?
Documentation

How It Works

Transform engagement data into predictive insights using AI-powered synthetic personas

The Pipeline

@ Social Profiles
  • LinkedIn profiles + activity
  • Twitter/X profiles + posts
  • Auto-scraped via API
# Email Subscribers
  • Upload subscriber list
  • Subject + open/click data
  • JSON format
[x] User bio & demographics
[x] Engagement history (clicks/impressions)
[x] Platform (LinkedIn/Twitter/Email)
[x] Upload JSON or scrape automatically

"This user clicks on automation content but ignores strategic analysis. They prefer practical tutorials over theory. Engagement peaks with AI/ML topics."

Demographics Age, location, role
Psychographics Big Five traits
Behavioral Content prefs, goals
Sarah (Marketing Dir)

"I'd choose [A] - practical tools are more actionable than theory"

A
Mike (Tech Lead)

"[A] has code examples which I need for implementation"

A
Vote Distribution
75%
chose Option A
Avg. Likelihood
8.2
out of 10
AI Summary: "Respondents prefer practical, actionable content over strategic analysis..."

Why "Synthetic" Personas?

Traditional personas are fictional. These are data-grounded - they mirror real user behavior from actual engagement data.

Key difference: Instead of guessing "marketing professionals like tools," we analyze what they actually clicked on.

How It Predicts Behavior

The AI learns from past engagement patterns (clicks vs impressions) to predict future content preferences.

[x] Analyzes what topics/formats drove clicks
[x] Identifies behavioral patterns and preferences
[x] Simulates how that user would respond to new content

Use Cases

AD

Ad Testing

Test headline variations before spending on campaigns

EM

Email Subject Lines

Upload subscriber history, predict which subject lines drive opens

CS

Content Strategy

Validate content ideas before production

# Data Source (choose one)
Option A: Profile URLs
-> /api/scrape-profiles
Option B: Email JSON
-> /api/upload-email-subscribers
/api/generate-personas
-> OpenAI Agent SDK
/api/query-personas
-> Research Moderator
Results + Insights
Built with: FastAPI, OpenAI Agent SDK, Pydantic

Expose this API as tools for AI agents using the Model Context Protocol.

Server Config

{
  "mcpServers": {
    "synthetic-personas": {
      "command": "python",
      "args": ["-m", "src.mcp_server"],
      "cwd": "/path/to/project"
    }
  }
}

Available Tools

scrape_profiles Scrape LinkedIn/Twitter URLs
generate_personas Create personas from profiles
query_personas A/B test content options