Microsoft Foundry: from landing zone to internal AI platform, a RAG reference architecture
adnan_hashmi · x · 2026-10-26
An engineering guide on evolving Microsoft Foundry from a landing zone into an internal AI platform. It covers controlled knowledge ingestion (chunk/embed/index into Azure AI Search with source authorization), grounded answering via authenticated RAG queries against Foundry-hosted model deployments with source references, plus evaluation and monitoring for quality, freshness, latency, and cost. The platform provides private connectivity, identity, logging, and templates, while product teams decide source authorization, retrieval, and acceptance criteria.
More from coding & agent
- Writing evals may become AI's highest-paying job: whoever owns the rubric controls agent output — hwchase17 · 2026-10-26
- Skillry launches a paid marketplace of "taste" skills for Claude Code, Codex and Cursor — yihui_indie · 2026-10-26
- Codex CLI's cyberpunk voice-token animation is just a split-flap airport board — arthurcolle · 2026-10-26
- Open-source 'be-ambitious' skill rewrites your prompt into an expert-level task — daniel_mac8 · 2026-10-26
- Engineer swears praising Codex ('youre doing a great job <3') gets better results — enggirlfriend · 2026-10-26
- Dev's take on personal agents: powerful with credentials, no need for cuteness — cnakazawa · 2026-10-26