Product
Jentic OSThe workplace. An in-house AI platform for every employeeJentic OneSafe access. Agents reach your systems without holding keysJentic AIRThe foundation. Gets your existing platforms ready for AI
Pricing
Developers

GET STARTED

API DirectoryBrowse 10,000+ APIs Ready For AI Agent IntegrationDocumentationGuides and API reference

TOOLS

API ScoringCheck your AI Readiness using our scorecardArazzo UIVisualize Arazzo Workflows As Interactive DocumentationArazzo EditorBuild And Edit Multi-Step API Workflows Visually

COMMUNITY

GitHubOpen source projects and examplesOpen StandardsBuilt on open specs. Never locked in.
Resources
Company
About UsOur mission and teamCareersJoin our teamContactGet in touch
Try it now
Jentic OSJentic OneJentic AIR
Pricing
API DirectoryDocumentationAPI ScoringArazzo UIArazzo EditorGitHubOpen Standards
Resources
About UsCareersContact
Try it now
JenticJentic
Products
  • Jentic OS
  • Jentic One
  • Jentic AIR
For Developers
  • API Directory
  • Documentation
  • GitHub
Company
  • About Jentic
  • Careers
  • Contact Us
  • Trust Centre
ISO/IEC 27001:2022 certification badge issued by Prescient SecurityISO/IEC 27001:2022 certification badge issued by Prescient Security

Information Security Management System

Certified to ISO/IEC 27001:2022 by Prescient Security

AICPA SOC for Service Organizations logoAICPA SOC for Service Organizations logo

SOC 2® Type 1 report

Audited by Prescient Assurance

Terms & Conditions•Privacy Policy•
© 2026 Jentic Technology Ltd. All rights reserved.
2 Grattan Court East, Dublin, D02 VX86, Ireland
Switch to light modeSwitch to dark mode
APIs / HR recruiting / Retriever API
Retriever API logo

Helloretriever Retriever API

52
AI ReadinessFoundational (C-)52/100
See full scorecard
Official vendor OpenAPI document · agent-readyHR recruitingEmployee Managementbearer9 EndpointsREST

For Agents

Submit device return orders for offboarding employees, check return status, and look up prepaid balances so an agent can run end-to-end equipment retrieval workflows.

Use for: I need to submit a laptop return order for an offboarding employee, Check whether a device return order has shipped, List all warehouse return addresses available in Retriever, Get the prepaid balance on our Retriever account

Not supported: Does not handle device provisioning, IT asset purchasing, or shipping label printing - use for submitting and tracking employee device returns only.

The Retriever API lets HR and IT teams submit and track device return orders for laptops, cell phones, and monitors from US and Canada-based employees. Orders cover prepaid balance lookups, warehouse address management, and per-deployment status queries. The API is tied to a Retriever portal account, so submitted orders are billable unless cancelled within 30 minutes via the dashboard.

Jentic One on GithubView OpenAPI Document

Install Jentic One Beta

Connect the Retriever API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Retriever 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.

1

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%2Fapp.helloretriever.com%2Fhelloretriever" | sh
2

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%2Fapp.helloretriever.com%2Fhelloretriever" | 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 Retriever API.

Create a device return order for a departing employee via /api/v2/device_returns/

Retrieve the status of a specific device return by order ID

List warehouse destinations the device can be shipped back to

Check prepaid balance before submitting orders that incur charges

Look up deployment records for a returning employee

Cancel test orders within 30 minutes by combining order creation with portal cancellation

Use Cases

Patterns agents use Retriever API for, with concrete tasks.

★ Automated Offboarding Device Return

Trigger a device return order automatically when HRIS marks an employee as offboarding. The orchestration calls POST /api/v2/device_returns/ with the employee shipping address and device type, then polls GET /api/v2/device_returns/{id}/ until the order ships. Returns are limited to laptops, cell phones, and monitors for US employees and laptops and cell phones for Canada employees, with the return destination required to be a US address.

Read offboarding event from HRIS, call POST /api/v2/device_returns/ with the employee's home address and device_type=laptop, then confirm by polling GET /api/v2/device_returns/{id}/ for tracking number

Prepaid Balance Monitoring

Avoid order failures by checking prepaid balance before initiating bulk returns at quarter-end or during a layoff event. GET /api/v2/prepaid_balances/ returns current credit, allowing finance to top up the account before submitting dozens of orders that would otherwise be rate-limited or rejected for insufficient funds.

Call GET /api/v2/prepaid_balances/ before any batch return submission and alert finance if balance is below the projected cost of pending returns

Return Status Reporting

Build a status dashboard for IT asset managers showing every active device return, its courier tracking, and expected receipt date. The agent walks /api/v2/device_returns/ with pagination, joins each entry with /api/v2/warehouse/ to resolve the destination, and produces a single view across all open returns.

List all active device returns via GET /api/v2/device_returns/, enrich each with warehouse name from GET /api/v2/warehouse/{id}/, and output a CSV grouped by status

Agent-Initiated Equipment Recovery

Let an internal IT helpdesk agent submit a Retriever return order in response to a Slack or ticket request. The agent searches Jentic for 'submit a device return', loads the operation schema, and executes with the employee's address and device type - without the agent ever holding the bearer token.

Search Jentic for 'submit a device return', load the schema, and call POST /api/v2/device_returns/ with the address and device type from the helpdesk ticket

Key Endpoints

9 endpoints — the retriever api lets hr and it teams submit and track device return orders for laptops, cell phones, and monitors from us and canada-based employees.

METHOD

PATH

DESCRIPTION

POST

/api/v2/device_returns/

Submit a device return order

GET

/api/v2/device_returns/{id}/

Get status of a specific device return

GET

/api/v2/deployments/

List deployments for returning employees

GET

/api/v2/deployments/{id}/

Get a specific deployment

GET

/api/v2/prepaid_balances/

Check prepaid account balance

GET

/api/v2/warehouse/

List warehouse destinations

POST

/api/v2/device_returns/

Submit a device return order

GET

/api/v2/device_returns/{id}/

Get status of a specific device return

GET

/api/v2/deployments/

List deployments for returning employees

GET

/api/v2/deployments/{id}/

Get a specific deployment

GET

/api/v2/prepaid_balances/

Check prepaid account balance

GET

/api/v2/warehouse/

List warehouse destinations

Jentic AI Readiness Score

This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.

R

Retriever API

- Foundational (C-)
52/100
72
Foundational Compliance
44
Developer Experience & Jentic Compatibility
31
AI-Readiness & Agent Experience
94
Agent Usability
60
Security
100
AI Discoverability
Powered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.0
Show dimension breakdown
72

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A-Signals: 4
87%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

0%

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.

44

Developer Experience & Jentic Compatibility

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

Grade: DSignals: 4
10%

Example Density

How richly the API is illustrated with examples.

37%

Example Validity

Percentage of examples that conform to their schemas.

31%

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.

31

AI-Readiness & Agent Experience

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

Grade: FSignals: 4
64%

Description Coverage

Coverage of descriptions across API elements.

0%

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

0%

OperationId Quality

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

58%

Summary Coverage

Coverage of summaries across operations/tags/info.

94

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.

60

Security

Trust, risk posture, and security compliance.

Grade: B-Signals: 1
60%

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.

View full reportHow the score is calculatedMore about the dimensions

Score it yourself

Every API in the directory is allowlisted, so you can re-score it with no key required.

Score your own APIScoring CLI agent skill
npx @jentic/api-scorecard-cli score <openapi-url>

Why Jentic?

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

Setup

Wiring Retriever by hand means learning its bearer auth and threading device-return and deployment ids through its v2 paths yourself. Through Jentic you install once, import the Retriever API from the API Directory, store the token once, and your agent calls it.

Permission scoping

Retriever puts the record id in the URL path (/api/v2/device_returns/{id}/), so a rule can pin your agent to reading and tracking specific device returns. You choose the operations it may call, so submitting a new billable device return is not included unless you add it.

Credential isolation

Your Retriever bearer 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 'submit a device return' or 'check return status', and Jentic returns the matching device-returns operation with its input schema so the agent calls the right endpoint without reading Retriever docs.

Related APIs

Alternatives and complements available in the Jentic catalogue.

Complementary

BambooHR API

→

BambooHR is the typical HRIS source-of-truth that triggers a Retriever return when an employee is marked as offboarding

Use BambooHR to detect the offboarding event, then call Retriever to submit the matching device return order

Complementary

Workable API

→

Workable manages the hiring side; Retriever closes the loop on equipment when employees leave

Workable is upstream (hire/onboard); Retriever is downstream (offboard/return)

Complementary

SmartRecruiters API

→

SmartRecruiters covers ATS workflows and can trigger downstream device retrieval through Retriever

Pair SmartRecruiters offboarding events with Retriever return orders for full lifecycle coverage

FAQs

Specific to using Retriever API through Jentic.

What authentication does the Retriever API use?

Bearer token authentication. Tokens are issued from the Retriever portal and passed in the Authorization header. Through Jentic the bearer token is stored encrypted in the vault (your Jentic One instance) and never enters agent context.

Can I submit a device return order without using the portal UI?

Yes. POST /api/v2/device_returns/ creates an order programmatically. Note that submitted orders are real and billable - to test, submit and then cancel via the portal dashboard within 30 minutes, after which orders are final.

What are the rate limits for the Retriever API?

Read requests are limited to 60 per minute and 500 per day. Write requests (submitting returns) are limited to 600 per minute and 5000 per day. A 429 response is returned when limits are exceeded - contact Retriever support for higher limits.

How do I trigger a device return through Jentic?

Run pip install jentic, then search 'submit a device return order'. Jentic returns POST /api/v2/device_returns/ with its input schema - load the schema, populate the employee address and device type, and execute. The agent never sees the bearer token.

Which countries and devices are supported?

Returns are supported for laptops, cell phones, and monitors from US-based employees, and laptops and cell phones from Canada-based employees. For Canada-based returns the destination warehouse must be a US address.

Can I cancel a return after submitting?

Yes, but only within 30 minutes of submission and only via the Retriever portal dashboard. The API does not expose a programmatic cancel endpoint - orders are final after the 30-minute window.

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

Yes. Because Jentic One is self-hosted, you set the rules that decide which Retriever operations your agent can call, and it runs under your own instance. Since Retriever puts the record id in the URL path, such as GET /api/v2/device_returns/{id}/, you can pin the agent to reading and tracking specific device returns while leaving out the billable POST /api/v2/device_returns/ that submits a new order. The bearer token stays with your instance and is injected only at execution, so the agent acts strictly within the operations you have allowed.

GET STARTED

Start building with Retriever API

Explore with Jentic One
View OpenAPI Document