tekBlueprint

A while ago there was a post about agentic development for a project. This is a follow-up, but in a slightly different, more practical direction. The task was an MCP service / KAG / GraphRAG in Go. After completion, it “unexpectedly” turned out that the project contained a fatal flaw in the shape of the letter G. So a deliberate decision was made to migrate to Rust. This venture required changing the tech stack, the libraries, the algorithms, implementing an LSM-like mechanism for the vector database, and so on. In other words, it was not a mechanical port but a migration with substantial rework.

A spontaneous article on agentic development, written after some time and attempts at using this approach. Below are general theses, some of which I probably already touched on about a year ago. Overall, things turned out as expected. There was no revolution, and the bubble is deflating here and there, even though everyone pretends everything is “on plan”. The promised AGI, for some reason, still hasn’t taken over the world :)

Chances are many of you already use various tools to automate your work – some still at L1, others maybe reached L5 by now but haven’t told anyone about it. This article covers the L3 → L4 transition, where full automation is not very practical and frankly doesn’t make much sense. Otherwise this whole thing would devolve into yet another blog churned out by neural slop – endless streams of articles nobody asked for.

Another variation on the theme of combining backend and frontend in a single application. There have already been examples of Spring Boot with ReactJS, Go with HTMX and Electron with ReactJS. This time, the alternative to Electron is Wails v3, which combines Go and ReactJS to create native desktop applications.

Part 3 covered parallelism and speed techniques. This is the final part (4 of 4) of the Production LLM Inference series. It covers inference frameworks, production operations, and a practical decision framework for choosing the right stack.

Part 2 covered quantization and KV cache optimization. This is Part 3 of 4 — it focuses on the techniques that accelerate inference: multi-token prediction and distributed parallelism strategies.

Part 1 covered model architectures and the key metrics of production inference. This is Part 2 of 4 – it focuses on the two largest VRAM consumers: model weights and the KV cache. We’ll examine how quantization shrinks model weights and how KV cache techniques reclaim memory for higher batch sizes.

Running large language models in production requires more than loading a checkpoint and calling forward(). The gap between research benchmarks and real-world serving is defined by latency targets, memory budgets, and cost constraints that research papers rarely address.

Process Decision Record (PDR) – is a documented practice for recording decisions to change, introduce, or cancel processes within a team. While an ADR answers the question of which architecture to choose, a PDR defines how the team will work.