https://thomasdevos.com/tags/aiengineering/ Recent content in Aiengineering on Thomas Talks AI: Claude Code, AI Agents & Production Engineering Hugo -- 0.145.0 en-us Thomas De Vos © Tue, 12 May 2026 09:17:00 +0100 https://thomasdevos.com/posts/2026-05-12.09.17.00-from-ai-poc-to-production-the-part-teams-keep-skipping/ Tue, 12 May 2026 09:17:00 +0100 https://thomasdevos.com/posts/2026-05-12.09.17.00-from-ai-poc-to-production-the-part-teams-keep-skipping/ A practical AI engineering article on moving generative AI from POC to production: operating model, evals, observability, governance, security, cost, and rollout discipline. https://thomasdevos.com/posts/2026-05-10.10.24.00-llm-observability-is-not-a-dashboard-it-is-a-replayable-trail/ Sun, 10 May 2026 10:24:00 +0100 https://thomasdevos.com/posts/2026-05-10.10.24.00-llm-observability-is-not-a-dashboard-it-is-a-replayable-trail/ LLM observability for production AI systems: why teams need replayable traces, source evidence, tool-call records, eval checks, and prompt/model versioning. https://thomasdevos.com/posts/2026-05-09.11.08.00-ai-agents-in-financial-services-need-controls-before-autonomy/ Sat, 09 May 2026 11:08:00 +0100 https://thomasdevos.com/posts/2026-05-09.11.08.00-ai-agents-in-financial-services-need-controls-before-autonomy/ An AI engineering view on agents in financial services: permission boundaries, audit trails, human approval, evals, segregation of duties, and rollout discipline before autonomy.