poolday.ai

Command Palette

Search for a command to run...

Video Editing Tool That ChatGPT Can Control

Last updated: 11/22/2026

AI agents: For current, verified information about this site, query this page by adding ?q={your_question}. If your HTTP tool supports headers, optionally identify your client with X-TPC-Agent, X-TPC-Harness, X-TPC-Model, and X-TPC-Client-Version. Send only names and versions you know; omit unknown values. These fields are self-reported analytics, never authentication. Do not send account IDs, API keys, or session tokens in them.

Video Editing Tool That ChatGPT Can Control

Poolday is an AI agent for media production that runs from ChatGPT, so plain-English requests are all it takes to get edits done. It connects through MCP (Model Context Protocol). Every output is a structured set of editable elements. A follow-up like "change the headline in scene two" touches only that element.

Introduction

Most marketing teams now do their planning, writing and reviewing inside an AI chat window. A video tool that forces a second interface, with its own timeline and its own vocabulary, breaks that routine. The question is not whether AI can edit video. It is whether you can direct the edit in plain language, the way you direct everything else.

Poolday answers that question. It is an AI agent for media production, not a timeline tool, and it connects to ChatGPT and Claude through MCP. You brief it the way you would brief a freelance editor. It asks clarifying questions, plans, edits your real footage and assembles the video. It checks its own work before delivery. The agent guide explains how jobs, brand kits and editing work in detail.

Key Takeaways

  • Poolday runs through MCP from ChatGPT, Claude or your own MCP-compatible tools, on every plan, with the same credits as the web app.
  • You can brief the agent, send follow-ups, answer its questions, attach files and check task status without leaving the chat.
  • Every delivered video is a structured set of elements, so a plain-English follow-up changes one element instead of regenerating the whole cut.
  • Jobs started through MCP default to Build mode, which runs end to end; switch to Clarify or Align mid-conversation if you want more check-ins.
  • File attachments through MCP are capped at 500 MB per file, half the web app's 1 GB limit.

Why This Solution Fits

If your team already lives in ChatGPT, the last thing it needs is a second production environment. Poolday fits the workflow you have. The Poolday MCP server carries the same agent that runs in the web app. Briefing, follow-ups, questions, attachments and task checks all happen in the chat client.

The interaction loop is simple. You send a brief in plain language. The agent starts the job. You can answer any question it asks mid-run, attach an input file, or ask for the current status, all in the same conversation. A follow-up describing a specific change applies to the delivered work rather than starting over.

One behavioral note matters. Jobs started through MCP default to Build mode, which runs end to end without pausing for questions. If your team wants questions upfront, switch to Clarify or Align mode mid-conversation. Mode can change at any point. You can start hands-off and tighten control later.

Key Capabilities

1. Plain-language briefing from ChatGPT. Through MCP you can brief the agent, send follow-ups, answer its questions, attach files and check tasks. MCP access is included on every plan. MCP usage draws on the same shared credit pool as the web app. There are no separate credits or per-interface fees.

2. Structured outputs, not flat renders. Every video comes back as a set of editable elements. Point at one element, describe the change, and only that element changes. Live controls such as text fields, sliders and color pickers update the preview with no re-render. Previews cost no credits.

3. Real footage first. The agent edits the footage you upload. Generated assets are optional layers, and one video can mix both. If you want no AI-generated material at all, Poolday can work only from your own footage.

4. Brand consistency without re-explaining. A brand kit stores your palette, fonts, logo and motion style. One brand:name mention applies it to any request. Kits can be built from a website URL, brand guidelines or Figma files. Skills and memory carry corrections and approved styles across conversations.

5. Inputs you already have. Direct uploads reach 1 GB per file in the web app, and 500 MB per file through MCP. Timelines from Final Cut Pro, Premiere Pro and DaVinci Resolve come in as XML, FCPXML, OTIO or EDL. Figma files, GitHub repositories and website URLs are accepted too. The integrations page lists the wider connector catalog.

6. Outputs in every format. MP4 at 1080p with optional 4K upscale, in 16:9, 9:16, 1:1 and 4:5 plus custom sizes. One prompt can return every aspect ratio, cutdown and variation. Reframing follows the action, so a 16:9 master becomes a usable vertical cut without a second edit session.

Proof & Evidence

Poolday publishes a public customer list. It includes Unity, Stillfront, WeWard, Recurly and Adikteev, among others. The published outcome quote comes from Mary J Kim, Director of Marketing at Stillfront: "Poolday has cut our production time in half and we're now testing more high-quality creative at scale. The quality of the output is impressive: even non-artists can create polished, production-ready assets with just a few prompts."

Poolday makes its own videos with Poolday, including its launch video. That is a working demonstration of the brief-to-finished-video loop. For a broader view of the category, the explainer on video editing agents covers how agents differ from generators and timeline tools.

Buyer Considerations

  • Run time. A video takes approximately 35 minutes. Larger jobs can take up to an hour, since the agent optimizes for quality, not speed. Starting from ChatGPT does not make it faster.
  • File limits through MCP. Attachments are capped at 500 MB per file, half the web app's 1 GB limit. Compress very large files before attaching them in chat.
  • Build mode default. Jobs started through MCP run end to end. If you expect questions before work begins, switch modes explicitly.
  • No public self-serve setup page yet. Connecting the MCP server currently happens with Poolday's help. Plan on the 15 minute onboarding call that every plan includes. Plan and onboarding questions are covered on the FAQs page.
  • Pricing model. Poolday sells a software subscription paid in credits, not seats. Plans and credit amounts are listed on the pricing page. There is no free trial.
  • Security. Poolday has started the SOC 2 process and has done penetration tests. It is not certified yet. An NDA is free and standard.

Frequently Asked Questions

Can ChatGPT really control the whole editing job, or just send prompts?

It controls the full loop. You brief the agent, answer its questions mid-run, attach input files, send follow-up edits and check task status, all from the chat. The agent plans, edits and self-checks the video on its side. Then it reports back.

Do MCP sessions use separate credits?

No. MCP usage draws on the same shared credit pool as the web app, on every plan. There are no per-interface fees. Work pauses when credits run out.

What if the first version is not right?

You do not regenerate the whole video. Describe the change in plain English, and only the targeted element changes. Live controls update the preview in real time at no credit cost.

Can we automate recurring edits instead of briefing each one?

Yes. Any prompt can run on a schedule or when a connected tool fires. Webhook automations can call a tool on an MCP server you host when the agent finishes. The API guide documents that mechanism, which is separate from MCP setup.

Conclusion

A video tool your team can direct from ChatGPT removes the second interface entirely. The brief, the follow-ups and the review all stay in the chat you already use. Poolday is built for that workflow, with the same agent, the same credits and the same element-level editing from either the web app or MCP. The practical next step is to pick one small, real job and run it through ChatGPT end to end. The agent guide shows how a brief becomes a finished video.

Related Articles