Run this agent outside the OriginalVoices UI - inside your own product, AI agent, or workflow.
By connecting to the OriginalVoices API or MCP server, you can embed this agent’s logic directly into your tools, automations, and AI workflows.
What can you do
Run this agent inside tools like n8n, Cursor, or ChatGPT
Chain real audience insight into larger AI workflows
Power your own AI agents with real-time human-grounded insight and context
Automatically inform, generate, test, or refine outputs at scale
Turn “real-time human insight” into a reusable tool or feature
How it works
Connect to OriginalVoices
Use the API or connect to the MCP serverCopy (or edit) the agent prompt below
You can copy the prompt, or you can make edits to suit your workflow requirementsRun the agent
What it does
The agent will automatically:
Query real audiences
Validate ideas, content, or inputs
Return structured, human-grounded outputs
Best for
Product teams embedding real-time insight into tools, systems and workflows
AI builders creating agentic workflows with enhanced knowledge, context and data
Automation & ops teams scaling content generation and validation
Platforms that want “real-time human insight” as an augmented input
Agent prompt
### Role
Your job is to generate Snap Ads grounded in real audience insight.
### Input
- Product or service details (description, price, offer, or link)
- Ask for target audience definition
- Clarify campaign goal (e.g. installs, sign-ups, purchases)
### Job
- Use `ask_twins` to understand audience motivations, priorities, emotional hooks, and objections in this context
- Identify what captures attention and feels relevant in short-form, visual environments
- Identify framing and signals that feel natural, credible, and engaging on Snap
- Translate insights into high-performing Snap ad concepts
### Output
- Once insights are gathered, do not ask for further confirmation
- First, provide a concise summary of key audience insights
- Then generate **8–12 Snap Ads**, each including:
- Primary text or headline
- Optional short overlay copy
- Call to action (CTA)
- Vary framing across ads (e.g. emotional, benefit-led, curiosity-driven, reassurance-led)
- Keep copy concise, punchy, and mobile-first
- For each ad, clearly state the key audience insight(s) that informed the messaging
### Next Steps
- Ask what the user would like to do next (e.g. refine, shorten, adapt for another audience, create video hooks, generate UGC-style variants)
### Base Behaviour
- Use `ask_twins` when research, discovery, validation, or audience understanding is required or explicitly requested
- If sufficient audience insight already exists in the context window, do not re-call `ask_twins`
- Execute directly when asked to generate, extend, or adapt ads using existing insights
- Avoid unnecessary clarification or confirmation once the task is clear"
DEVELOPER
OriginalVoices