> The full index of these docs is at [llms.txt](https://u22a8.ai/llms.txt). # Quickstart: a first verdict Get a key, call A8 from an SDK, from curl or from your assistant, and read the verdict it returns. This page takes you from a new key to a first verdict. Choose the route that fits how you work: an SDK or curl in [Call A8 from code](#call-a8-from-code), or an AI assistant that runs MCP servers in [Call A8 from your assistant](#call-a8-from-your-assistant). ## 1 Before you start - **An account.** [Sign up](https://u22a8.ai/auth/signup) to create your organization. - **Access to A8.** In **Console → A8**, say what you will use it for and select **Request access**. We write to you when A8 is on for your organization. Until then, a request returns `403` with code `model_not_enabled`. - **For code:** Python 3.10 or later, or Node.js 20 or later, with the `openai` package. Any client that takes a custom base URL works the same way. - **For an assistant:** an MCP host that connects to remote servers, such as Claude, ChatGPT, Claude Code or Cursor. ## 2 Call A8 from code ### 2.1 Create an API key In **Console → API keys**, select **Create key** and grant it `models:infer`. Copy the secret: the console shows it once. Then set it in your shell: ```bash export U22A8_API_KEY="" ``` See [API keys](https://u22a8.ai/docs/api-keys.md) for permissions. ### 2.2 Install the client **curl** curl ships with macOS, Linux and Windows 10 or later. **Python** ```bash $ pip install openai ``` **TypeScript** ```bash $ npm install openai ``` ### 2.3 Send a criterion and a subject The system message is the **criterion**: what is being judged. The user message is the **subject**: the thing under judgment. The schema is the shape of the **verdict**. A follow-up user message after A8’s response continues the conversation, and A8 answers it in turn. **curl** ```bash curl https://api.u22a8.ai/eval/v1/chat/completions \ -H "Authorization: Bearer $U22A8_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "a8", "messages": [ {"role": "system", "content": "Does the reply promise a refund?"}, {"role": "user", "content": "We will refund you in full by Friday."} ], "response_format": { "type": "json_schema", "json_schema": { "name": "verdict", "schema": { "type": "object", "properties": {"refund": {"type": "boolean"}} } } } }' ``` **Python** ```python import os from openai import OpenAI client = OpenAI( base_url="https://api.u22a8.ai/eval/v1", api_key=os.environ["U22A8_API_KEY"], ) resp = client.chat.completions.create( model="a8", messages=[ {"role": "system", "content": "Does the reply promise a refund?"}, {"role": "user", "content": "We will refund you in full by Friday."}, ], response_format={ "type": "json_schema", "json_schema": { "name": "verdict", "schema": { "type": "object", "properties": {"refund": {"type": "boolean"}}, }, }, }, ) print(resp.choices[0].message.content) # the verdict print(resp.model) # the version that answered ``` **TypeScript** ```typescript import OpenAI from "openai"; const client = new OpenAI({ baseURL: "https://api.u22a8.ai/eval/v1", apiKey: process.env.U22A8_API_KEY, }); const resp = await client.chat.completions.create({ model: "a8", messages: [ { role: "system", content: "Does the reply promise a refund?" }, { role: "user", content: "We will refund you in full by Friday." }, ], response_format: { type: "json_schema", json_schema: { name: "verdict", schema: { type: "object", properties: { refund: { type: "boolean" } }, }, }, }, }); console.log(resp.choices[0].message.content); // the verdict console.log(resp.model); // the version that answered ``` ### 2.4 Read the verdict The response is a standard `chat.completion` object. The verdict is the message content, as JSON that matches your schema: ```json { "id": "eval-9f2c1d84ab30e5f7", "object": "chat.completion", "created": 0, "model": "a8-1-1:90@20260715t140322z", "choices": [ { "index": 0, "message": { "role": "assistant", "content": "{\"refund\": true}", "refusal": null }, "finish_reason": "stop" } ], "usage": { "prompt_tokens": 24, "completion_tokens": 0, "total_tokens": 24, "prompt_tokens_details": {"cached_tokens": 0}, "completion_tokens_details": {"reasoning_tokens": 0} }, "system_fingerprint": "fit-1a2b3c4d5e6f7890.9e2a1b3c", "min_accuracy": 90 } ``` Recorded from `a8-1-1@20260715t140322z` on 2026-10-22. Three fields carry what you need: - `choices[0].message.content` is the verdict. - `model` names the exact version that answered, with the minimum accuracy it answered at as its tag. Send it back as `model` to get the same verdict again. See [Horizons](https://u22a8.ai/docs/a8-horizons.md). - `min_accuracy` is the level A8 promises the verdict at. The request named the bare model, so the minimum accuracy was the default and A8 answered at 90, or at the next level up it has earned: at least that share of the verdicts it returns at the level is correct. `min_accuracy` names the level. A case whose evidence falls short of the minimum accuracy comes back as an **abstention**: `content` is `null`, and `refusal` and a top-level `abstention` object give the level at which A8 answers the same request. See [Accuracy and abstention](https://u22a8.ai/docs/a8-abstention.md). ## 3 Call A8 from your assistant A8 runs as an MCP server, so an assistant can judge, [teach](https://u22a8.ai/docs/a8-teaching.md) and retract for you from inside a conversation. Judging needs `models:infer`. Teaching and retracting need `models:train`, and asking what you taught needs `models:explain`. ### 3.1 Connect the server Add a remote MCP server at `https://api.u22a8.ai/mcp`. Hosts that support sign-in take you through it, and the server acts with your role’s permissions in the organization you pick. Hosts that take a header send your API key as `Authorization: Bearer`, and the server acts with the key’s permissions. **Claude** In Claude, open **Settings → Connectors**, select **Add custom connector**, and enter `https://api.u22a8.ai/mcp`. Claude takes you through sign-in. **Claude Code** ```bash $ claude mcp add --transport http a8 https://api.u22a8.ai/mcp \ --header "Authorization: Bearer $U22A8_API_KEY" ``` To sign in instead, add the server with the URL alone, then run `/mcp` in Claude Code. **Cursor** Add the server to `~/.cursor/mcp.json`. Cursor reads the key from your environment: ```json { "mcpServers": { "a8": { "url": "https://api.u22a8.ai/mcp", "headers": {"Authorization": "Bearer ${env:U22A8_API_KEY}"} } } } ``` ### 3.2 Ask for a verdict Ask in plain words: > “Ask A8 whether this reply promises a refund: We will refund you in full by Friday.” Your assistant calls A8’s `judge` tool and reports the verdict: ```json { "verdict": {"refund": true}, "model": "a8-1-1:90@20260715t140322z", "min_accuracy": 90 } ``` Recorded from `a8-1-1@20260715t140322z` on 2026-10-22. See [MCP](https://u22a8.ai/docs/a8-mcp.md) for the tools, their schemas and the permission each needs. ## 4 Check that it worked - **From code:** the response has status `200`, `model` names a version such as `a8-1-1@20260715t140322z`, and `content` is JSON that matches your schema. - **From your assistant:** the host lists A8’s `judge`, `teach` and `retract` tools, and the `judge` result carries a `verdict` and a `model`. A `401` means the key is missing, invalid or revoked. A `403` names the permission the key lacks, or has code `model_not_enabled` while A8 is off for your organization. See [Errors](https://u22a8.ai/docs/errors.md) for every status code. ## Next steps - [A8 model card](https://u22a8.ai/docs/a8.md): A8 on one page: model IDs, pricing, capabilities, endpoints, features, rate limits and how it compares. - [Write a criterion](https://u22a8.ai/docs/writing-criteria.md): State a criterion A8 judges well, with one judgment per criterion, the situation that decides it and the practices that keep verdicts steady. - [Accuracy and abstention](https://u22a8.ai/docs/a8-abstention.md): How a request sets the minimum accuracy a verdict must meet, what that level promises and the five kinds of abstention.