Articles for people who
ship the stack
Original rewrites on React, Node.js, TypeScript and AI — practical notes from the same engineering practice behind our operator software. Article bodies are in English.
Tagged: AI Engineering
Diagnosing LLM Output Problems: When to Prompt, Retrieve or Fine-Tune
A symptom-first way to decide whether a weak AI feature needs a better prompt, a retrieval layer or fine-tuning, and why training a model on facts backfires.
7 min readServing a LoRA Fine-Tune Locally: Verify, Fuse and Avoid Silent Failures
Prove a LoRA adapter actually improved a small model, fuse and serve it behind a local OpenAI-compatible API, and catch the failures that return confident wrong output.
12 min readSix AI Concepts That Tell You What to Check Before Trusting an Answer
Tokens, context windows, temperature, hallucination, RAG and agents explained as verification tools, so you can spot errors, control cost and judge AI product claims.
10 min readComposing Speech, Vision and Generation Models into Multimodal Apps
Learn the six building blocks of multimodal AI, how speech, vision and generative models chain into pipelines, and which open tools and projects to start with.
11 min readImproving RAG Answers One Measured Change at a Time
A measure-first workflow for fixing weak RAG answers: tune chunking, top_k, reranking, hybrid search and query rewriting one at a time and track retrieval metrics.
4 min readFifteen LLM Concepts Traced Through a Single Support-Bot Request
Follow one customer question through an AI assistant to learn what models, tokens, embeddings, context, RAG, agents and evaluation really do, and where each one stops.
13 min readEvaluation Harnesses for LLM Apps: Datasets, Scoring and Regression Gates
Learn what an LLM evaluation harness is, its four core components, and how it catches prompt regressions and compares models fairly before anything reaches users.
9 min readFrom Scanned Lab Reports to Structured Data: OCR Architecture Trade-offs
How a budget-constrained health startup can weigh OCR libraries, Google Cloud APIs and a self-hosted vision LLM when turning medical scans into structured JSON.
8 min readWhy an LLM Call Is Not an App: Where LangChain Fits in a RAG Pipeline
Learn what LangChain actually does by tracing a document question-answering app from PDF upload to grounded answer, and see when an alternative framework fits better.
11 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.