poolday.ai

Command Palette

Search for a command to run...

AI Video Automation That Turns Wins Into Case Studies

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.

AI Video Automation That Turns Wins Into Case Studies

Poolday is an AI agent for media production that turns a customer win into a finished case study video without anyone opening an editor. You brief it once, save that brief as a command, and let an automation run it whenever a win lands. The result is a short, on-brand video built from your real footage.

Introduction

Every marketing team says the same thing after a good quarter: we should have turned that into a video. Then the story dies in a Slack thread because nobody has time to storyboard, edit and brand a case study video.

An automation closes that gap. The trigger is an event you already have, such as a closed deal in your CRM, a new row in a spreadsheet or a webhook from your own tooling. The output is a repeatable format: a 60 to 90 second recap with the customer's name, the problem, the result and your product on screen. Poolday runs that whole job, from brief to finished MP4, and checks its own work before you see it. This piece explains how the wiring works and what to check before you commit a plan.

Key Takeaways

  • Poolday is an AI agent for media production, not a timeline editor. You brief it like a freelance editor and it plans, edits real footage, assembles the video and reviews itself before delivery.
  • Automations let any prompt run on a schedule or when a connected tool fires, so a case study video can be produced the moment a win is recorded.
  • Webhook automations accept events from systems you host, which covers internal tools that have no prebuilt connector.
  • Brand kits and commands make the format repeatable: one saved brief, one brand:yourname mention, consistent output every run.
  • A human still approves the story. The agent removes the editing work, not the judgment about what is safe to publish.

Why This Solution Fits

A case study video is a recurring format with variable inputs. That is exactly the shape of work an agent handles well: the structure stays the same, the footage, names and numbers change each time.

With Poolday, you set this up in three layers.

  1. The brief. You write the case study format once: length, sections, tone, what must appear on screen, what must never appear. Save it as a command with /name so any teammate can invoke it.
  2. The brand. A brand kit holds your palette, fonts, logo, motion style and reusable building blocks. Build it from your website, brand guidelines or Figma files, then apply it in any request with one brand:name mention. Several customers or series can each have their own kit in one account.
  3. The trigger. An automation runs the command on a schedule or when a connected tool fires, for example a new Drive file or a GitHub push. Poolday lists more than 200 connectors, and any service that supports MCP can be added in one click; any REST API can also be added with a key. See the integrations catalog for what is available.

Because the agent edits real footage, your case studies stay authentic. A team can keep AI generation out entirely and still get a finished, on-brand video. Generated elements are optional when you want them.

Key Capabilities

Event-triggered production. Any prompt can run on a schedule or on a trigger from a connected tool. When the win lands, the agent starts.

Webhook automations for internal systems. If your win lives in a tool with no connector, your system can POST the event to a webhook automation. Published limits: 60 runs per hour per automation (editable), 300 per organization per hour, up to 10 files at 50 MB each and 200 MB total, and your tool must respond within 2 minutes. When the agent finishes, it calls a tool on an MCP server you host, so the finished video can land back in your own pipeline.

Editing real footage. Uploads up to 1 GB per file in the web app cover raw interviews, screen recordings and event footage. Timelines from Final Cut Pro, Premiere Pro and DaVinci Resolve come in as XML, FCPXML, OTIO or EDL. The agent plans before it edits, which matters when the story has to land.

Point and select revisions. Every output is a structured set of elements, not a flat render. Point at the lower third and change only that. Live controls update the preview in real time at no credit cost, so review rounds are cheap.

Distribution. The agent can post and auto-post finished videos to social and ad accounts through a publishing connector, MCP, or an automation that publishes on completion.

Where you run it. The web app is the main surface. MCP (Model Context Protocol) access is on every plan, so you can brief the agent and answer its questions from Claude, ChatGPT or your own tools.

Proof & Evidence

Poolday's public customer list includes B2B software companies such as Upflow, Recurly and Yuma AI, gaming companies such as Unity, Stillfront and Gogii Games, and agencies and studios such as Wonder Studios and Dialed Studios.

The published outcomes are quotes, not case study metrics. Mary J Kim, Director of Marketing at Stillfront, said: "Poolday has cut our production time in half and we're now testing more high-quality creative at scale." Alex Dispoto, CEO of ChewOnThis, said the agent "streamlines the boring parts of editing while keeping me in complete control of the visual identity and quality."

On timing, Poolday's own figure is approximately 35 minutes for a video (internal, November 2026). Larger jobs can take longer because the agent optimizes for quality, not speed.

One honest limit: the agent cannot cut a live feed in real time, and captions burned into footage cannot be cleanly removed or translated. Plan your inputs accordingly.

Buyer Considerations

Plan and access. Poolday has three plans: Pro, Business and Enterprise, with the same agent and unlimited users on every plan. MCP access is on every plan; API access starts at Business. Business also adds a starter automation built at onboarding and video workflows for recurring formats, which is exactly the use case described here. Current plan details are on the pricing page.

Credits, not seats. The subscription is paid in credits, and the monthly amount becomes one shared credit pool for the agent and every model. Work pauses when credits run out, so size the pool against your video volume.

No free trial. There is no free trial. Every plan starts with a 15 minute onboarding call and a shared Slack channel, and Poolday monitors and audits your first ten prompts.

Security posture. Poolday has started the SOC 2 process and has done penetration tests. It is not certified yet. An NDA is free and standard. If your case studies contain customer data, note that the agent can also replace sensitive data in screenshots and screen recordings with dummy data.

Human review stays in the loop. An automation can produce a draft the moment a win lands, but publishing a customer's name and results is a judgment call. Build a review step into the flow, and get the customer's approval before anything goes public.

Frequently Asked Questions

Can an AI video tool really produce a case study video from a trigger event?

Yes, with the right wiring. The trigger fires an automation, the automation runs a saved brief, and the agent edits your footage into a finished video. The brief and brand kit carry the consistency; the event carries the content.

What if our win data sits in an internal tool?

Use a webhook automation. Your system POSTs the event, the agent runs, and it calls a tool on an MCP server you host when it finishes. Any REST API can also be added with a key.

Do we need video editing skills to run this?

No. You brief the agent in plain language, and the learning curve is short: the first video takes roughly seven prompts, the second four, the third one or two. Revisions happen through point and select or live controls, not a timeline.

How do we keep every case study on brand?

Save a brand kit and a command. The kit holds palette, fonts, logo, motion style and reusable blocks, and the command holds the format. Each run applies both automatically, so the only variable is the story itself.

Conclusion

A customer win is perishable material. The longer it sits in a spreadsheet, the less it helps your pipeline. Poolday turns the moment into a repeatable production line: a saved brief, a brand kit, a trigger, and a finished video about 35 minutes later. Start by reading the agent guide to see how jobs, brand kits and commands work, then check the FAQs for plan and onboarding questions before you pick a plan.

Related Articles