# Getting started with AI

> Connect your Black Ice ontology to AI models in minutes.

**Category:** Getting started | **Tab:** getting-started

---

## Why connect AI to your ontology?

Black Ice structures your terminology, market rules, and brand voice. AI models consume that structure and turn it into governed content — translations, copy, QA checks — without guessing.

> Without an ontology, AI writes fluently. With one, it writes *correctly*.

## The 3-step pattern

Every AI integration follows the same basic flow:

**1. Export your ontology**

Go to **Settings → GitHub Sync** and push your workspace to a repository. This generates a structured Markdown bundle containing your concepts, terms, market definitions, and relationship maps — and keeps it automatically updated every time you sync.

Alternatively, use **Export → JSON Schema** or **Export → CSV** for one-off workflows.

**2. Connect your AI tool to the repo**

The recommended approach is to **link your AI tool directly to the GitHub repo** so it always reads the latest ontology — no manual uploads, no stale context.

| AI Tool | Recommended setup |
|---|---|
| Claude | **Connect your Claude Project to the GitHub repo** — always-current context, zero re-uploads |
| Claude Code | Point it at the same repo — it reads and operates on files directly |
| ChatGPT | Upload the export as a knowledge file in a **Custom GPT** (manual re-upload on changes) |
| Gemini | Paste into the prompt — the 1M token window handles large ontologies |
| Ollama | Load as a system prompt in your local pipeline (use `git pull` to stay current) |

> **Why GitHub-linked?** When you connect Claude Projects to the same repo that GitHub Sync pushes to, every concept update, term approval, or market definition change in Black Ice is automatically available in your next Claude session. No re-uploading, no re-prompting, no stale context.

**3. Prompt with semantic context**

Your prompts no longer need to explain terminology, tone, or market rules. The ontology already contains all of that. Instead, your prompts become task-focused:

- *"Write a landing page for the Spain market"*
- *"Review these translated strings for terminology consistency"*
- *"Localize only the concepts that changed since last sprint"*

## What can you do with it?

- **Generate market-specific content** without briefing docs
- **QA translations** against your approved terminology
- **Run delta localization** — only translate what changed
- **Enforce consistency** across multiple projects from a single ontology
- **Run fully local pipelines** for regulated industries

## Recommended integration: Claude + GitHub Sync

Claude's instruction-following precision and Claude Projects' GitHub integration make it the strongest fit for ontology-driven workflows. Enable GitHub Sync in Black Ice, connect your Claude Project to the same repo, and every session starts with your latest ontology — no uploads required. Claude Code extends this into agentic pipelines that operate directly on your repository.

→ See the full guide: [Black Ice + AI: What Your Ontology Unlocks](/docs/integrations/ai-integrations-overview)

## Next steps

- [Set up GitHub Sync](/docs/integrations/github-sync) to export your ontology
- [Read the full AI integrations guide](/docs/integrations/ai-integrations-overview) for model-specific workflows
- [Define your market rules](/docs/features/market-definitions) so AI models know your brand voice per locale