> ## Documentation Index
> Fetch the complete documentation index at: https://secndai.manicule.dev/llms.txt
> Use this file to discover all available pages before exploring further.
> For every page in one file, fetch https://secndai.manicule.dev/llms-full.txt (large).
> To search and read these docs as tools, connect the MCP server at https://secndai.manicule.dev/api/mcp.
> Every agent surface: https://secndai.manicule.dev/.well-known/llms-manifest.json

# Escalate to a human (/patterns/escalate-to-human)

<!-- agent-signals: reading_time_min: 1 · est_tokens: 301 · updated: 2026-11-12 -->
Related: [Confidence routing](/patterns/confidence-routing.md), [Companion true/false check](/patterns/companion-check.md), [Batching and concurrency](/patterns/batching.md)

> Make uncertainty an explicit operational path.

When the API returns `ask_human`, create a review item containing only the evidence the reviewer needs: the original situation, question, option descriptions, suggested answer, probability distribution, pinned model ID, and threshold.

Use your own request or case ID for deduplication. Do not use a new decision response ID as the sole deduplication key: a retry can produce another ID for the same business case.

## Review flow

1. Persist the pending case before acknowledging it to the caller.
2. Present the evidence and all options; label the model's answer as a suggestion.
3. Require a human decision before any irreversible action.
4. Record who approved the action and apply your normal authorization checks.
5. Expire stale reviews and provide a visible status to the user.

A queue with no reviewer is a blocked workflow. Set an ownership and response-time policy before enabling it. If inference fails entirely, use the same review path or return a temporary failure; never fabricate a confident answer.

Use human outcomes for workflow evaluation only under your data policy. Do not assume customer data is automatically training data.