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

# Quickstart

> Go from zero to your first result in under 5 minutes.

You open Runable. You type what you want built. The agent builds it. This page gets you from sign-in to your first real output as fast as possible.

## Sign in

Go to [runable.com](https://runable.com) and sign in using one of four methods

You land on the home dashboard with an input bar at the center.

<Frame caption="The Runable home dashboard with the input bar and artifact type shortcuts.">
  ![Runable home dashboard showing the central input bar, artifact type shortcuts below it, and model selector](https://pub-51091dcf1e9d4b04bb2e74f489c4f346.r2.dev/8548467920510be2692be1af6bfba92a6e5462e3120ba2d5565bfb72887538a5.png)
</Frame>

## Pick what you want to create

Click an artifact type below the input bar before sending your message. Each type configures the agent with the right tools for the job.

| Artifact        | What it creates                                 | What you can set                                   |
| --------------- | ----------------------------------------------- | -------------------------------------------------- |
| **Slides**      | Presentation decks in HTML or image format      | Slide count, theme (Professional / Visual), format |
| **Report**      | Multi-page formatted documents                  | Page count                                         |
| **Spreadsheet** | Interactive spreadsheet files                   | —                                                  |
| **Carousel**    | Multi-slide social media posts                  | Slide count range                                  |
| **Image**       | AI-generated images on the canvas               | Aspect ratio                                       |
| **Video**       | AI-generated video clips                        | Aspect ratio, audio on/off                         |
| **Audio**       | Speech, music, sound effects, voice content     | Voice selection                                    |
| **Canvas**      | Freeform visual workspace for images and videos | —                                                  |
| **Website**     | Full-stack deployed web application             | —                                                  |
| **Chat**        | Text conversation with the Latest AI Models     | —                                                  |

You can also skip the artifact picker entirely. Type your prompt and the agent figures out which type to use.

## Write a detailed prompt

The more context you give, the better the output. Here are prompts you can copy and use right now.

<Tabs>
  <Tab title="Slides">
    <Prompt description={`Investor pitch deck for a fintech startup`} actions={["copy"]}>
      Create a 12-slide investor pitch deck for a fintech startup called PayFlow that helps freelancers manage invoices and get paid faster. Target audience is Series A VCs. Include these slides: title slide with tagline, the problem freelancers face with late payments, our solution (automated invoicing + instant payouts), how it works (3-step flow diagram), market size (global freelancer economy is $1.5 trillion), traction (12,000 users, $2M ARR, 40% MoM growth), business model (2.9% transaction fee + $15/mo Pro plan), competitive landscape showing our differentiation vs FreshBooks and Wave, team slide with 3 co-founders, financial projections for next 3 years, the ask ($5M Series A for engineering and go-to-market), and a closing slide with contact info. Use a clean, modern design with a blue and white color palette. Professional theme, not too corporate.
    </Prompt>
  </Tab>

  <Tab title="Website">
    <Prompt description={`Landing page for a coffee subscription service`} actions={["copy"]}>
      Build a landing page for a coffee subscription service called BeanBox. The page needs: a hero section with a headline like "Freshly roasted, delivered weekly" and a CTA button that says "Start your subscription", a section showing how it works in 3 steps (choose your roast, set your schedule, enjoy fresh coffee), a pricing section with 3 tiers (Starter at $14/mo for 1 bag, Classic at $24/mo for 2 bags, and Family at \$38/mo for 4 bags), a section with customer testimonials (make up 3 realistic ones), an FAQ section covering shipping, cancellation, and roast options, and a footer with social links and contact email. Use warm earth tones, a dark brown and cream color scheme, and make it feel premium but approachable. Include a Stripe checkout for the subscription tiers.
    </Prompt>
  </Tab>

  <Tab title="Video">
    <Prompt description={`Product teaser for a skincare brand`} actions={["copy"]}>
      Create a 10-second product teaser video for a luxury skincare brand called Glow Lab. The video should open with a close-up shot of a serum bottle on a marble surface with soft golden light. The bottle slowly rotates to reveal the label. Warm, aspirational mood. Soft bokeh in the background with blurred green botanicals. The lighting shifts slightly from warm gold to cool rose as the bottle turns. End with the bottle centered and a subtle sparkle effect on the glass. Aspect ratio 9:16 for Instagram Reels. Generate with audio, a soft ambient chime sound.
    </Prompt>
  </Tab>

  <Tab title="Report">
    <Prompt description={`Market research report on EV industry`} actions={["copy"]}>
      Write a 12-page market research report on the electric vehicle industry in Southeast Asia. Cover these sections: executive summary, current market size and growth rate for each major market (Thailand, Indonesia, Vietnam, Philippines, Malaysia), key players and their market share (BYD, Hyundai, VinFast, Tesla, local manufacturers), government incentive programs and policy landscape by country, charging infrastructure status and investment pipeline, consumer adoption trends and barriers (price, range anxiety, charging access), supply chain considerations (battery manufacturing, raw materials sourcing in the region), 5-year market forecast with growth projections, and strategic recommendations for a company considering entering the market. Use data tables and include the year for every statistic.
    </Prompt>
  </Tab>

  <Tab title="Image">
    <Prompt description={`Product mockup for a coffee brand`} actions={["copy"]}>
      Generate a photorealistic product shot of a matte black coffee bag with a minimalist white label that says "Blue Roasters" in a clean sans-serif font. The bag is standing upright on a wooden table. Behind it, slightly out of focus, there is a white ceramic pour-over dripper and a small potted succulent. Soft natural window light coming from the left. The mood is calm, premium, and modern. Studio-quality lighting with subtle shadows. Aspect ratio 4:3.
    </Prompt>
  </Tab>

  <Tab title="Audio">
    <Prompt description={`Phone greeting for a small accounting firm`} actions={["copy"]}>
      Generate a text-to-speech voiceover using the voice "George" for our accounting firm's phone system greeting. The script is: "Thank you for calling Oakridge Accounting. Our office hours are Monday through Friday, 9 AM to 5 PM Eastern. If you know your party's extension, you may dial it at any time. For tax preparation and filing, press 1. For bookkeeping and payroll services, press 2. For new client inquiries, press 3. To leave a general message, press 4. Or stay on the line and someone will be with you shortly. Thank you for choosing Oakridge Accounting." Keep the tone professional and warm, not robotic. Medium pace, clear pronunciation.
    </Prompt>
  </Tab>
</Tabs>

<Tip>
  You do not need a perfect prompt. The agent reads what you wrote, identifies what is missing, and asks clarifying questions before it starts building. But more detail upfront means fewer back-and-forth rounds and better results on the first try.
</Tip>

## Answer the agent's questions

Before building, the agent asks a few short questions to make sure it gets things right. The questions depend on what you are creating, but typically cover:

* Target audience and tone
* Visual style or color preferences
* Structure (how many pages, slides, or sections)
* Specific features or integrations needed

You answer once. The agent builds with those answers baked in.

<Frame caption="The agent asking clarifying questions before starting to build.">
  ![Chat interface showing the agent asking about audience, style preferences, and structure before generating content](https://pub-51091dcf1e9d4b04bb2e74f489c4f346.r2.dev/496c428f04512a6baa665fbad6e0bd4ab6b25c6d0727a7189165447cdc0c2573.png)
</Frame>

## Watch it build in real time

Once you answer, the agent starts working. Every agent chat gets its own isolated sandbox environment.

## Refine by talking

When the output appears, keep the conversation going. Tell the agent what to change.

<Prompt description={`Restyle a section of your website`} actions={["copy"]}>
  Make the hero section background dark (#1a1a2e) with white text. Change the headline to "Built for founders who ship fast." Make the CTA button use our accent color #e94560 with white text and rounded corners.
</Prompt>

<Prompt description={`Restructure a slide in your presentation`} actions={["copy"]}>
  Redesign slide 4 to show the market size data as a horizontal bar chart instead of bullet points. Add the source and year for each data point. Make the chart use our brand blue (#2563EB) and keep the background white.
</Prompt>

<Prompt description={`Add a new feature to your website`} actions={["copy"]}>
  Add a pricing section below the hero with three tiers in a card layout: Free (0/mo, 100 messages, 1 project), Pro (\$29/mo, unlimited messages, 10 projects, priority support), and Enterprise (custom pricing, unlimited everything, dedicated account manager). Add a "Get Started" button under each card that links to /signup?plan=free, /signup?plan=pro, and /contact respectively.
</Prompt>

The agent edits your existing output in place. You never leave the window.

<Info>
  Did not like a change? Click the rollback button on any previous message to restore that exact version. Or branch the conversation to try a different direction without losing your current work.
</Info>

## Know your input bar

| Element            | What it does                                                                                                                                                                                         |
| ------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Text area**      | Type your prompt here.                                                                                                                                                                               |
| **+ button**       | Attach files: images, PDFs, spreadsheets, videos, code, anything. Up to 10 files, 25 MB each. You can also drag and drop files, paste from clipboard, or take a screenshot.                          |
| **Chat mode**      | Switches to text-only conversation mode. The agent answers questions and analyzes attached images and PDFs, but it cannot execute code, generate media, or search the web.                           |
| **Plan mode**      | The agent researches your request, asks questions, and writes a detailed plan for your approval before building anything.                                                                            |
| **Model selector** | <Badge size="sm">Lite</Badge> Fast and low cost. <Badge color="blue" size="sm">Pro</Badge> Handles most tasks well. <Badge color="purple" size="sm">Max</Badge> Deep reasoning for complex projects. |
| **Connectors**     | Link Google, Slack, Notion, GitHub, Shopify, and 3,000+ other apps so the agent can work with your existing tools.                                                                                   |
| **Quick actions**  | Shortcuts below the input bar: Create Slides, Generate Videos, Build Websites, Canvas, and more. Tap one to start with a focused prompt.                                                             |

## Two things that will save you time

<Columns cols={2}>
  <div>
    ### Use Plan Mode for complex projects

    If your project has more than one or two moving parts (a multi-page website with Stripe, a database, and user auth), turn on **Plan Mode** before sending your message.

    The agent researches your request, asks clarifying questions, and writes a structured plan showing exactly what it will build and in what order. You review, adjust, and approve. Only then does it start.

    This saves you from the "that is not what I meant" moment three steps into a build.
  </div>

  <div>
    ### Save your preferences to memory

    Tell the agent your defaults once and it remembers them across every future conversation.

    <Prompt description="Set your brand defaults once. The agent remembers this in every future chat." actions={["copy"]}>
      Remember this for all future work: My company is called Dune. We build B2B SaaS tools. Brand colors are #1a1a2e (dark navy) and #e94560 (coral accent). Font is Inter. Always use dark mode for websites and presentations. Our tone is professional but not corporate. We speak directly, no buzzwords.
    </Prompt>

    Every website, deck, carousel, and image starts from these defaults. No repeating yourself.
  </div>
</Columns>

## Next steps

<CardGroup cols={2}>
  <Card icon="credit-card" href="/quickstart-copied-2" title="Plans and credits">
    See which plan fits your usage and how credits work.
  </Card>

  <Card icon="robot" href="/how-the-agent-works" title="How the agent works">
    Understand the agent loop, sandbox, tools, and real-time streaming.
  </Card>
</CardGroup>