> ## Documentation Index
> Fetch the complete documentation index at: https://docs.eigi.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Scaling & Performance

> Handle high volumes with enterprise-grade reliability

## Overview

eigi.ai is built for enterprise scale. Whether you're handling hundreds or thousands of concurrent calls, the platform delivers consistent performance and reliability.

***

## Capacity & Scale

### Handle Any Volume

<CardGroup cols={2}>
  <Card title="Concurrent Calls" icon="phone-volume">
    Handle thousands of simultaneous conversations
  </Card>

  <Card title="Auto-Scaling" icon="arrows-up-down">
    Capacity automatically adjusts to demand
  </Card>

  <Card title="Global Infrastructure" icon="globe">
    Low latency from anywhere in the world
  </Card>

  <Card title="No Code Changes" icon="code">
    Scale without modifying your setup
  </Card>
</CardGroup>

***

## Concurrency Management

### How Concurrency Works

| Metric               | Description                                 |
| -------------------- | ------------------------------------------- |
| **Concurrent Calls** | Number of active calls at the same time     |
| **Peak Capacity**    | Maximum concurrent calls your plan supports |
| **Queue Management** | How overflow calls are handled              |
| **Burst Handling**   | Temporary capacity for traffic spikes       |

### Concurrency Tiers

| Tier           | Concurrent Calls | Use Case                  |
| -------------- | ---------------- | ------------------------- |
| **Starter**    | Up to 10         | Small businesses, testing |
| **Growth**     | Up to 50         | Growing operations        |
| **Business**   | Up to 200        | Medium enterprises        |
| **Enterprise** | Unlimited        | Large-scale deployments   |

***

## Queue Management

### When Capacity is Full

Configure how to handle calls when at capacity:

<CardGroup cols={2}>
  <Card title="Hold & Wait" icon="hourglass">
    Caller waits with music/message until agent available
  </Card>

  <Card title="Callback Queue" icon="phone-arrow-down-left">
    Collect number and call back automatically
  </Card>

  <Card title="Voicemail" icon="voicemail">
    Record message for later follow-up
  </Card>

  <Card title="Overflow Routing" icon="route">
    Route to backup agent or human team
  </Card>
</CardGroup>

### Queue Settings

| Setting                    | Description                              |
| -------------------------- | ---------------------------------------- |
| **Max Wait Time**          | How long callers wait before alternative |
| **Position Announcements** | Tell callers their queue position        |
| **Estimated Wait**         | Provide estimated wait time              |
| **Music/Message**          | What plays while waiting                 |

***

## Performance Optimization

### Real-Time Processing

Voice AI requires fast processing. eigi.ai is optimized for:

| Component              | Optimization                                |
| ---------------------- | ------------------------------------------- |
| **Speech Recognition** | Stream processing for instant transcription |
| **LLM Processing**     | Optimized inference with low latency        |
| **Voice Synthesis**    | Word-by-word streaming for natural flow     |
| **Tool Execution**     | Parallel processing when possible           |

### Latency Targets

| Metric             | Target                             |
| ------------------ | ---------------------------------- |
| **First Response** | \< 800ms after user stops speaking |
| **Turn-Taking**    | Natural conversation pace          |
| **Tool Calls**     | \< 200ms overhead                  |
| **Audio Quality**  | HD voice with \< 50ms jitter       |

***

## Reliability

### Uptime & Availability

<CardGroup cols={3}>
  <Card title="99.9% Uptime" icon="check-circle">
    Enterprise SLA available
  </Card>

  <Card title="Redundancy" icon="clone">
    No single point of failure
  </Card>

  <Card title="Auto Recovery" icon="rotate">
    Automatic failover
  </Card>
</CardGroup>

### What Happens During Outages

| Scenario                | Handling                       |
| ----------------------- | ------------------------------ |
| **Provider Outage**     | Automatic failover to backup   |
| **Partial Degradation** | Non-critical features disabled |
| **Maintenance**         | Zero-downtime deployments      |
| **Network Issues**      | Automatic reconnection         |

***

## Provider Redundancy

### Multi-Provider Fallback

Configure backups for critical services:

<AccordionGroup>
  <Accordion title="LLM Fallback" icon="brain">
    If primary LLM is slow or unavailable: - Primary: GPT-4o - Fallback 1:
    Claude 3.5 Sonnet - Fallback 2: Gemini 2.0 Flash
  </Accordion>

  <Accordion title="TTS Fallback" icon="volume-high">
    If voice synthesis fails: - Primary: ElevenLabs - Fallback: Cartesia -
    Emergency: OpenAI TTS
  </Accordion>

  <Accordion title="STT Fallback" icon="microphone">
    If speech recognition fails: - Primary: Deepgram - Fallback: Azure Speech
  </Accordion>
</AccordionGroup>

***

## Load Balancing

### Traffic Distribution

Calls are intelligently distributed:

| Strategy              | Description                  |
| --------------------- | ---------------------------- |
| **Geographic**        | Route to nearest server      |
| **Load-Based**        | Route to least busy server   |
| **Provider Health**   | Avoid degraded providers     |
| **Cost Optimization** | Balance performance and cost |

***

## Monitoring

### Real-Time Dashboards

Monitor your system health:

<CardGroup cols={2}>
  <Card title="Active Calls" icon="phone">
    Current concurrent calls and capacity
  </Card>

  <Card title="Queue Status" icon="list">
    Callers waiting and wait times
  </Card>

  <Card title="Provider Status" icon="server">
    Health of all connected services
  </Card>

  <Card title="Error Rates" icon="triangle-exclamation">
    Track and alert on issues
  </Card>
</CardGroup>

### Key Metrics

| Metric            | Description              | Alert Threshold |
| ----------------- | ------------------------ | --------------- |
| **Concurrency %** | Current vs. max capacity | > 80%           |
| **Avg. Latency**  | Response time            | > 1000ms        |
| **Error Rate**    | Failed calls             | > 1%            |
| **Queue Length**  | Callers waiting          | > 10            |

***

## Analytics at Scale

### Handling Large Data Volumes

<CardGroup cols={2}>
  <Card title="Real-Time Analytics" icon="gauge-high">
    Live metrics even during high volume
  </Card>

  <Card title="Historical Data" icon="clock-rotate-left">
    Access all historical call data
  </Card>

  <Card title="Data Retention" icon="database">
    Configurable retention policies
  </Card>

  <Card title="Export & Backup" icon="download">
    Export data for external analysis
  </Card>
</CardGroup>

***

## Multi-Agent Scaling

### Managing Multiple Agents

Scale across many agents:

| Feature                  | Description                               |
| ------------------------ | ----------------------------------------- |
| **Shared Resources**     | Pool capacity across agents               |
| **Agent Prioritization** | Allocate more capacity to critical agents |
| **Load Spreading**       | Distribute traffic across agents          |
| **Independent Scaling**  | Scale specific agents as needed           |

***

## Enterprise Features

### Advanced Capabilities

<CardGroup cols={2}>
  <Card title="Dedicated Infrastructure" icon="server">
    Isolated resources for your organization
  </Card>

  <Card title="Custom SLAs" icon="file-contract">
    Tailored uptime and support agreements
  </Card>

  <Card title="Priority Support" icon="headset">
    Direct access to engineering team
  </Card>

  <Card title="Compliance" icon="shield-check">
    HIPAA, SOC2, GDPR compliance options
  </Card>
</CardGroup>

***

## Cost Optimization

### Scale Efficiently

<AccordionGroup>
  <Accordion title="Right-Size Your Plan" icon="sliders">
    Choose concurrency limits that match your actual usage patterns.
  </Accordion>

  <Accordion title="Optimize Call Duration" icon="clock">
    Well-designed prompts lead to shorter, more efficient calls.
  </Accordion>

  <Accordion title="Use Appropriate Providers" icon="gauge">
    Match provider capabilities to task complexity.
  </Accordion>

  <Accordion title="Monitor and Adjust" icon="chart-line">
    Regularly review usage patterns and optimize.
  </Accordion>
</AccordionGroup>

***

## Traffic Patterns

### Handling Variable Load

Configure for your traffic patterns:

| Pattern             | Strategy                       |
| ------------------- | ------------------------------ |
| **Steady**          | Consistent capacity allocation |
| **Peak Hours**      | Scale up during busy times     |
| **Campaign Bursts** | Reserve capacity for campaigns |
| **Seasonal**        | Adjust for seasonal variations |

***

## Testing at Scale

### Load Testing

Before launching high-volume campaigns:

<Steps>
  <Step title="Baseline Test">Measure performance at current volume</Step>
  <Step title="Gradual Increase">Slowly increase load to find limits</Step>
  <Step title="Stress Test">Test beyond expected maximum</Step>
  <Step title="Failure Testing">Verify graceful degradation</Step>
</Steps>

***

## Best Practices

<Tip>**Plan for Peak**: Size your capacity for peak demand, not average.</Tip>

<Tip>**Configure Fallbacks**: Always have backup providers configured.</Tip>

<Tip>
  **Monitor Proactively**: Set up alerts before hitting capacity limits.
</Tip>

<Warning>
  Test your scaling configuration before running large campaigns. Start small
  and scale up gradually.
</Warning>

***

## Troubleshooting

<AccordionGroup>
  <Accordion title="Calls being queued unexpectedly">
    * Check current concurrency vs. limit - Review call duration (longer calls
      use capacity longer) - Consider upgrading your plan - Optimize agent prompts
      for efficiency
  </Accordion>

  <Accordion title="High latency during peak times">
    * Verify you're not hitting capacity limits - Check provider status for
      degradation - Review if specific tools are causing delays - Consider
      geographic distribution
  </Accordion>

  <Accordion title="Inconsistent call quality">
    * Check network connectivity - Verify provider health status - Review audio
      settings - Test with different providers
  </Accordion>
</AccordionGroup>