Install Jentic One Beta

Connect the InterviewStream API to your agent

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

List and retrieve candidates and their associated profile data

List and retrieve requisitions (open roles) and the candidates linked to each

Read requisition-candidate join records to track which candidate is in which pipeline stage

Pull share links generated for a candidate so reviewers can view recorded responses

GET STARTED

Start building with InterviewStream API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use InterviewStream API for, with concrete tasks.

★ ATS Sync of Candidate Data

Talent-acquisition teams sync InterviewStream candidate and requisition data back into their primary ATS so the pipeline status and recorded-interview links live alongside other application data. GET /candidates and GET /requisitions return the source records, while GET /requisitionCandidates returns the join table that maps candidates to roles. Daily sync replaces manual export-and-import.

List all InterviewStream candidates, then for each requisitionCandidate emit a row with iCandidate, iRequisition, and the share link

Reviewer Distribution

Hiring managers need to share recorded video responses with peer reviewers. The /requisitionCandidates/{id}/shareLinks endpoint returns the canonical share URL for a candidate's response, which the integration drops into Slack, email, or a custom review portal. Distribution that previously required a manager to log in and copy a link becomes an automated push.

Retrieve the share link for requisitionCandidate 9982 and post it to the #hiring-eng Slack channel

Incoming Assessment Triage

Recruiting coordinators monitor /incoming-assessment for new candidate responses and push notifications to the assigned reviewer in real time. Combined with /requisitionCandidates/{id}/requests, the team has full context on which requests are outstanding and which have just landed. Triage that took daily portal logins becomes an event-driven flow.

Poll GET /incoming-assessment every 15 minutes and post each new entry to the assigned hiring manager with the candidate name and requisition title

Agent-Driven Hiring Status Reports

An AI agent answers questions like 'how many candidates are at the video-interview stage for our backend role?' by calling /requisitions/{iRequisition}/candidates and aggregating the response. Jentic stores the X-AUTH-TOKEN in your Jentic One instance so the agent never sees the raw token. Status reports that previously required a portal login and manual count happen on demand in chat.

Pull candidates for requisition iRequisition 4421, count the number with a recorded share link, and report the total to the hiring manager

Key Endpoints

10 endpoints — jentic publishes the only available openapi specification for the interviewstream api, keeping it validated and agent-ready.

METHOD

PATH

DESCRIPTION

GET

/candidates

List candidates in the workspace

GET

/candidates/{iCandidate}

Retrieve a single candidate by ID

GET

/requisitions

List open requisitions

GET

/requisitions/{iRequisition}/candidates

List candidates attached to a requisition

GET

/requisitionCandidates/{iRequisitionCandidates}/shareLinks

Read share links for a requisition-candidate record

GET

/requisitionCandidates/{iRequisitionCandidates}/requests

Read interview requests for a requisition-candidate record

GET

/incoming-assessment

List newly received candidate responses

GET

/candidates

List candidates in the workspace

GET

/candidates/{iCandidate}

Retrieve a single candidate by ID

GET

/requisitions

List open requisitions

GET

/requisitions/{iRequisition}/candidates

List candidates attached to a requisition

GET

/requisitionCandidates/{iRequisitionCandidates}/shareLinks

Read share links for a requisition-candidate record

GET

/requisitionCandidates/{iRequisitionCandidates}/requests

Read interview requests for a requisition-candidate record

GET

/incoming-assessment

List newly received candidate responses

Why Jentic?

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

Setup

Wiring the InterviewStream API by hand means setting up its X-AUTH-TOKEN header and tracking the read paths for candidates, requisitions, and share links. Through Jentic you install once, import the InterviewStream API from the API Directory, store the token once, and your agent calls it.

Permission scoping

InterviewStream puts the requisition id in the URL path (/requisitions/{iRequisition}/candidates), so a rule can pin your agent to one requisition and the read operations you approve on it. Every operation here is a read, so no write path is available to add.

Credential isolation

Your InterviewStream X-AUTH-TOKEN is stored once, encrypted, by your own Jentic One instance and injected into the request header at execution time. It never enters the agent's prompt, logs, or context.

Intent-based discovery

Agents search Jentic by intent such as 'list InterviewStream candidates' or 'get share links for a requisition candidate', and Jentic returns the matching operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using InterviewStream API through Jentic.

Why is there no official OpenAPI spec for the InterviewStream API?

InterviewStream does not publish a public OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call the InterviewStream API via structured tooling. It is validated against the live API and kept up to date. Get started with Jentic One, the self-hosted execution layer.

What authentication does the InterviewStream API use?

It uses a persistent token passed in the X-AUTH-TOKEN header (the spec defines an apiKey scheme named HasApiKey with header name X-AUTH-TOKEN). Through Jentic, the token is stored in your Jentic One instance and injected at execution time so it never enters the agent's prompt or logs.

Can I list candidates with the InterviewStream API?

Yes. GET /candidates returns the list of candidates in the workspace and GET /candidates/{iCandidate} retrieves a single candidate by ID. The candidate's interview activity sits under the requisitionCandidates resource via the iRequisitionCandidates ID.

What are the rate limits for the InterviewStream API?

The OpenAPI spec does not declare numeric rate limits. InterviewStream applies per-tenant fair-use throttling; treat HTTP 429 as the canonical signal and back off. For bulk sync, prefer paginated reads at off-peak times.

How do I retrieve a candidate's share link through Jentic?

Search Jentic for 'get InterviewStream share link'. The SDK returns the GET /requisitionCandidates/{iRequisitionCandidates}/shareLinks operation. Run pip install jentic, await client.search('get InterviewStream share link'), then await client.execute(...) with the iRequisitionCandidates ID.

Does this API allow creating or sending interview requests?

No. The 10 endpoints in v0.3.0 are read-only - they cover listing and retrieving candidates, requisitions, share links, requests, and incoming assessments. Creating interview requests is performed through the InterviewStream UI or via webhooks negotiated separately.

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

Yes. Because you run Jentic One yourself, your own rules decide which InterviewStream operations and credentials the agent may use. Every endpoint here is read-only (candidates, requisitions, requisition-candidate links, share links, requests, and the incoming-assessment feed), so you can grant only the reads you approve and no write path exists. Since the requisition id lives in the URL path, such as GET /requisitions/{iRequisition}/candidates, a rule can also pin the agent to a single requisition.

InterviewStream API

AI ReadinessFoundational (C-)52/100

See full scorecard

Agent-ready OpenAPI document · curated by JenticHR recruitingRecruiting AtsapiKey10 EndpointsREST

Know of an official OpenAPI document? Contribute it →

For Agents

Read InterviewStream candidates, requisitions, requisition-candidate links, share links, and incoming assessments tied to a recruiting workflow.

Use for: I need to list all candidates in InterviewStream, Get the requisitions currently open in our InterviewStream account, Find which candidates are linked to requisition 4421, Retrieve the share link for a candidate's recorded interview

Not supported: Does not handle interview-request creation, candidate scoring, recording playback delivery, or scheduling - use for InterviewStream read-only candidate, requisition, share-link, and incoming-assessment data only.

Jentic publishes the only available OpenAPI specification for the InterviewStream API, keeping it validated and agent-ready. InterviewStream is a video-interviewing platform used by HR teams to send asynchronous interview requests to candidates and review the recorded responses; the v0.3.0 API exposes 10 read endpoints covering candidates, requisitions, requisition-candidate links, share links, requests, and the incoming-assessment feed. Authentication is a persistent token passed in the X-AUTH-TOKEN header.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A-Signals: 4

89%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

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: FSignals: 4

68%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

OperationId Quality

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

45%

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 InterviewStream API to your agent

Capabilities

Start building with InterviewStream API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

InterviewStream API

Jentic AI Readiness Score

General 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