Everything we have written, sorted by ground

Building an agent that holds up in production, and knowing when you need several.

1. 01How to create an AI agent in an SME (without picking the wrong target)4′
2. 02Multi-agent: patterns when one agent is not enough3′
3. 03Model Context Protocol: wire an agent to your tools without chaos4′
4. 04AI automation: from isolated chat to pipeline3′

Grounding a model on your data without retraining it, and controlling what goes in.

1. 01RAG LLM: ground a model on your data without fine-tuning5′
2. 02Context engineering: making AI more deterministic in production5′
3. 03RAG vs fine-tuning: how SMEs should choose5′

Operating LLMs without chaos: evals, observability, and where to host.

1. 01LLMOps: run LLMs in production without chaos5′
2. 02Local AI: Ollama, self-host and real selection criteria4′

Keeping control of what the agent may do, and reviewing what it produces.

1. 01Human in the loop: designing supervision for AI agents4′
2. 02AI code review: speed up without automatic merge3′

Getting a team to work with AI without losing engineering discipline.

1. 01AI native: process, lucidity and team delivery4′
2. 02Claude Code: context, compact, clear and session hygiene10′
3. 03Vibe coding: when to explore and when to specify4′

What it actually costs, to set up and to run, and what to settle before signing.

1. 01AI agent for SMEs: setup budget, run cost and traps4′
2. 02AI ROI: quantify an agent's return before you sign6′