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

# Orchestration Pipeline

> How Theo processes every request through a 5-stage pipeline.

Theo is not a model proxy. Every API call passes through a multi-stage pipeline that handles classification, skill injection, model selection, tool execution, and response formatting.

## The Five Stages

```
Request → Classify → Load Skills → Route Model → Agent Loop → Response
```

### 1. Intent Classification

Determines the task type (`fast`, `think`, `code`, `image`, `research`, `roast`, etc.) using a multi-tier classification system. Skipped if you set `mode` explicitly.

### 2. Skill Loading

Loads domain expertise from two sources: the user's **installed skills** (persistent) and **per-request skills** (ephemeral `skills[]` array). Each skill injects system prompt extensions and tool definitions.

### 3. Engine Routing

Selects the optimal Theo engine based on the resolved mode. If the primary engine is unavailable, failover routes to the backup automatically.

### 4. Agent Loop

For requests with tools, Theo enters an iterative loop: the engine reasons, calls a tool, observes the result, and continues until done. For simple prompts with no tools, this collapses to a single call.

### 5. Response

The final output is formatted with content, engine metadata, tool execution log, artifacts, follow-up suggestions, and usage data. The request is billed, cached, and audited.

## Performance

| Scenario                  | Typical Latency |
| ------------------------- | --------------- |
| Fast mode, no tools       | \~500ms         |
| Think/code mode, no tools | 1-3s            |
| Agentic with tool calls   | 2-5s            |
| Image generation          | 5-15s           |
| Research (async)          | 30-120s         |

## Pipeline Diagram

See [How Theo Thinks](/introduction/how-theo-thinks) for the complete stage-by-stage breakdown with examples.