Install Jentic One Beta

Connect the Fera API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Fera 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%2Ffera.ai%2Ffera" | 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%2Ffera.ai%2Ffera" | 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 Fera API.

Create, approve, and decline product reviews tied to specific orders and customers

Attach customer photos and videos to product listings as social proof

Aggregate star ratings per product and retrieve them for storefront display

Subscribe to webhooks for review submission, approval, and decline events

List orders and customers to correlate reviews with verified purchases

GET STARTED

Start building with Fera API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Fera API for, with concrete tasks.

★ Review Moderation Workflow

Automate moderation of user-generated reviews so an agent can approve clean submissions and decline ones containing prohibited content, instead of staff manually triaging the queue. Fera exposes dedicated PUT /reviews/{id}/approve and PUT /reviews/{id}/decline endpoints, removing the need for status-field updates on the base review object. Typical review volume is hundreds per day for a mid-sized store; agent moderation cuts response time from hours to seconds.

Fetch all reviews where state is pending, classify each via a content filter, and call PUT /reviews/{id}/approve or PUT /reviews/{id}/decline based on the result

Verified-Purchase Review Requests

Trigger review request emails after orders ship by joining order data with customer records and generating review entries linked to the original purchase. The Fera API exposes orders, customers, and reviews as related resources so an agent can correlate them in a single workflow. Implementation through Fera typically takes a day; building an equivalent flow on a generic e-commerce stack takes a week.

List orders fulfilled in the last 7 days, fetch each customer record, and create a Fera review draft with order_id and customer_id pre-populated

Visual Social Proof Galleries

Build dynamic photo and video galleries on product pages by pulling user-submitted media filtered by product. The /photos endpoints support listing, retrieving, and updating individual media items, and the API exposes both customer photos and review photos as separate resources. This replaces manual gallery curation with an agent-driven feed that surfaces fresh content as it is approved.

GET /photos filtered by product_id, return the 10 most recent approved photos, and update each to mark it as featured

Agent-Driven Review Insights via Jentic

Through Jentic, an agent can answer questions like which products have low ratings or which customers leave the most reviews without writing custom integration code. Jentic stores Fera credentials in your Jentic One instance and exposes review, rating, and product operations as tools, so a Claude or GPT agent can call them directly. This unlocks ad-hoc analytics and customer-support workflows without engineering involvement.

Search Jentic for 'list product reviews', load the schema, and return the 5 products with the lowest average rating in the last 30 days

Key Endpoints

37 endpoints — the fera api powers product reviews, photos, videos, ratings, and customer-generated content for online stores.

METHOD

PATH

DESCRIPTION

GET

/reviews

List reviews

POST

/reviews

Create review

PUT

/reviews/{id}/approve

Approve review

PUT

/reviews/{id}/decline

Decline review

GET

/photos

List customer photos

POST

/photos

Upload customer photo

GET

/reviews

List reviews

POST

/reviews

Create review

PUT

/reviews/{id}/approve

Approve review

PUT

/reviews/{id}/decline

Decline review

GET

/photos

List customer photos

POST

/photos

Upload customer photo

Why Jentic?

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

Setup

Wiring the Fera API by hand means managing its X-API-Key header, tracking the v3 private endpoints, and handling pagination across reviews and photos yourself. Through Jentic you install once, import the Fera API from the API Directory, store the API key once, and your agent calls it.

Permission scoping

Fera puts the review id in the URL path (/reviews/{id}/approve, /reviews/{id}/decline), so a rule can pin your agent to acting on the reviews you allow. You choose the operations it may call, so a moderation action like decline is not included unless you add it alongside approve.

Credential isolation

Your Fera API key is stored once, encrypted, by your own Jentic One instance and injected at execution time. The raw X-API-Key value never enters the agent's prompt, logs, or context.

Intent-based discovery

Agents search Jentic by intent such as 'approve a customer review' or 'list product photos', and Jentic returns the matching Fera operation with its input schema, so the agent calls the right endpoint without browsing developers.fera.ai.

FAQs

Specific to using Fera API through Jentic.

What authentication does the Fera API use?

The Fera API uses an API key sent in the X-API-Key header. When called through Jentic the key is stored encrypted in your Jentic One instance and never appears in agent context.

Can I approve reviews programmatically with the Fera API?

Yes. Fera exposes dedicated PUT /reviews/{id}/approve and PUT /reviews/{id}/decline endpoints, separate from the generic update review call, so moderation status changes are explicit and auditable.

What are the rate limits for the Fera API?

Fera does not publish per-second limits in the OpenAPI spec; check the developer documentation at developers.fera.ai for the current quotas tied to your plan.

How do I attach a photo to a product review through Jentic?

Search Jentic for 'attach product photo', load the POST /photos schema, and execute with product_id, customer_id, and the image URL. Run pip install jentic to get started.

Does the Fera API support webhooks?

Yes. The Webhooks resource lets you subscribe to events such as review created, approved, and declined, so an agent can react to new content as it arrives instead of polling.

Can the Fera API distinguish verified-purchase reviews?

Yes. Reviews can be linked to an order_id, which Fera uses to flag verified purchases. Agents can join /reviews and /orders to filter for verified entries.

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

Yes. Jentic One runs self-hosted, so your own rules decide which Fera operations and credentials the agent may use. Because Fera puts the review id in the URL path for actions like PUT /reviews/{id}/approve and PUT /reviews/{id}/decline, you can pin the agent to the reviews you allow and choose the exact operations it may call. For example, you can grant approve without ever exposing decline, and keep the API key injected only at execution time rather than in the agent's context.

Fera API

AI ReadinessAI-Aware (B+)67/100

See full scorecard

Official vendor OpenAPI document · agent-readyE CommerceStorefrontapiKey37 EndpointsREST

For Agents

Manage product reviews, photos, videos, and ratings for e-commerce stores via 37 REST endpoints, including moderation actions and webhook subscriptions.

Use for: I need to create a product review for a verified customer, Approve a pending review submitted yesterday, List all reviews with a 1-star or 2-star rating, Retrieve photos attached to a specific product

Not supported: Does not handle payments, inventory, or order fulfilment - use for product reviews, ratings, and customer UGC only.

The Fera API powers product reviews, photos, videos, ratings, and customer-generated content for online stores. It provides programmatic access to review moderation actions such as approve and decline, plus first-class endpoints for managing media uploads tied to specific products and orders. The 37-endpoint surface covers Customers, Media, Orders, Products, Ratings, Reviews, and Webhooks for end-to-end social-proof automation.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A-Signals: 4

97%

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).

10%

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: CSignals: 4

51%

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.

67%

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 Fera API to your agent

Capabilities

Start building with Fera API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Fera API

Jentic AI Readiness Score

Fera 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