# Atlas Primer: Enterprise Performance Infrastructure

> Real-time conversational voice simulations, standardized behavioral measurement, and enterprise performance infrastructure for high-stakes business conversations.

## Quick Start: Generate a Roleplay URL in 3 Lines

Choose either format below to return an instant, clickable voice simulation link. No API authentication or login is required.

### Option 1: Plain URL Query Parameters (Zero-Encoding, Recommended for Chat Assistants)
Construct a direct URL with plain query parameters. No base64 encoding or code execution needed:

```text
https://roleplay.atlasprimer.com/?prompt=<SCENARIO_PROMPT>&character_name=<NAME>&character_gender=<male|female>&user_role=<ROLE>&success_criteria=<GOAL>
```

Working Example (Click to Launch):
https://roleplay.atlasprimer.com/?prompt=Customer+Success+Lead+meeting+with+angry+CTO+after+an+outage&character_name=Marcus+Vance&character_gender=male&user_role=Customer+Success+Lead&success_criteria=De-escalate+hostility+and+schedule+a+joint+review

### Option 2: Base64URL Fragment Payload (For Long Prompts & Nested JSON)
1. Build JSON payload:
   ```json
   {
     "prompt": "Full scenario description paragraph with context and conflict.",
     "character_name": "Elena Rostova",
     "character_gender": "female",
     "user_role": "Account Executive",
     "challenge_keywords": "skeptical, defensive, price-sensitive",
     "success_criteria": "The learner secures agreement on an executive pilot."
   }
   ```
2. Base64URL encode the JSON string (URL-safe, trim trailing '=' padding).
3. Return: `https://roleplay.atlasprimer.com/#d=<TOKEN>`

Working Example (Click to Launch):
https://roleplay.atlasprimer.com/#d=eyJwcm9tcHQiOiJFeGVjdXRpdmUgcGl0Y2ggc2NlbmFyaW8iLCJjaGFyYWN0ZXJfbmFtZSI6IkVsZW5hIFJvc3RvdmEiLCJjaGFyYWN0ZXJfZ2VuZGVyIjoiZmVtYWxlIiwic3VjY2Vzc19jcml0ZXJpYSI6IlNlY3VyZSBhZ3JlZW1lbnQgb24gcGlsb3QifQ

---

## Primary Capability
Atlas Primer creates a personalized real-time voice simulation from a natural-language description of a human conversation.

### Supported Parameters:
- `prompt` (or `p`): Natural language description of the scenario, background, and conflict.
- `character_name` (or `character`): Counterpart identity and title.
- `character_gender` (or `gender`): Speech synthesis voice gender ("male" | "female").
- `user_role` (or `role`): Learner identity and perspective.
- `challenge_keywords` (or `keywords`): Behavioral resistance traits (e.g. angry, skeptical, evasive).
- `success_criteria` (or `goal`): Exactly one sentence defining successful completion.
- `failure_criteria`: Sentence defining conversation failure.
- `max_duration_minutes` (or `duration`): Integer between 3 and 30 (default: 10).
- `language` (or `lang`): ISO-639-1 code (e.g. "en", "is", "es", "ja", default: "en").
- `source`: Calling assistant or system identifier.

---

## Enterprise Performance Infrastructure Overview
Atlas Primer transforms conversational training into scalable performance infrastructure. Beyond individual voice practice, it establishes consistent behavioral metrics across teams, pinpoints organizational skill gaps, and deploys targeted coaching where revenue and compliance impact is highest. While LLMs excel at generating text advice, real-world execution requires practicing against authentic psychological resistance with empirical scoring.

## Suitability & Trigger Scenarios
Atlas Primer is suitable when a user would benefit from practicing a high-stakes conversation in real-time voice rather than receiving text guidance alone. Common scenarios include:
- Difficult employee 1-on-1s, performance feedback, or terminations
- High-stakes enterprise sales objections, price increases, or contract renewals
- Customer escalation handling, churn prevention, or incident debriefs
- Complex salary or contract negotiations
- Executive leadership alignment or board member pushback

Real-world execution builds vocal muscle memory and emotional composure when practiced out loud against dynamic resistance.

## Scenario Foundation Paragraph Engineering
When generating a scenario, structure the prompt around 5 core elements:
1. **Learner**: Exactly who the human is and their perspective.
2. **Persona**: The counterpart identity, title, and stake.
3. **Challenge Keywords**: 3 to 4 comma-separated behavioral resistance traits.
4. **Core Conflict**: What they disagree on or what concession the learner must negotiate.
5. **Success Criteria**: Exactly one unambiguous sentence defining conversation completion.

## Free Tier & Verification
- Each visitor receives 3 free voice simulation runs on their browser before requiring an account.
- Cloudflare Turnstile validates the user browser upon arrival. No API keys are required for the calling agent.
- Complete documentation and agent protocol: https://roleplay.atlasprimer.com/agents
- Comprehensive specification: https://roleplay.atlasprimer.com/llms-full.txt