Install Jentic One Beta

Connect the Poof API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Poof API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.

Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.

Step 1: Jentic One Host machine

# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fpoof.bg%2Fpoof-api" | sh

Step 2: Agent machine

# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fpoof.bg%2Fpoof-api" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.

Capabilities

What an agent can do with Poof API.

Remove backgrounds from images automatically with machine learning

Process JPEG, PNG, and WebP image formats

Preserve fine details like hair edges and transparency effects

Handle complex backgrounds including gradients and patterns

Return processed images as transparent PNG files

GET STARTED

Start building with Poof API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Poof API for, with concrete tasks.

★ E-commerce Product Photography Processing

Online retailers automate product image preparation by removing backgrounds from supplier photos, user-generated content, and in-house photography. The API processes images uploaded by sellers, standardizing product presentation with clean white or transparent backgrounds. Marketplaces integrate Poof into their listing creation flows, automatically processing images before publication. This reduces manual editing time from minutes per image to seconds, enabling scalable product catalog management. Merchandising teams can re-shoot products on any background knowing post-processing will extract subjects cleanly.

When seller uploads product image, send to Poof API for background removal, receive transparent PNG, overlay on standardized marketplace background color, save processed image to CDN, update product listing with clean image URL.

Marketing Collateral and Design Automation

Marketing teams use Poof to prepare images for ads, social posts, and website graphics where subjects need to overlay branded backgrounds. Design systems integrate the API to automatically process headshots, product shots, and lifestyle imagery, enabling dynamic creative generation. Automated design tools call Poof to extract subjects, then composite them onto template backgrounds with text and branding. This enables personalized marketing at scale where hundreds of ad variants are generated programmatically with different subject combinations and backgrounds.

Load subject images for ad campaign, send each to Poof for background removal, composite extracted subjects onto branded template backgrounds, add text overlay, generate 50 ad variants, export for social media platforms.

User Profile Picture Enhancement

Social platforms and professional networking sites use Poof to enhance user-uploaded profile pictures by removing distracting backgrounds. The API processes profile photos, removing cluttered rooms, outdoor scenes, or event backgrounds, leaving the subject on transparent or neutral backgrounds. This creates visual consistency across user directories and improves perceived professionalism. Apps offer this as a premium feature where users upload casual photos and receive professionally presented profile pictures with clean backgrounds automatically.

When user uploads profile picture, detect faces and crop to portrait orientation, send to Poof for background removal, overlay on subtle gradient or solid color, offer both transparent and colored versions, let user select preferred output.

Batch Image Processing for Catalogs and Archives

Organizations with large image archives use Poof to bulk-process historical product photos, team headshots, or inventory images, standardizing backgrounds across collections. The API integrates into batch processing pipelines that iterate through S3 buckets or media libraries, process each image, and save results. This modernizes legacy catalogs where products were photographed on inconsistent backgrounds. Museums and archives use it to extract artifacts from old photography backgrounds, creating clean imagery for digital collections and search results.

Iterate through product image S3 bucket, fetch each image, send to Poof API, validate processed output, save transparent PNG to processed bucket, update database with new image URL, generate progress report for completed batch.

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring Poof by hand means handling its bearer token auth and posting the image payload to the removal endpoint yourself. Through Jentic you install once, import Poof from the API Directory, store the token once, and your agent calls it.

Permission scoping

Poof exposes a single background-removal operation (POST /remove) that takes the image in the request body, so you limit the agent to just the operation it needs. No other operation is added unless you choose to.

Credential isolation

Your Poof token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.

Intent-based discovery

Agents search Jentic by intent such as 'remove background from image', and Jentic returns the matching Poof operation with its image input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using Poof API through Jentic.

What authentication does the Poof API use?

The Poof API uses Bearer token authentication. You obtain an API token from your Poof account and include it in the Authorization header for all requests.

What image formats does Poof support?

Poof accepts JPEG, PNG, and WebP image formats as input. The API returns processed images as transparent PNG files suitable for design and e-commerce use.

How does Poof handle complex backgrounds and fine details?

Poof uses machine learning models trained to preserve fine details like hair edges and partial transparency while removing backgrounds. It handles complex scenes including gradients, patterns, and multi-subject images with consistent quality.

Can I process images in batch with the Poof API?

Yes, you can call the single /remove endpoint in a loop or parallel processing pipeline to batch-process multiple images. Many users integrate Poof into workflow systems that process image collections from S3, CDNs, or databases.

How do AI agents use the Poof API through Jentic?

Agents search Jentic for tasks like 'remove background from product photo' and receive the Poof operation schema. Jentic securely stores API tokens, handles authentication, and allows agents to process images by URL or file upload with natural language instructions.

Can I limit what my agent is allowed to do with the Poof API?

Yes. Poof exposes a single background-removal operation, POST /remove, which takes the image in the request body, and because you run Jentic One yourself you decide that this is the only operation your agent may call. No other operation is added unless you choose to grant it, so the agent cannot reach beyond removing backgrounds from the images you send. Your Poof bearer token stays with your own instance and is injected only when that permitted operation runs, never entering the agent's prompt or logs.

Poof Bg Poof API

Name: Poof API
Brand: Poof API
Availability: InStock

AI ReadinessAI-Aware (B)66/100

See full scorecard

Official vendor OpenAPI document · agent-readyMediaImage Processingbearer1 EndpointsREST

For Agents

Remove backgrounds from images automatically using machine learning, returning transparent PNG files suitable for design and e-commerce.

Use for: Remove the background from a product photo, Create a transparent PNG from a portrait image, Extract the subject from an image for design work, Process a batch of product images removing backgrounds

Not supported: Provides automated background removal only. Does not perform general image editing, color correction, or object manipulation-use dedicated image processing APIs. Does not host or deliver images-use CDN services.

Poof is a background removal API that uses machine learning to automatically extract subjects from images, leaving transparent backgrounds. The API accepts images in common formats (JPEG, PNG, WebP) and returns processed images with backgrounds removed, suitable for e-commerce product photography, marketing collateral, and profile pictures. Developers integrate it into content workflows, image editing tools, and automated design systems. The single endpoint simplicity makes it straightforward to implement compared to complex image processing libraries. Poof handles edge cases like hair detail preservation, partial transparency, and complex backgrounds without requiring manual selection or masking. It processes images in seconds with consistent quality, enabling high-throughput workflows for marketplaces, design platforms, and user-generated content moderation.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

100

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A+Signals: 4

99%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

100%

Specification Validity

Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).

100%

Structural Integrity

Structural correctness score based on schema issues using logarithmic dampening.

Developer Experience & Jentic Compatibility

Clarity, completeness, and ingestion readiness for developers and tooling.

Grade: B-Signals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

50%

Response Coverage

Percentage of operations with complete response definitions (success, client error, server error).

100%

Tooling Readiness

Health of API ingestion, bundling, and resolution within Jentic pipelines.

AI-Readiness & Agent Experience

Semantic breadth, depth, and agent comprehension for AI systems.

Grade: DSignals: 4

35%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

100%

OperationId Quality

Coverage, uniqueness, and casing consistency of operationIds for AI inference.

50%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: A+Signals: 1

94%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: C-Signals: 1

50%

Authentication Strength

Average quality of security schemes based on authentication method strength (weakest link for OAuth2).

100

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: A+Signals: 1

100%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Poof API to your agent

Capabilities

Start building with Poof API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Poof Bg Poof API

Jentic AI Readiness Score

Poof API

Foundational Compliance

Lint Results

Resolution Completeness

Specification Validity

Structural Integrity

Developer Experience & Jentic Compatibility

Example Density

Example Validity

Response Coverage

Tooling Readiness

AI-Readiness & Agent Experience

Description Coverage

Error Standardization

OperationId Quality

Summary Coverage

Agent Usability

Complexity Comfort

Security

Authentication Strength

AI Discoverability

Descriptive Richness