# Plan Sovereign AI

> Runs checklists for sovereign AI planning — four control pillars, retrofit failure modes, guardrailed agent architecture, and sovereignty acceptance tests. Use when the user must meet GDPR, EU residency, on-prem, air-gap, model swap, or says "sovereign AI", "data sovereignty", "Cloud Act", "Haystack on-prem".

- Skill: `hiteshbandhu/plan-sovereign-ai` (Agent Skill, multi-file: 4 files)
- Install (CLI): `npx skillmds@latest add hiteshbandhu/plan-sovereign-ai`
- Raw SKILL.md: https://api.skillmd.com/api/skills/hiteshbandhu/plan-sovereign-ai/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: DevOps & Infra
- Author: hiteshbandhu (https://skillmd.com/u/hiteshbandhu)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/hiteshbandhu/plan-sovereign-ai

---


# Plan sovereign AI

Playbook from Bilge Yücel (Deepset). Pick a workflow in [workflows.md](workflows.md).

```
User goal?
├─ Map required sovereignty level           → A
├─ Plan retrofit on existing cloud stack      → B
├─ Design guardrailed agent reference arch    → C
└─ Run sovereignty acceptance checklist       → D
```

Source: `playlists/sovereign-ai-ai-engineer/`. Citations: [src-001 @ M:SS] in workflows.

Optional: `{SKILL_OUTPUT_DIR}/plan-sovereign-ai/`