel) without preprocessing.This is where vector storage and embedding optimization come in.📦 Role of Vector StorageInstead of reloading and reprocessing documents every time:* Documents are chunked into smaller segments.* Each chunk is converted into a vector embedding.* These embeddings are stored in a vector database (e.g. FAISS, Pinecone, Weaviate).* At query time, the user’s question is embedded and matched against stored vectors to retrieve relevant chunks.This avoids reprocessing the original files and drastically reduces cost and latency⚙️ Efficiency StrategiesHere’s how to make RAG more efficient:StrategyDescriptionBenefitVector StorageStore precomputed embeddingsAvoids repeated parsing and embeddingANN IndexingUse Approximate Nearest Neighbor searchFast retrieval from large datasetsQuantizationCompress embeddings (e.g. float8, int8)Reduces memory footprint with minimal accuracy lossDimensionality ReductionUse PCA or UMAP to reduce vector sizeSpeeds up search and lowers storage costContextual CompressionFilter retrieved chunks before sending to LLMReduces token usage and cost Get full access to Just Five Mins! at www.justfivemins.com/subscribe

Design for UI/UX is obviously an art form, but can AI do as good a job or better? or as the case may well be, using AI to help with the tedious stuff?UX PilotFigmaHey, this is a free podcast. However, if you feel you want to support me then check out Patreon. I will have some more detailed deep dives for Patreon members as well as one-to-one sessions.Or just buy a unicorn a coffee here!Oh, and yes, I have ended up on YouTube (doesn’t everyone eventually?):https://www.youtube.com/@justfifteenmins but don’t worry, no ugly face to worry about (yet!). Get full access to Just Five Mins! at www.justfivemins.com/subscribe

Okay, AI agent automation is everywhere and so are MCPs (Model Context Protocol) to allow you to connect to anything and everything via AI. However, this still needs some technical know-how, even in the low-code offerings.But what if you have a complete virtual AI employee? and better yet, where it can work with your existing applications seamlessly - even older ERP systems or applications that have no API or external connections?Let’s take a listen to find out more!Warmwind OSWarmwind OS introThis is a deeper dive into Warmwind OSHey, this is a free podcast. However, if you feel you want to support me then check out Patreon. I will have some more detailed deep dives for Patreon members as well as one-to-one sessions.Or just buy a unicorn a coffee here!Oh, and yes, I have ended up on YouTube (doesn’t everyone eventually?):https://www.youtube.com/@justfifteenmins but don’t worry, no ugly face to worry about (yet!). Get full access to Just Five Mins! at www.justfivemins.com/subscribe

So, a slightly boring episode but surprisingly useful, I think. Hey, this is a free podcast. However, if you feel you want to support me then check out Patreon. I will have some more detailed deep dives for Patreon members as well as one-to-one sessions.Or just buy a unicorn a coffee here!Oh, and yes, I have ended up on YouTube (doesn’t everyone eventually?):https://www.youtube.com/@justfifteenmins but don’t worry, no ugly face to worry about (yet!). Get full access to Just Five Mins! at www.justfivemins.com/subscribe

Oh dear, so many meme phrases!Hey, this is a free podcast however, if you feel you want to support me then check out Patreon. I will have some more detailed deep-dives for Patreon members as well as one-to-one sessions.Or just buy a unicorn a coffee here!Oh, and yes, I have ended up on YouTube (doesn’t everyone eventually?):https://www.youtube.com/@justfifteenmins but don’t worry, no ugly face to worry about (yet!). Get full access to Just Five Mins! at www.justfivemins.com/subscribe

Using VS Code (free and open source) along with the AI Toolkit extension allows you to play with several different AI models as well as local models - all from one user interface. Yes, you can run AI models locally! (okay, not the larger online ones!) and certainly the SLM (small language models) models like PHI-4 from Microsoft.You can even get into building AI agents visually and generate actual code!You don’t have to be a developer - this stuff is easy enough to use if you are curious about this sort of thing. If you want some guidance or examples of what you can do, just ping over a comment and I will be happy to help.Hey, this is a free podcast however, if you feel you want to support me then check out Patreon. I will have some more detailed deep-dives for Patreon members as well as one-to-one sessions.Or just buy a unicorn a coffee here!Oh, and yes, I have ended up on YouTube (doesn’t everyone eventually?):https://www.youtube.com/@justfifteenmins but don’t worry, no ugly face to worry about (yet!). Get full access to Just Five Mins! at www.justfivemins.com/subscribe

What does all this mean?Microsoft AI Extensions: An abstract set of classes to enable a c# .Net developer to talk to different AI models/platforms instead of specific individual frameworks. Also allows you to create and interact with MCP (model context protocol).MCP: Model Context Protocol - soooo many resources out there now. I did an episode on MCP a few podcasts ago if you want to take a look/listen.Azure AI Foundry Local: A bit like Ollama allowing you to run AI models locally :) Get full access to Just Five Mins! at www.justfivemins.com/subscribe

How easy is it to create AI agents? without code (or at least minimal!)?Take a listen as we refresh our memories with n8n.io. Build automation workflows but specifically AI agent-based ones! all this locally or on your infrastructure too!Hey, this is a free podcast. However, if you feel you want to support me then check out Patreon. I will have some more detailed deep dives for Patreon members as well as one-to-one sessions.Or just buy a unicorn a coffee here!Oh, and yes, I have ended up on YouTube (doesn’t everyone eventually?):https://www.youtube.com/@justfifteenmins but don’t worry, no ugly face to worry about (yet!). Get full access to Just Five Mins! at www.justfivemins.com/subscribe

Well, I have been trying to settle on some day-to-day tools i.e. OneNote for my note taking (don’t shoot me!) and I did have Todoist for tracking my endless lists of things to either “really do” or attempt to capture for later (yeah right!).Although there are lots of choice, and that is a good thing, I thought with Todoist I had found the perfect “ToDo” app (or just a large bucket of broken dreams!). No problem with Todoist at all, but I came across Tick Tick and dismissed it a few times.About 6 months ago I figured I would give Tick Tick a try. Anyway, have a listen if you want to find out how that went. No affiliates or selling here, just info from my perspective :)Hey, this is a free podcast. However, if you feel you want to support me then check out Patreon. I will have some more detailed deep dives for Patreon members as well as one-to-one sessions.Or just buy a unicorn a coffee here!Oh, and yes, I have ended up on YouTube (doesn’t everyone eventually?):https://www.youtube.com/@justfifteenmins but don’t worry, no ugly face to worry about (yet!).Unicorn University:https://applied-ai-services.kit.com/020c6040f2 Get full access to Just Five Mins! at www.justfivemins.com/subscribe

So, are you “vibe coding”? or just asking AI to help with some code?Have you come across custom instructions for VS Code? Windsurf and Cursor AI etc. all of their options too.Provide a preset app requirements and/or product requirements document (PRD) and you can make building apps with AI a bit more predictable and follow your guidelines about the tech stack you want to use, testing approach etc.Hey, this is a free podcast. However, if you feel you want to support me then check out Patreon. I will have some more detailed deep dives for Patreon members as well as one-to-one sessions.Or just buy a unicorn a coffee here!Oh, and yes, I have ended up on YouTube (doesn’t everyone eventually?):https://www.youtube.com/@justfifteenmins but don’t worry, no ugly face to worry about (yet!).Unicorn University:https://applied-ai-services.kit.com/020c6040f2 Get full access to Just Five Mins! at www.justfivemins.com/subscribe

Well, just a ramble as advertised! Some links mentioned in the show:Microsoft Build 2025Google IOAnthropicGoogle StichHey, this is a free podcast. However, if you feel you want to support me then check out Patreon. I will have some more detailed deep dives for Patreon members as well as one-to-one sessions.Or just buy a unicorn a coffee here!Oh, and yes, I have ended up on YouTube (doesn’t everyone eventually?):https://www.youtube.com/@justfifteenmins but don’t worry, no ugly face to worry about (yet!).Unicorn University:https://applied-ai-services.kit.com/020c6040f2 Get full access to Just Five Mins! at www.justfivemins.com/subscribe

Firstly, I am not sure what AI did to generate that title image!As mentioned in the shameless plug, I will be starting to do some further deep dives/one-to-one things soon via Patreon… if you are interested of course! (see links below).Anyway, plugging aside, I did a video a few months ago about Cursor AI (a VS Code based AI editor) and using local LLMs. Although you can use local LLMs (via Ollama or LMStudio etc.), the experience wasn’t very connecting :)VOID AI Editor addresses this. In fact, it is an open-sourced version of Cursor AI, still based on VS Code, but absolutely does integrate directly with local LLMs such as Llama 4, DeepSeek etc.Hey, this is a free podcast however, if you feel you want to support me then check out Patreon. I will have some more detailed deep dives for Patreon members as well as one-to-one sessions.Or just buy a unicorn a coffee here!Oh, and yes, I have ended up on YouTube (doesn’t everyone eventually?):https://www.youtube.com/@justfifteenmins but don’t worry, no ugly face to worry about (yet!).Unicorn University:https://applied-ai-services.kit.com/020c6040f2 Get full access to Just Five Mins! at www.justfivemins.com/subscribe

So, if you code (including “Vibe Coding” if you must!) or are just a “fiddler” (like myself!) then you have no doubt used some sort of code editor.Because I mostly live in a Microsoft world, Visual Studio (as of this recording, v 2022) has been my mainstay. But what about cross platform editors (and indeed IDEs - Integrated Development Environments)? and, given all of the choices around us, what about other vendors?That is what we are talking about this time on JFM! :)Hey, subscription to this podcast is FREE if you want to subscribe! I hadn’t realised before it forced you to pay ;) Of course, if you wish to or must pay, then please feel free with a paid subscription or via PatreonOr just buy a unicorn a coffee here!Oh, and yes, I have ended up on YouTube (doesn’t everyone eventually?):https://www.youtube.com/@justfifteenmins but don’t worry, no ugly face to worry about (yet!).Unicorn University:https://applied-ai-services.kit.com/020c6040f2 Get full access to Just Five Mins! at www.justfivemins.com/subscribe

Oh yes, jumping on the band wagon again!Open AI released a whole lot of updated models and so on last week. But one tool (in preview) jumped out. Open AI Codex CLI.Now, from first impressions, this looks and feels a lot like Anthropic Claude Code that I looked at a few weeks back. But hey, everyone copies everyone right?Anyway, it is more of a “technical” thing to use but you really don’t have to be super technical. It, like Claude Code, generated very clean code based on just a couple of prompts.Anyway, take a listen for more :)Some links from the show:Open AI Codex CLI - Getting StartedHey, subscription to this podcast is FREE if you want to subscribe! I hadn’t realised before it forced you to pay ;) Of course, if you wish to or must pay, then please feel free with a paid subscription or via PatreonOr just buy a unicorn a coffee here!Oh, and yes, I have ended up on YouTube (doesn’t everyone eventually?):https://www.youtube.com/@justfifteenmins but don’t worry, no ugly face to worry about (yet!).Unicorn University:https://applied-ai-services.kit.com/020c6040f2 Get full access to Just Five Mins! at www.justfivemins.com/subscribe