Chainlink Confidential Ai Attester Skill

Chainlink Confidential AI Attester

Runs LLM inference inside Trusted Execution Environment (TEE). Documents go in, LLM analysis comes out — the raw documents are never stored or exposed.

Beta product for the EthGlobal NYC hackathon. Get an API key at the Chainlink booth or via the #partner-chainlink channel in the EthGlobal Discord.

Playground UI: https://confidential-ai-dev-preview.cldev.cloud/playground — easiest way to try it. Everything there maps 1:1 to the API calls below.

---

Workflow 1 — Submit: POST /v1/inference

Auth: Authorization: Bearer $API_KEY — always use an env var, never hardcode.

Request shape:

{
  "model": "gemma4",
  "system_prompt": "",
  "prompt": "...",
  "resources": [{ "filename": "doc.pdf", "content_type": "application/pdf", "content_base64": "" }],
  "cre_callback": { "url": "https://..." }
}

• cre_callback is optional — omit it and poll instead.
• Models: gemma4 (images/general, default), qwen3.6 (long text).
• Prefer PNG over PDF for demos — PDF preprocessing can take up to 5 minutes.

Response: 202 Accepted → { "id": "...", "status": "queued" } — save the id.

For curl examples and multi-language snippets → [references/code-examples.md](references/code-examples.md) For full request/response spec, error codes, resource types → [references/api-reference.md](references/api-reference.md)

---

Workflow 2 — Poll: GET /v1/inference/{id}

Poll every 2–5 s until status is completed or failed.

Key fields on completion: output (LLM text), usage, completed_at.

For error symptoms → [references/troubleshooting.md](references/troubleshooting.md)

---

Writing Prompts That Work

Always enforce JSON output with two layers:

1. System prompt — keep the default unless you have a specific reason to change it.
2. User prompt — binary question + exact JSON schema to return

For per-use-case prompt templates (lending, KYC, accredited investor, proof of reserves) → [references/prompts.md](references/prompts.md)

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: smartcontractkit
• Source: smartcontractkit/chainlink-agent-skills
• License: MIT

Install and usage instructions live in the source repository linked above.