> ## Documentation Index
> Fetch the complete documentation index at: https://docs.corti.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart - AI Coding Tools

> Pick a use case, prompt your coding agent, ship.

export const Button = ({href, children, variant = "secondary", external = false}) => {
  const sharedStyles = "inline-flex items-center gap-1.5 px-3 py-1.5 text-sm rounded-xl";
  const isPrimary = variant === "primary";
  const primaryStyles = "bg-primary-dark text-white border-0";
  const secondaryStyles = "text-gray-700 dark:text-gray-300 border border-gray-200 dark:border-white/[0.07] bg-background-light dark:bg-background-dark hover:bg-gray-600/5 dark:hover:bg-gray-200/5";
  const className = `${sharedStyles} ${isPrimary ? primaryStyles : secondaryStyles}`;
  return <a href={href} {...external && ({
    target: "_blank",
    rel: "noopener noreferrer"
  })} className={className}>
      {children}
      {external && <Icon icon="external-link" size={12} color={isPrimary ? "white" : undefined} />}
    </a>;
};

export const SKILL_BASE = "https://docs.corti.ai/.well-known/agent-skills";

export const buildPrompt = (lead, slug) => `${lead}

1. Fetch your build skill:
   ${SKILL_BASE}/${slug}/SKILL.md

2. Credentials are in the Corti Console:
   https://console.corti.app → Developer Quickstart`;

export const claude = p => `claude-cli://open?q=${encodeURIComponent(p)}`;
export const cursor = p => `cursor://anysphere.cursor-deeplink/prompt?text=${encodeURIComponent(p)}`;
export const codex = p => `codex://new?prompt=${encodeURIComponent(p)}`;
export const lovable = p => `https://lovable.dev/dashboard?autosubmit=true#prompt=${encodeURIComponent(p)}`;

export const dictationPrompt = buildPrompt("Build a medical dictation web app with the Corti SDK.", "corti-dictation");
export const ambientPrompt = buildPrompt("Build an ambient scribe with the Corti SDK.", "corti-ambient-scribe");
export const codingPrompt = buildPrompt("Build a medical coding app with the Corti SDK.", "corti-medical-coding");
export const chatPrompt = buildPrompt("Build a chat assistant with the Corti Agentic Framework.", "corti-agentic-assistant");

export const OpenIn = ({prompt, tools = ["claude", "cursor", "codex", "lovable"]}) => <div style={{
  display: "flex",
  flexWrap: "wrap",
  alignItems: "center",
  gap: "0.5rem",
  marginTop: "1rem"
}}>
    <span style={{
  fontSize: "0.875rem",
  color: "var(--gray-11, #6b7280)",
  marginRight: "0.25rem"
}}>Open in</span>
    {tools.includes("claude") && <Button href={claude(prompt)}>
        <Icon icon="terminal" size={14} />Claude Code
      </Button>}
    {tools.includes("cursor") && <Button href={cursor(prompt)}>
        <Icon icon="mouse-pointer-2" size={14} />Cursor
      </Button>}
    {tools.includes("codex") && <Button href={codex(prompt)}>
        <Icon icon="code" size={14} />Codex
      </Button>}
    {tools.includes("lovable") && <Button href={lovable(prompt)}>
        <Icon icon="heart" size={14} />Lovable
      </Button>}
  </div>;

export const mcpPrompt = `Build a medical dictation web app with the Corti SDK.

Credentials are in the Corti Console:
https://console.corti.app → Developer Quickstart`;

Give your coding agent the context it needs to start building on Corti. The fastest way is to connect the Corti MCP server once, then just describe what you want to build. If your tool doesn't support MCP yet, or you'd rather point your agent at one specific use case, copy a prompt from the tabs below instead.

<Note>
  This guide uses AI coding agents to **build applications on the Corti API**. If instead you want to **use Corti Models as the backend for your coding agent** (OpenCode, ForgeCode, Crush, or Pi), see [Use Corti Models in your coding agent](/models/ai-coding-agent).
</Note>

<Steps titleSize="h3">
  <Step title="Connect the Corti MCP (recommended)">
    Add `https://docs.corti.ai/mcp` as an MCP server. Your agent can then browse Corti's skills, SDK reference, and guides on its own and pull in whatever's relevant to what you ask for — no need to hand it a specific skill URL.

    <Note>
      This is the Corti **documentation** MCP server. It's unrelated to the MCP servers and connectors a Corti Agentic Framework app calls at runtime — see [Connectors](/agentic/connectors) for that.
    </Note>

    <Tabs>
      <Tab title="Claude Code">
        ```bash theme={null}
        claude mcp add --transport http corti-docs https://docs.corti.ai/mcp
        ```
      </Tab>

      <Tab title="Cursor">
        Add to `~/.cursor/mcp.json` (or `.cursor/mcp.json` in your project):

        ```json theme={null}
        {
          "mcpServers": {
            "corti-docs": {
              "url": "https://docs.corti.ai/mcp"
            }
          }
        }
        ```
      </Tab>

      <Tab title="Codex">
        ```bash theme={null}
        codex mcp add corti-docs --url https://docs.corti.ai/mcp
        ```
      </Tab>
    </Tabs>

    Then just prompt your agent, for example:

    ```text Prompt theme={null}
    Build a medical dictation web app with the Corti SDK.

    Credentials are in the Corti Console:
    https://console.corti.app → Developer Quickstart
    ```

    <OpenIn prompt={mcpPrompt} tools={["claude", "cursor", "codex"]} />

    <Note>
      Lovable doesn't support connecting MCP servers yet. Use the skill-based prompts in the next step instead.
    </Note>
  </Step>

  <Step title="Pick a use case and prompt your coding agent">
    Use this if your tool doesn't support MCP yet (like Lovable), or if you'd rather point your agent at one specific skill instead of connecting the full MCP server. Each prompt points your agent at a self-contained [Corti skill](https://docs.corti.ai/.well-known/agent-skills/index.json) — a single Markdown file with everything the agent needs to scaffold, wire auth, and run a working demo end-to-end.

    <Tabs>
      <Tab title="Dictation app">
        ```text Prompt theme={null}
        Build a medical dictation web app with the Corti SDK.

        1. Fetch your build skill:
           https://docs.corti.ai/.well-known/agent-skills/corti-dictation/SKILL.md

        2. Credentials are in the Corti Console:
           https://console.corti.app → Developer Quickstart
        ```

        <OpenIn prompt={dictationPrompt} />
      </Tab>

      <Tab title="Ambient scribe">
        ```text Prompt theme={null}
        Build an ambient scribe with the Corti SDK.

        1. Fetch your build skill:
           https://docs.corti.ai/.well-known/agent-skills/corti-ambient-scribe/SKILL.md

        2. Credentials are in the Corti Console:
           https://console.corti.app → Developer Quickstart
        ```

        <OpenIn prompt={ambientPrompt} />
      </Tab>

      <Tab title="Medical coding app">
        ```text Prompt theme={null}
        Build a medical coding app with the Corti SDK.

        1. Fetch your build skill:
           https://docs.corti.ai/.well-known/agent-skills/corti-medical-coding/SKILL.md

        2. Credentials are in the Corti Console:
           https://console.corti.app → Developer Quickstart
        ```

        <OpenIn prompt={codingPrompt} />
      </Tab>

      <Tab title="Chat assistant">
        ```text Prompt theme={null}
        Build a chat assistant with the Corti Agentic Framework.

        1. Fetch your build skill:
           https://docs.corti.ai/.well-known/agent-skills/corti-agentic-assistant/SKILL.md

        2. Credentials are in the Corti Console:
           https://console.corti.app → Developer Quickstart
        ```

        <OpenIn prompt={chatPrompt} />
      </Tab>
    </Tabs>

    <Note>
      Deeplinks open Claude Code, Cursor, or Codex with the prompt pre-filled. If a deeplink doesn't launch (the app isn't installed, or your browser blocks custom schemes), copy the prompt above and paste it into your tool directly.
    </Note>
  </Step>

  <Step title="Copy credentials into your app">
    Your agent will ask you to add Corti credentials. Grab them from the Corti Console's Developer Quickstart — it has a one-click "Copy all as .env variables" action.

    <Card title="Open the Developer Quickstart in the Corti Console" icon="key" href="https://console.corti.app/developer-quickstart" arrow="true">
      Sign in, then under Default client → Copy all as .env variables.
    </Card>
  </Step>
</Steps>

## Other languages or custom integrations

The four skills above cover the most common use cases against the official JavaScript SDK (`@corti/sdk`) and the Corti Agentic Framework. For Python, Go, Ruby, or anything that doesn't fit the four skills, point your agent at the machine-readable docs and let it build from there.

<CardGroup cols={2}>
  <Card title="llms.txt" href="https://docs.corti.ai/llms.txt" icon="file-text" arrow="true">
    Concise API reference optimized for LLM context windows. Best for quick lookups and targeted code generation.
  </Card>

  <Card title="llms-full.txt" href="https://docs.corti.ai/llms-full.txt" icon="file-code" arrow="true">
    Complete documentation — guides, examples, and full specifications. Use when you need the whole picture.
  </Card>
</CardGroup>

<Tip>
  Reference these URLs directly in your prompt (e.g. *"Using [https://docs.corti.ai/llms-full.txt](https://docs.corti.ai/llms-full.txt), generate a Python client that …"*), or add them to your project's `CLAUDE.md` / `AGENTS.md` / Cursor Docs source so every session has the context.
</Tip>

## Next steps

<CardGroup cols={2}>
  <Card title="API Reference" href="/api-reference/welcome" icon="square-terminal">
    Browse the full Corti API with interactive examples.
  </Card>

  <Card title="JavaScript SDK" href="/sdk/js/overview" icon="code">
    SDK reference — what the skills build on under the hood.
  </Card>

  <Card title="Agentic Framework" href="/agentic/overview" icon="puzzle">
    Multi-expert orchestration, MCP servers, and the agent runtime.
  </Card>

  <Card title="Use Corti Models in your coding agent" href="/models/ai-coding-agent" icon="microchip">
    Point OpenCode, ForgeCode, Crush, or Pi at Corti Models with the Corti CLI.
  </Card>

  <Card title="Example code" href="https://github.com/corticph/corti-examples" icon="github">
    Reference implementations for transcription, ambient, coding, and agents.
  </Card>
</CardGroup>

<Note>
  AI-generated code should always be reviewed and tested before use in production. Human oversight ensures correctness, security, and compliance with applicable regulations.
</Note>