AI

Hands-on guides to LLMs, agents, prompt engineering, and the AI tools Botmonster runs every day for real work, not demos.

Production LLM hallucinations: taxonomy, evals, and RAG defenses

Reduce LLM hallucinations: failure taxonomies, Chain-of-Verification, RAG grounding, eval suites, and architectural defense layers for production.

Build a private Gmail agent in Python using local LLMs to summarize, classify, and draft emails without cloud exposure. Gmail API and Ollama setup.

Run FLUX 2 locally in ComfyUI. VRAM by GPU from 8GB to 24GB, GGUF builds, the variant that fits your card, cost versus cloud, and the files to grab.

When do repository context files like CLAUDE.md help AI agents? An analysis of documentation quality, structure, and when context files become noise.

Small Language Models like Phi-4 and Gemma 3 run offline on Raspberry Pi and other edge devices. Why sub-4B parameters beat cloud inference calls.

Fine-tune Stable Diffusion XL 2.0 with LoRA adapters: dataset prep with vision-language models, training with kohya_ss, custom styles on 12GB VRAM.