Blog
Long-form tutorials and engineering notes on .NET, React, AI/ML, and SaaS architecture.
Filtered by:category: ai
AI
Build a payment-exceptions agent in LangGraph: deadline-aware triage, sanctions-hit analysis, repair drafting and a human-gated release — with full code.
AI
Core ML concepts for developers: dataset types, cleaning, splitting without leakage, Pipeline + ColumnTransformer, evaluation, full LightGBM pipeline.
AI
A developer's intro to Generative AI: model families, GPT & transformers, language modeling, AI ethics, and a real text-generation app with guardrails.
AI
Hugging Face deep dive: transformers, datasets, tokenizers, Trainer, peft (LoRA), accelerate, trl, gradio, Spaces. Full fine-tune + ship in one afternoon.
AI
Python for AI/ML done right: NumPy vectorization, pandas groupby + chaining, matplotlib OO, functional patterns, httpx + Pydantic APIs, JSON pitfalls.
AI
50 senior AI agent interview questions with deep answers: agent loops, tool design, MCP, multi-agent orchestration, memory, guardrails — real production code.
AI
55 senior Generative AI interview questions with deep answers: LLM internals, RAG, prompting, evals, cost and security — real production code throughout.
AI
Build production AI agents that don't loop forever or hallucinate tools — the agent loop, planning, tool use, memory, and guardrails, with real code.
AI
LLMs from first principles: tokenization, embeddings, RoPE, self-attention, multi-head, nanoGPT, pretraining, SFT, LoRA, QLoRA, DPO, vLLM serving.
AI
The MLOps playbook: deploying models (REST/batch/streaming), versioning + registry + CI/CD, drift monitoring, cloud strategies, and a full end-to-end app.
AI
How Mattrx swapped its Python ML service for ML.NET — regression, classification, and clustering trained in C#, in-process, no PhD required.
AI
Full C# RAG chatbot: Semantic Kernel + Azure AI Search hybrid + reranker + streaming + tenant security. Mattrx Help: 4% hallucination, 91% recall.