INSIGHTS

Exploring the intersection of AI, SAP, and enterprise automation through research-driven perspectives and practical experience.

AI ENGINEERING

2026-07-26•7 min read

The Homelab Grand Prix: Racing 14 Quantized LLMs on Two DGX Sparks

I put fourteen quantized LLMs on the grid of my two-node DGX Spark cluster and timed every one, top speed measured in tokens per second. A 35B model took pole at 57.1 tok/s, but the real finding sits behind it: a 122B model lands within 29 percent of that, and speculative decoding nearly doubled a 120B into the same class. Total size predicts very little. Here is the full grid, the configuration each car ran, and what actually moves the needle.

AI ENGINEERING

2026-07-14•10 min read

Soofi S: A Sovereign AI Model from Germany, and Why the Details Matter

A German consortium just published Soofi S, a 30B open foundation model you are actually allowed to inspect: weights, training recipe, and per-source data accounting all on the table. I read the paper. Here is what it can do, why a sovereign model built in Germany matters, and where it earns its place in a business stack.

AI ENGINEERING

2026-07-10•8 min read

Standing Orders for Your Coding Agent: AGENTS.md Done Right

I run two coding agents side by side and kept re-typing the same corrections. So I read the standards, mined 2,500+ of my own prompts, and rebuilt my setup around one rule: put every instruction where it actually loads. Here is what the evidence says — and what I changed.

AI ENGINEERING

2026-07-08•8 min read

DFlash and the Warp-Drive Trick for Faster LLM Inference

Autoregressive decoding hits the same wall a rocket does near light speed: more raw compute buys less and less. DFlash, a new ICML 2026 paper from UC San Diego's Z Lab (arXiv:2602.06036), sidesteps it with block-diffusion drafting instead of brute force. I read the paper, checked the benchmarks, and tested what it actually takes to run it on my own DeepSeek V4 Flash box.

AI ENGINEERING

2026-07-03•11 min read

Deep Agents from Scratch: A 6-Session Field Guide to Shipping Agents You Can Trust

Data Science Dojo and SambaNova ran a hands-on webinar series that builds a production-grade AI agent from a bare ReAct loop all the way to evaluation and deployment. I walked through every notebook — here is the distilled arc: think, build, remember, capable, scale, ship. Code and notebooks are public on GitHub.

AI ENGINEERING

2026-06-24•8 min read

Choosing an Agentic AI Framework: A Decision-Maker's Map

Dozens of agentic AI frameworks now compete for attention, and most comparisons mislead — they pit tools from different layers against each other. Here is a clear map: what LangChain, MLflow, Haystack and the leading alternatives actually do, the six dimensions that separate them, and how to choose without locking yourself in.

AI ENGINEERING

2026-06-09•16 min read

Measuring RAG Performance: Metrics That Actually Tell You Something

A RAG pipeline produces fluent answers from day one — whether or not they are correct. Here is how to measure RAG performance properly: retriever, generator and end-to-end metrics, why overlap scores like BLEU mislead, how to wire it all into a test suite with DeepEval, and what a measured benchmark of six RAG pipelines reveals.

AI ENGINEERING

2026-05-12•9 min read

Grounding LLMs in Verified Knowledge with Oxigraph

Large language models are fluent but not factual. Here is how an RDF triple store like Oxigraph turns a knowledge graph into a verifiable source of truth an LLM can query — and why that beats trusting the model's memory.

AI & ERP

2025-03-15•7 min read

Enabling LLMs to Navigate ERP Systems

Exploring the intersection of Large Language Models and Enterprise Resource Planning — how AI can understand and automate complex SAP workflows.

AI ENGINEERING

2025-02-28•8 min read

RAG Architectures for Enterprise Knowledge

Building production-ready Retrieval-Augmented Generation pipelines for enterprise environments — from vector embeddings to evaluation frameworks.

PROCUREMENT

2025-01-20•6 min read

Agentic AI in Procurement Workflows

How autonomous AI agents are transforming procurement — from supplier evaluation to requisition routing and approval orchestration.

Stay Informed

Follow my research and insights on AI-driven enterprise automation

CONNECT ON LINKEDIN FREELANCERMAP PROFILE