> ## Documentation Index
> Fetch the complete documentation index at: https://docs.auditynow.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Quickstart
> Get an AI agent talking to your Audity workspace in five minutes.
This is the agent path: install one connector, paste one token, run real workflows from your AI assistant of choice. If you'd rather call the API directly with curl or your own HTTP client, see [API Quickstart](/api-quickstart).
## Prerequisites
* An active Audity account with API access. A write-capable, audit-capable plan is recommended if you want the agent to create projects, convert leads, or spend credits.
* One of: Claude Desktop / Claude.ai (Pro+), ChatGPT (Plus+ for Custom GPTs), Cursor, n8n, or any MCP-compatible client
## 1. Get a Personal Access Token
1. Sign in to [app.auditynow.com](https://app.auditynow.com)
2. Go to **Settings → API Tokens**
3. Click **Create Token**
4. Label it (e.g. `Claude on my MacBook`, `n8n production`) and pick **Read + Write** scopes
5. Copy the token immediately, it starts with `aky_` and **is shown only once**
We can't recover a lost token. If you lose one, revoke it and create a new one. Never paste your token into a chat message body, only into your agent's connection settings or credential store.
## 2. Connect your agent
Each platform's setup has its own quirks; pick yours and follow the deeper guide for a step-by-step.
Settings → **Connectors** → **Add Custom Connector** → paste `https://docs.auditynow.com/mcp`. Configure the `Authorization: Bearer aky_` header when prompted.
[Full Claude guide →](/guides/claude)
Create a Custom GPT → **Configure → Actions → Import from URL** → `https://docs.auditynow.com/api-reference/openapi.json`. Auth: API Key, Bearer, paste your `aky_` (no `Bearer ` prefix, ChatGPT adds it).
[Full ChatGPT guide →](/guides/chatgpt)
Cursor Settings → **MCP → Add Server**. URL `https://docs.auditynow.com/mcp`, headers `Authorization: Bearer aky_`.
[Full Cursor guide →](/guides/cursor)
Add an **AI Agent** node, attach an **MCP Client Tool** sub-node. Endpoint `https://docs.auditynow.com/mcp`, Header Auth credential, header `Authorization: Bearer aky_`.
[Full n8n guide →](/guides/n8n)
## 3. Verify it works
Ask your agent any of these:
```text theme={null}
List my Audity projects.
```
```text theme={null}
What's my Audity tier and how many credits do I have left this month?
```
```text theme={null}
Search my Audity Nucleus for anything related to {a real client of yours}.
```
If the agent returns real data, your projects, your tier, your memories, you're connected. If it says "I don't have access to Audity" or returns 401/403, jump to your platform's troubleshooting accordion.
## 4. Run your first agent-driven audit
Try a task that chains multiple tools together. Use a real client name from your workspace, or a hypothetical one if you're evaluating:
```text theme={null}
Start a new Audity project for "Globex Industries", mid-market manufacturing.
Then trigger the audit analysis. Once it's done, summarize the top three
opportunities ranked by impact and flag the highest-severity risk. Cite each
opportunity by ID.
```
Under the hood:
1. `POST /api/projects`, creates the project (1,000 credits)
2. `POST /api/projects/{id}/audit-analysis`, runs synthesis (synchronous, 60–300 seconds). If an action times out, verify with `GET /api/projects/{id}/audit-analysis` before retrying; re-triggering an in-flight analysis can waste credits.
3. `GET /api/projects/{id}/opportunities`, fetches the AI-generated opportunities
4. The agent synthesizes a summary citing the IDs
The whole loop runs in the agent's context. You see the answer; Audity sees three legitimate API calls authenticated with your PAT, with credit deductions and audit logging applied normally.
**Save the project ID.** The agent will mention it in its response. You'll need it for follow-up prompts like "pull the deliverables for {id}" or "patch the description on {id}".
## 5. Try a Nucleus workflow
Audity's persistent memory layer is the agent's other superpower. After running a few audits, try:
```text theme={null}
What patterns do I have stored in Audity Nucleus across my healthcare clients?
For each one, include the confidence score and source type.
```
The agent calls `GET /api/nucleus/memories?type=pattern` and surfaces what's there. If you don't have any patterns yet, ask:
```text theme={null}
Capture this note for me into Audity Nucleus: "Healthcare clients consistently
underestimate the data governance lift required before any AI deployment.
Plan a 4-6 week governance phase before model work."
```
The agent calls `POST /api/nucleus/memories` and creates an explicit memory you'll find on every future Nucleus query.
## Scope for v1
The agent surface is deliberately narrow. These belong to the web app, not the API:
* **Document upload** (PDFs, transcripts, contracts). Once uploaded via the dashboard, agents can read documents via project detail.
* **Deliverable regeneration.** Stakeholder memos and other deliverable docs are produced by the synthesis pipeline; agents read them, they don't trigger fresh generation.
* **Web research.** The route exists but isn't on the agent allowlist in v1. Trigger from the web app.
* **PAT management via PAT.** Tokens are created and revoked from a browser session, not via the API.
If a workflow you need crosses one of these, [tell us](mailto:support@auditynow.com).
## What's next
The end-to-end agent recipe for taking a client from intake to deliverables.
Triage your ReadyLink inbox and convert qualified leads from your AI assistant.
Memories, captures, insights, contacts. The persistent layer.
Token formats, scopes, rotation, error codes, what's logged.
Skip MCP, call the API directly from a terminal or script.
The full OpenAPI 3.1 reference. Click any endpoint to try it live.