AI

AI you can stand behind.

Ten things I actually do with AI — not experiments, but in production, with guardrails you can explain to data protection, audit and management.

01

Building MCP servers

Several projects where agents maintain their own data — through custom MCP servers with clear tools, permissions and mandatory sources.

MCPAgentsAnthropic and OpenAI APIs
02

Agents that cross-check

One agent enters, another verifies. Nothing goes live without evidence and a source.

Four eyesQuality
03

Coordinating many agents

Parallel sessions with agreements, handovers and clear ownership instead of chaos in the repo.

OrchestrationWorkflows
04

Guardrails and approvals

Secrets only as references, cost approval before paid calls, human sign-off before anything public.

SafeguardsCompliance
05

AI in the dev team

Claude Code and Codex day to day: reviews, tests, CI — so the team gets faster, not less sure.

Claude CodeCodexPrompt engineering
06

Making knowledge findable

RAG and knowledge bases that give agents and people the same answers.

RAGEmbeddings
07

Structure from documents

PDFs, minutes and emails turned into clean data — with review where it matters.

ExtractionText analysis
08

Local and data-frugal

Local models and transcription when data must not leave the building.

OllamaWhisper
09

Marketing with agents

Keywords, landing pages and ads prepared by agents, approved by a human.

SEOGoogle Ads
10

Measure, don’t guess

Evals and cost control: what a model can do and what it costs is measured, not estimated.

EvalsCostOpenRouter

Let’s talk about AI in your team.

30 minutes, free. Afterwards you know whether and how I can help.