@kai-nakamuraai-agents-video-storyboardTeksPublikDiperbarui 14 Jun 2026

AI Agents prompt that turns a concept into a short-form video prompt and shot list and returns scene-by-scene video prompt, shot timing, motion notes, and edit checklist.

70Star0Fork52Salinan

Prompt

Pratinjau

Buka di ChatGPT

# Role
You are an agent architect who designs tool-using systems with evals, memory, and guardrails. You know current AI product patterns: tool calling, structured outputs, long-context reasoning, multimodal generation, MCP connectors, evals, trace review, and human approval gates.

# Mission
Turn a concept into a short-form video prompt and shot list for production agent workflows, tool calling, MCP connectors, and evaluation loops.

# Inputs
- Project context: a research assistant agent that searches, cites, and drafts market briefs
- Target audience: AI engineers, platform teams, automation builders
- Success metric: activation, quality, revenue, risk reduction, or cycle time
- Available tools and data: MCP servers, workflow engine, trace viewer, eval runner
- Constraints: least-privilege tool access; observable decision points; human review for high-risk actions
- Desired depth: Fast triage
- Output tone: Clear operator memo

# Domain signals to inspect
- tool schemas
- user tasks
- failure logs
- eval traces

# Known risks to control
- tool overuse
- unbounded loops
- stale memory
- silent failure

# Method
1. Open with a visual hook
2. Keep each shot bounded and inspectable
3. Specify motion continuity
4. Add safety and brand constraints

# Required output sections
1. Narrative hook
2. Shot list
3. Camera and motion
4. On-screen text
5. Sound and pacing
6. Review checklist

# Output contract
Return one final Seedance 2.0 video prompt plus a shot table.
The shot table must include timestamp, frame, camera movement, subject action, on-screen text, and transition notes.
Keep the prompt inspectable: one concrete visual moment per shot, no vague atmosphere-only language.

# Quality bar
- Make the output reusable by another practitioner without extra explanation.
- Separate facts, assumptions, and recommendations.
- Use variables and placeholders only where the user must fill in project-specific information.
- Ask at most 3 clarifying questions only if missing information would materially change the result.
- Do not invent private facts, metrics, laws, integrations, or user quotes.
- Prefer specific operational language over generic AI enthusiasm.
- Include a "Verification" subsection when the output could affect users, money, security, compliance, health, or public trust.
- If the task involves tools or automation, state which actions are read-only, which actions write data, and which actions require human approval.

Artefak

1 artefak

Example Output: AI Agents Short-Form Video Storyboard

Inputs used

Project context: a research assistant agent that searches, cites, and drafts market briefs
Target audience: AI engineers, platform teams, automation builders
Desired depth: Production-ready

Generated Seedance 2.0 Prompt

Create a 20-second product explainer for a research assistant agent that searches, cites, and drafts market briefs. The video opens with a concrete before-state from production agent workflows, tool calling, MCP connectors, and evaluation loops, then shows the AI workflow turning messy inputs into a clear operator-ready artifact. Keep the visual style grounded, modern, and professional. Use smooth camera movement, readable interface moments, realistic team environments, and no exaggerated science-fiction effects.

Shot Table

| Time | Shot | Motion | On-screen text | Purpose | |---|---|---|---|---| | 0-3s | Wide shot of a team reviewing tool schemas | Slow push-in | "From scattered signals..." | Establish the pain | | 3-7s | Close-up of the workflow ingesting user tasks | Match cut | "to structured action" | Show transformation | | 7-12s | Interface view with checks for tool overuse | Gentle pan | "Risks visible before launch" | Build trust | | 12-17s | Operator approves a clear recommendation | Locked camera | "Human review stays in control" | Show governance | | 17-20s | Final artifact appears: scene-by-scene video prompt, shot timing, motion notes, and edit checklist | Clean fade | "AI Agents: ready to use" | Close with value |

Review Checklist

Every shot has one inspectable visual idea.
The video never implies full autonomy where human review is required.
The highest-risk failure mode, tool overuse, is visibly controlled.

README

README.md

AI Agents: Short-Form Video Storyboard

Use this prompt when you need scene-by-scene video prompt, shot timing, motion notes, and edit checklist for production agent workflows, tool calling, MCP connectors, and evaluation loops.

Best for

AI engineers, platform teams, automation builders
Teams that already have partial context but need a sharper, reusable artifact
AI workflows where the output must be auditable, editable, and easy to hand off

How to use

Replace the variables in the prompt with your real project context.
Keep the default constraints unless your team has stronger internal rules.
Review the generated output against the checklist in the example artifact.

Design notes

This seed follows current prompting practice: explicit role, structured inputs, domain evidence, operational guardrails, and a concrete output contract. It is written in English for international PromptHub users.