Agent Guide

The Poolday agent is a general-purpose video editing system that can handle a wide range of tasks autonomously. Here are some examples of what it can do: • Edit and assemble video compositions from raw footage • Generate new visual assets using AI models (images, video clips, effects) • Add and sync audio, music, and voiceovers • Create and animate text, captions, and graphics • Apply transitions, effects, and color grading • Call one or multiple genAI models on one or multiple files (AI UGC, lipsync, background swap, etc.) • Translate and localize content across languages • Analyze footage and make creative decisions • Crop or resize footage into any target aspect ratio • Choose and cut footage based on user preferences • And more... The agent coordinates multiple specialized sub-agents, each responsible for a specific capability. Together, they plan, execute, and refine edits with minimal human input. You can chat and interact with the agent when unsure. You can ask it for any sort of help. It has full knowledge of what it can do and cannot do and can give you tips.

Treat Poolday like a creative agency you brief. You're the creative director. The clearer you describe what you want, the better the work comes back.

Your first video might take seven prompts. Your second, four. Your third, one or two. By then it knows your taste. Early on, expect a gap between what you wanted and what came back. That's normal. Keep going, and reach out for help if you need it.

The agent usually runs an hour or more on a video. That is by design. We work with businesses that value quality above all therefore the agent prioritizes quality. This can be adjusted by users in the UI.

Don't watch the screen. Brief it, answer its questions, then leave. Run as many conversations at once as you want. Our best customers keep five or more going.

Use this recipe. Fill the four lines and the first pass lands close: • Input: what you're handing it. • Desired output: what you want back. • Audience: who it's for. • Hard constraints: rules it can't break, like "the spokesperson is always on screen" or "never show coins."

Be specific about what you care about. "Keep the best moments" does nothing until you say what best means. The fast cuts? The punchline? Tell it.

It works well with references. Drop in images or videos you like and say what you like and what you don't. The more context up front, the better the first pass.

Import your brand guidelines, Figma, components, or just your website. Once it has your brand, everything comes back on-brand.

When taste matters, ask for options before it commits. For example: "Give me five voiceover directions to choose from, then keep going once I pick one."

Tell it where it has room to move. For example: "The CTA and product images are fixed, but you choose the pacing, music, and order of clips."

You control every pixel and every sound. Ask for the controls you want. Say "give me controls to adjust the volume of music and SFX" and you'll get them.

Point at anything in the video to select it. Drag a box to grab a few elements at once. Then tell the agent what to change.

Talk to it. Ask the best way to approach your problem, and push back when you disagree. It knows everything Poolday can do.

Skills are knowledge you teach the agent about your specific preferences. They help the agent understand what you mean when instructions are subjective. For example, a prompt like "Pick the best moments from this video" is subjective. "Best" means different things to different people: • For a lifestyle creator: moments with smiling faces, laughter, and dynamic movement • For a gaming channel: scenes with many characters on screen, explosions, and intense action • For a podcast: only the guest's answers, skipping the interviewer's questions By creating a skill, you teach the agent what "best" means for you. Once the skill is created, your prompt can simply say: "Pick the best moments from my video" The agent will apply your criteria automatically. How to create a skill: Describe what you want the agent to remember. Be specific about your preferences, style, and any constraints. Example: "Create a skill for picking highlights. I want moments with high energy: people laughing, fast movement, or dramatic reactions. Skip anything slow or with long pauses." Skills are saved to your account and can be updated or refined over time.

We support skills, custom apps, and ways to build your own workspace. Save that for later. For now, stay in the chat and ship your first videos.

Open a conversation, drop in your assets, and brief the agent. If you get stuck, ask us to add you to Slack.