Amazon Augmented AI Runtime

Name: Amazon Augmented AI Runtime API
Brand: Amazon Augmented AI Runtime
Availability: InStock

★ Only Publicly Available SpecAI/MLMl Inferencehmac5 EndpointsREST

For Agents

Send low-confidence ML predictions to human reviewers and retrieve the human-validated result, so agents can defer hard cases instead of guessing.

Quickstart

Get started with Amazon Augmented AI Runtime in minutes using your preferred integration method.

# Add to your MCP client config (Claude Desktop, Cursor, Windsurf)
{
  "jentic": {
    "url": "https://api.jentic.com/mcp",
    "auth": "oauth"
  }
}

# Then ask your agent:
"send a prediction for human review"

# → Jentic returns the GET /events tool with parameter schema, agent executes.

Capabilities

What an agent can do with Amazon Augmented AI Runtime API.

Start a human review task with StartHumanLoop attached to a flow definition and input data

Read the status and reviewer output of a human review task with DescribeHumanLoop

List human review tasks created against a given flow definition with ListHumanLoops

Stop an in-progress human review task with StopHumanLoop when the result is no longer needed

GET STARTED

Start building with Amazon Augmented AI Runtime API

Explore with Jentic

View OpenAPI Spec

Jentic publishes the only available OpenAPI specification for Amazon Augmented AI Runtime, keeping it validated and agent-ready.

Jentic publishes the only available OpenAPI specification for Amazon Augmented AI Runtime, keeping it validated and agent-ready. Amazon Augmented AI (A2I) is the human-in-the-loop layer for ML predictions — when a model's confidence falls below threshold, A2I routes the prediction to a configured workforce (private, vendor, or Amazon Mechanical Turk) for human review. The runtime API starts, monitors, stops, and deletes individual human review tasks (called HumanLoops) tied to a flow definition you create in the SageMaker console.

Use Cases

Patterns agents use Amazon Augmented AI Runtime API for, with concrete tasks.

★ Human-in-the-loop for low-confidence predictions

ML teams use A2I to defer borderline predictions to human reviewers instead of acting on them blindly. When a SageMaker endpoint returns a confidence score below threshold, the application calls StartHumanLoop with the input data and the FlowDefinitionArn that defines the reviewer UI and workforce; once a reviewer submits, DescribeHumanLoop returns the structured human-validated result.

Call StartHumanLoop with FlowDefinitionArn for the document-classification flow, HumanLoopName='doc-1234', and the document JSON as input, then poll DescribeHumanLoop until status is Completed.

Compliance and audit review of ML decisions

Regulated teams use A2I to ensure a percentage of automated decisions are reviewed by qualified humans for audit. By configuring the flow definition to sample a fixed proportion of predictions and route them to a private workforce, A2I produces a defensible record of human-validated outcomes that ListHumanLoops and DescribeHumanLoop can replay during audits.

Call ListHumanLoops with FlowDefinitionArn and a CreationTimeAfter filter to retrieve all sampled review tasks from the last quarter for audit export.

Document and image review for ML pipelines

Document- and image-processing teams use A2I to add human verification to OCR, object-detection, and form-extraction pipelines. The flow definition renders the document or image alongside the model's prediction in the reviewer UI; the reviewer corrects or confirms it; DescribeHumanLoop returns the corrected result for downstream pipeline steps.

Submit StartHumanLoop with the Textract output as InputContent and the document-extraction flow definition, then on Completed status feed reviewer-corrected fields back into the downstream pipeline.

Agent-driven human-fallback through Jentic

AI agents that need to defer hard cases use Jentic to call StartHumanLoop and DescribeHumanLoop without holding raw AWS credentials. Jentic stores keys in the MAXsystem vault, signs each request with SigV4, and returns the structured response — so an agent can pause its workflow until a human verdict arrives, then resume with the validated result.

Search Jentic for 'send a prediction for human review', load StartHumanLoop, and execute it when the agent's own confidence is below 0.7, then poll DescribeHumanLoop until Completed.

Key Endpoints

5 endpoints — jentic publishes the only available openapi specification for amazon augmented ai runtime, keeping it validated and agent-ready.

METHOD

PATH

DESCRIPTION

POST

/human-loops

Start a human review task

GET

/human-loops/{HumanLoopName}

Read the status and output of a human review task

GET

/human-loops

List human review tasks for a flow definition

POST

/human-loops/stop

Stop an in-progress human review task

DELETE

/human-loops/{HumanLoopName}

Delete a completed human review task

POST

/human-loops

Start a human review task

GET

/human-loops/{HumanLoopName}

Read the status and output of a human review task

GET

/human-loops

List human review tasks for a flow definition

POST

/human-loops/stop

Stop an in-progress human review task

DELETE

/human-loops/{HumanLoopName}

Delete a completed human review task

Why though Jentic?

Three things that make agents converge on Jentic-routed access.

Credential isolation

AWS credentials are stored encrypted in the Jentic vault (MAXsystem). Each A2I Runtime call is signed with SigV4 server-side; the agent only receives scoped, short-lived authorisation, so raw access keys never enter the agent's context.

Intent-based discovery

Agents search by intent (e.g., 'send a prediction for human review') and Jentic returns matching A2I operations with their input schemas, so the agent calls StartHumanLoop or DescribeHumanLoop without browsing AWS docs.

Time to first call

Direct A2I Runtime integration: 1 day for SigV4 signing and S3-output handling. Through Jentic: under 30 minutes for the API surface — search, load schema, execute (the flow definition still needs to exist in SageMaker).

Related APIs

Alternatives and complements available in the Jentic catalogue.

Complementary

Amazon SageMaker

Create the FlowDefinition and produce the predictions that A2I reviews

Use SageMaker to define the flow and serve predictions; use A2I Runtime when those predictions fall below confidence threshold.

Complementary

Amazon Textract

Textract output is a common A2I input for human document review

Use Textract for document OCR; route low-confidence Textract output through A2I when accuracy matters.

Alternative

Amazon Mechanical Turk

Lower-level crowdsourcing API — A2I sits on top of it for ML-specific review

Choose Mechanical Turk when you need direct control over crowdsourced HIT design; choose A2I when you want managed integration with SageMaker predictions.

FAQs

Specific to using Amazon Augmented AI Runtime API through Jentic.

Why is there no official OpenAPI spec for Amazon Augmented AI Runtime?

AWS does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call Amazon Augmented AI Runtime via structured tooling. It is validated against the live API and kept up to date. Get started at https://app.jentic.com/sign-up.

What authentication does the Amazon Augmented AI Runtime API use?

A2I Runtime uses AWS Signature Version 4 HMAC signing with an access key ID and secret access key, optionally with a session token. Through Jentic, those credentials live in the MAXsystem vault and the agent never handles raw secrets — Jentic signs each request server-side.

Can I create a flow definition with the Amazon Augmented AI Runtime API?

No — flow definitions are created via the SageMaker control-plane API (CreateFlowDefinition), not the A2I runtime. The runtime only starts, reads, stops, and deletes individual HumanLoop tasks against an already-defined flow. Set up the flow definition first in SageMaker, then call StartHumanLoop here.

What are the rate limits for the Amazon Augmented AI Runtime API?

AWS does not publish a fixed RPS for A2I Runtime in the spec; standard AWS API throttling applies. The deeper bottleneck is reviewer throughput, not API rate — high-volume workflows should size the workforce appropriately and use ListHumanLoops to monitor backlog.

How do I send a model prediction for human review through Jentic?

Search Jentic for 'send a prediction for human review', load StartHumanLoop, and call POST /human-loops with FlowDefinitionArn, a unique HumanLoopName, and the input JSON. Then poll DescribeHumanLoop until HumanLoopStatus is Completed and read HumanLoopOutput.OutputS3Uri for the reviewer's verdict. Install with pip install jentic.

Where does the Amazon Augmented AI Runtime API store the reviewer's output?

Reviewer output is written to the S3 bucket configured in the flow definition, not returned inline. DescribeHumanLoop returns an OutputS3Uri pointing at the JSON object the reviewer produced; your application reads it directly from S3 once the loop status is Completed.