Postman AI Native Platform
Fabric
Fern
Astro
Passport

The AI stack for the agentic era.

Every layer your agents need to reach your APIs, and every control you need to govern them.

Five orbits, one stack.

Each ring settles into a load-bearing layer: access, gateway, runtime, experience, and the AI-native foundation.

5Layers1Stack0Glue code

Hover a layer · click to inspect

Five layers. One agent-native stack.

We build the infrastructure every AI model depends on: the APIs that connect, communicate, and deliver value, from the first request to a governed production runtime.

Passport

ACCESS MANAGEMENT

Access management for humans and agents, controlling who and what can reach your APIs across the stack.

LEARN MORE

Fabric Gateway

AGENT-NATIVE GATEWAY

The AI-native gateway with support for AI, MCP, and APIs, governing policy, identity, and scope at the edge of every enterprise environment.

LEARN MORE

Fern

DOCS, SDKS & CLIS

Agent and developer experience covering docs, SDKs, and CLIs, so every API is discoverable, typed, and callable out of the box.

LEARN MORE

Astro

AGENT OPERATING SYSTEM

The agent operating system that runs and controls AI agents in production, with runtime, observability, and guardrails at scale.

LEARN MORE

Postman AI Native Platform

THE FOUNDATION

The foundation platform every layer above is built on and lives within: the API Catalog, the Context Graph, and the AI Engineer, unified in one workspace.

LEARN MORE
API SCORING PORTAL

Are your APIs ready for AI Agents?

Postman scores how well AI agents like Claude, ChatGPT, and Cursor can find, read, and build with your APIs. See where you rank.

Score your API

The science of the agent-native stack.

APIFlow-Bench: a vendor-neutral benchmark measuring whether AI agents can reliably execute multi-step API workflows in enterprise contexts, run across 19 models by the Postman AI team.

“APIFlow-Bench: The Enterprise Survival Test for AI Agents.”

A vendor-neutral benchmark testing long-horizon API chains (up to 20 dependent subtasks) across seven capability axes: authentication refresh, endpoint discovery, schema repair, multistep reasoning, error recovery, pagination, and statefulness. Deterministic state verification and sandboxed generation measure workflow reliability rather than conversational fluency.

READ THE BENCHMARK

The latest from across the stack.

PRODUCT MILESTONE

The Autonomous AI Engineer ships in v12

Agent Mode graduates from copilot to collaborator, planning, calling, and verifying APIs end to end.

READ
STRATEGIC PARTNERSHIP

Claude, native in Agent Mode

A deep integration that lets Claude reason over your live API surface inside the workspace.

READ
RESEARCH

Benchmarking discovery on Fern-indexed APIs

Agent-readable docs cut time-to-first-successful-call by an order of magnitude.

READ

Watch the stack in action.

Executive briefings, developer conferences, and media deep-dives on preparing APIs for the agentic era.

EXECUTIVE BRIEFINGPASSPORT

Preparing your APIs for agent-based AI

38 MINSWATCH →
MEDIA INTERVIEWFERN

Standardizing your SDKs for machines

24 MINS · TECHSTRONGWATCH →
DEVELOPER CONFERENCEASTRO

Agentic protocol design

10 MINS · KUBECONWATCH →

Postman AI stack.

Five products, one agent-native stack. Start building with any layer today.