# Amazon Augmented AI

**Canonical:** https://apis.io/providers/amazon-augmented-ai/  
**APIs profiled:** 1

Amazon Augmented AI (Amazon A2I) is a machine learning service that makes it easy to build the workflows required for human review of ML predictions. Amazon A2I brings human review to all developers, removing the undifferentiated heavy lifting associated with building human review systems or managing large numbers of human reviewers.

## Kin Score — 30.0 / 100 (thin)

Scored 2026-08-24 under rubric 0.13.0. Trend: flat (-0.5 from 30.5).

| Facet | Score |
|---|---|
| Discoverability | 66.7 |
| Contract Quality | 69.4 |
| Governance | 30.3 |
| Contract Governance | 30.3 |
| Operational Transparency | 0.0 |
| Developer Ergonomics | 11.9 |
| Commercial Clarity | 0.0 |
| Access Clarity | 0.0 |

## Agent readiness — 22.3 (agent-aware)

| Dimension | Value |
|---|---|
| Spec Presence | yes |
| Agentic Access | derived |
| Reversibility Documented | no |
| MCP Server | no |
| Auth Clarity | bearer |
| Idempotency | no |
| Error Semantics | no |
| OpenAPI Examples | verified |
| Rate Limit Signal | no |
| Event Surface Described | no |
| Agent Skills | no |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |
| Delegated Identity | no |
| Protected Resource Metadata | no |
| Dynamic Client Registration | no |
| Agentic Commerce | no |

## Access

Self-serve signup — onboarding: self-serve, pricing: unknown, trial: no (confidence: medium).

## APIs (1)

- **Amazon Augmented AI Human Loops API** — Operations for creating and managing human review loops

## MCP servers (1)

- **Amazon Augmented AI MCP Server**

## Agentic access (1)

- **Amazon Augmented Ai Agentic Access** — 5 operations · 3 acting · 1 human-in-the-loop

## Security (3)

- **Amazon Augmented Ai Authentication** — apiKey · 1 scheme
- **Amazon Augmented Ai Domain Security** — TLSv1.3 · HSTS · DMARC
- **Amazon Augmented Ai Vulnerability Disclosure** — Hackerone · security.txt · contact published

## Use cases (6)

- **Review low-confidence document text extraction results**
- **Validate image classification predictions before deployment**
- **Moderate user-generated content with human reviewers**
- **Ensure accuracy of medical record processing**
- **Verify identity document data extraction results**
- **Build training datasets with human-verified labels**

## Tags

Amazon Augmented AI, Human-in-the-Loop, Machine-Learning, AI Review

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/providers/amazon-augmented-ai/). Scores are computed from the provider's own public artifacts under a published rubric.