Skip to main content
No items found.
currentColor
  • Platform
    • Complete Runtime Protection
      The unified enforcement platform for AI attacks.
    • Runtime Defense Agents
      Your AI security engineering team. Running inline.
    • Surfaces
    • LLM Protection
      Deterministic agent controls.
    • Agent Protection
      Control how agents behave in production.
    • MCP Protection
      Runtime control for the MCP layer.
    • WAF
      WAF for the Agentic Era.
    • API
      AI Security for the Agentic era.
  • Why Impart
  • Use Cases
    • Branding
    • Branding
    • Branding
    • Branding
    • Branding
    • Branding
    • Branding
    • Branding
    • Branding
  • Performance
  • Trust
    • Heading
      One runtime engine. Every request. Before your backend sees it.
    • Documentation
      Let the payload pass. It won’t execute.
    • Research
      Let the request run. It won’t succeed.
    • Events
      Lorem Ipsu Dolor Sit Ament
    • AI/LLM Security
      Let the prompt start. Harmful requests won't finish.
  • Resources
    • Resource Center
      Blog, Product Updates, Guides, and more.
    • Events
      Where to find us next.
    • AI/LLM Security
      Let the prompt start. Harmful requests won't finish.
  • Company
    • About
      At AI speed, runtime is the only source of truth.
    • Newsroom
      Impart in the News.
    • Careers
      Come build runtime defense with us.
  • Book a Demo
currentColor
  • Platform
    • Complete Runtime Protection
      The unified enforcement platform for AI attacks.
    • Runtime Defense Agents
      Your AI security engineering team. Running inline.
    • Surfaces
    • LLM Protection
      Deterministic agent controls.
    • Agent Protection
      Control how agents behave in production.
    • MCP Protection
      Runtime control for the MCP layer.
    • WAF
      WAF for the Agentic Era.
    • API
      AI Security for the Agentic era.
  • Why Impart
  • Use Cases
    • Branding
    • Branding
    • Branding
    • Branding
    • Branding
    • Branding
    • Branding
    • Branding
    • Branding
  • Performance
  • Trust
    • Heading
      One runtime engine. Every request. Before your backend sees it.
    • Documentation
      Let the payload pass. It won’t execute.
    • Research
      Let the request run. It won’t succeed.
    • Events
      Lorem Ipsu Dolor Sit Ament
    • AI/LLM Security
      Let the prompt start. Harmful requests won't finish.
  • Resources
    • Resource Center
      Blog, Product Updates, Guides, and more.
    • Events
      Where to find us next.
    • AI/LLM Security
      Let the prompt start. Harmful requests won't finish.
  • Company
    • About
      At AI speed, runtime is the only source of truth.
    • Newsroom
      Impart in the News.
    • Careers
      Come build runtime defense with us.
  • Request a Demo
Back to Blog

Announcing LLM Enrichments for API Specifications

Brian Joe
12.21.2023
•
2
min read

Today we’re excited to announce Specification Enrichment, an LLM-powered enhancement to our API Discovery feature. This enhancement is a copilot bolted onto a SaaS experience—a truly integrated enhancement that helps security teams better understand their risk and makes them more efficient.

LLM-powered Specification Enrichment

This enhancement enriches API descriptions provided by developers or automatically discovered by Impart, and makes them easier for humans to read by generating human readable endpoint descriptions and summaries based on API behavior.  

This helps security teams:

  • More quickly understand the purpose of large collections of endpoints
  • Reduce risk by improving documentation quality with high-quality descriptions that can be sent to engineering teams via developer workflows
  • Become more efficient by being able to use these enhanced API specifications directly in Impart’s integrated API security platform

Here’s what one of our customers said when we showed them the enhancement:

“It’s very cool knowing these API endpoint descriptions were generated via Large Language Models. They’re much easier to understand quickly.”

How API Discovery Helps Security Teams

Endpoint Inventory powered by API Discovery

API Discovery was designed to solve a few customer problems that we heard often from security teams:

  • Not knowing what API endpoints were in production
  • Not knowing what sensitive data was being carried by these APIs
  • Not being able to provide DAST tooling with an endpoint map
  • Not being able to provide DAST tooling with realistic test payloads

To solve these problems, we built an API Discovery solution that worked primarily through observing API traffic. By observing API traffic through multiple integration methods, we are able to determine what endpoints are seeing traffic as well as what the actual payloads are.  

This enables us to build a real-time API specification on the fly with rich detail about API endpoints and parameters, baseline that traffic, and compare live traffic to that baseline to identify risk factors like shadow APIs or non-conforming behavior.  

This API catalog and traffic baseline can be shared directly with DAST tooling such as BURP to enable security teams to easily run tests against different endpoints, without having to spend lots of time identifying what endpoints to test, or analyzing production databases to recreate realistic test payloads.

Schedule a demo at try.imp.art today to learn more about how Impart can help you better manage your API risk efficiently with LLM-powered Specification Enrichment. Also, be sure to follow us on LinkedIn for the latest and greatest.

Tags
Product
Table of contents
TOC Element
currentColor
Get a Demo

SOC 2 Type II

GDPR Ready

Platform

The Engine
Runtime Defense Agents

Trust

Performance

Surfaces

LLM
MCP
Agent
WAF
API

Company

About
Why Impart
Newsroom
Careers
Contact

Resources

Resource Center
Events

Trust

Performance
Subscribe*
Thank you! Your submission has been received!
Something went wrong while submitting the form.
Privacy Policy
Cookies Settings
© {{year}} Impart Security. All rights reserved.