@kai-nakamuraai-agents-image-campaign-brief单文本公开更新于 2026年6月14日

AI Agents prompt that creates a production-quality visual prompt for campaign assets and returns image-generation prompt with composition, style, text, constraints, and QA notes.

53收藏0Fork204复制

Prompt

预览

在 ChatGPT 打开

# 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
Create a production-quality visual prompt for campaign assets 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. Specify subject, setting, lighting, and camera
2. Constrain brand colors and typography
3. Call out exact rendered text
4. Add negative constraints and inspection notes

# Required output sections
1. Creative objective
2. Composition
3. Style system
4. Text and layout
5. Asset variants
6. QA checklist

# Output contract
Return one final GPT Image 2 prompt plus a QA checklist.
The prompt must include: subject, environment, composition, lighting, lens/camera, material details, typography, exact visible text, aspect ratio, and negative constraints.
It must be tailored to production agent workflows, tool calling, MCP connectors, and evaluation loops.

# 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.

产物

1 个产物

Example Output: AI Agents Image Campaign Brief

Inputs used

Project context: a research assistant agent that searches, cites, and drafts market briefs
Target audience: AI engineers, platform teams, automation builders
Success metric: quality and conversion lift
Desired depth: Production-ready
Output tone: Technical spec

Generated GPT Image 2 Prompt

Create a production-ready campaign visual for a research assistant agent that searches, cites, and drafts market briefs. The image should feel credible for production agent workflows, tool calling, MCP connectors, and evaluation loops, not like a generic stock illustration. Show the main subject in a clean editorial composition with a clear foreground, midground, and background. Use precise lighting, realistic materials, and inspectable details that communicate tool schemas and user tasks. Include one concise line of visible text: "AI Agents workflow, ready for review". Use modern international SaaS art direction, refined typography, high contrast, accessible color choices, and a polished product-launch finish. Avoid fake logos, unreadable microtext, misleading claims, cluttered dashboards, distorted hands, and vague futuristic haze.

Production QA Checklist

The visible text is readable and spelled exactly as specified.
The visual clearly supports production agent workflows, tool calling, MCP connectors, and evaluation loops.
The output avoids the highest-risk failure mode: tool overuse.
A designer can adapt the asset into a landing page, social post, or deck cover without re-prompting from scratch.

Reuse note

Replace the visible text, product category, brand palette, and aspect ratio before using this in a live campaign.

README

README.md

AI Agents: Image Campaign Brief

Use this prompt when you need image-generation prompt with composition, style, text, constraints, and QA notes 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.