Install Jentic One Beta

Connect the Iterant Public API to your agent

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

List page opportunities ranked by priority score and filter by intent, role, archetype, status, or surface

Read one opportunity's thesis, target prompt, keywords, and drafted brief, with supporting citations through includeEvidence

Report a page's Search Console performance, traffic, conversions, or component anatomy over a 7d, 28d, or 90d window

Track AI visibility as share of voice, citation gaps, top sources, or prompt scores, split by platform such as chatgpt or gemini

GET STARTED

Start building with Iterant Public API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Iterant Public API for, with concrete tasks.

★ Agent-run content pipeline

An AI agent responsible for a brand's content picks the next page to build and hands it to Iterant. Through Jentic the agent searches for 'list page opportunities', reads the ranked list for the brand, and starts a task with command build_page and the chosen opportunityRef, with the bearer key injected at call time. It then polls the task until it reports succeeded and returns the resultingRoute.

Call GET /api/v1/public/brands/{brandSlug}/page-opportunities/ with status ready, then POST /api/v1/public/brands/{brandSlug}/tasks/ with command build_page and the top row's ref as opportunityRef, and poll GET /api/v1/public/brands/{brandSlug}/tasks/{taskId}/ until it settles

AI search visibility reporting

A marketing lead wants to know how often assistants cite the brand against competitors. The visibility overview returns one projection per call, such as kpis, share_of_voice, citation_gaps, or top_sources, filtered by platform and window, so a weekly report can show where competitors win citations on ChatGPT, Gemini, or Google AI Overviews.

Call GET /api/v1/public/brands/{brandSlug}/visibility/overview/ with view citation_gaps, platform chatgpt, and window 28d, and list the prompts where the brand is not cited

Page performance review

Before rewriting a page, an editor checks how it performs today. The page report takes a urlPath and asks only for the metrics needed, such as performance for Search Console clicks, impressions, CTR, and position, or traffic for sessions and conversions, over a 7d, 28d, or 90d window.

Call GET /api/v1/public/brands/{brandSlug}/reports/pages/ with urlPath /pricing, metrics performance, and window 28d, and report clicks and average position

Internal linking for new pages

When a page goes live it needs links from the rest of the site. The linking advisory returns which existing pages should link to the target, the suggested anchor text, and the passage the link would sit in, each with a relevance from 0 to 1, so an editor can act on the strongest placements first.

Call GET /api/v1/public/brands/{brandSlug}/linking/advisory/ with urlPath /pricing and list suggestions with relevance above 0.6

Key Endpoints

12 endpoints — the iterant public api reads a brand's website pages, ranked page opportunities, page performance reports, and ai visibility, and starts iterant's agent to build or change a page.

METHOD

PATH

DESCRIPTION

GET

/api/v1/public/brands/

List accessible brands

GET

/api/v1/public/brands/{brandSlug}/overview/

Get a brand overview

GET

/api/v1/public/brands/{brandSlug}/page-opportunities/

List page opportunities

GET

/api/v1/public/brands/{brandSlug}/reports/pages/

Get a page report

GET

/api/v1/public/brands/{brandSlug}/visibility/overview/

Get AI visibility

POST

/api/v1/public/brands/{brandSlug}/tasks/

Start an agent task

GET

/api/v1/public/brands/{brandSlug}/tasks/{taskId}/

Get an agent task

GET

/api/v1/public/brands/

List accessible brands

GET

/api/v1/public/brands/{brandSlug}/overview/

Get a brand overview

GET

/api/v1/public/brands/{brandSlug}/page-opportunities/

List page opportunities

GET

/api/v1/public/brands/{brandSlug}/reports/pages/

Get a page report

GET

/api/v1/public/brands/{brandSlug}/visibility/overview/

Get AI visibility

POST

/api/v1/public/brands/{brandSlug}/tasks/

Start an agent task

GET

/api/v1/public/brands/{brandSlug}/tasks/{taskId}/

Get an agent task

Why Jentic?

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

Setup

Wiring Iterant by hand means minting an itr_ key, sending it as a bearer token, handling RateLimit fields and Retry-After on 429s, and sending an Idempotency-Key on task starts. Through Jentic you install once, import Iterant from the API Directory, store the key once, and your agent calls it.

Permission scoping

Iterant puts the brand slug in the URL path (/api/v1/public/brands/{brandSlug}/...), so a rule can pin your agent to one brand. You choose the operations it may call, so task starts that change the site, such as POST to the tasks route, are not included unless you add them.

Credential isolation

Your Iterant API key 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 'list page opportunities' or 'track AI visibility for a brand', and Jentic returns the matching Iterant operation with its input schema, including brandSlug and the view and window enums, so the agent calls the right endpoint.

FAQs

Specific to using Iterant Public API through Jentic.

What authentication does the Iterant Public API use?

Per its OpenAPI spec, every operation uses a bearer token: send Authorization: Bearer with an itr_ API key that an organization admin mints under Settings > Developers. An org-scoped key reads every brand in the organization, and a brand-pinned key reads only its own. Through Jentic the key is stored by your own instance and attached at call time, so the agent never sees it.

What are the rate limits for the Iterant Public API?

The spec states 600 requests per minute per key and 30 task starts per minute, with RateLimit-Limit, RateLimit-Remaining, and RateLimit-Reset fields on responses. A 429 carries Retry-After in seconds. See https://iterant.ai/docs/developers/rest-api for details.

How long does an Iterant agent task take?

The spec says a typical task settles in about five minutes and recommends polling GET /api/v1/public/brands/{brandSlug}/tasks/{taskId}/ every 30 to 60 seconds. A build_page task reports the page it produced in resultingRoute, and the task create call accepts an Idempotency-Key header so a retry within 24 hours returns the first task.

Is there an Iterant MCP server?

You don't need an MCP server to give your agent Iterant. Jentic connects it directly from the API Directory: import it, store your key once, and your agent calls the page, opportunity, and visibility operations it needs without loading another server's tool definitions into its context.

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

Yes. Write a rule that allows only the GET operations under /api/v1/public/brands/acme/, for example, and the agent can read that brand's pages, opportunities, reports, and visibility but cannot start tasks that change the site. Every call it makes is logged.

How do I read a brand's AI visibility through Jentic?

Search Jentic for 'track AI visibility for a brand', load the GET /api/v1/public/brands/{brandSlug}/visibility/overview/ operation, and execute it with the brandSlug from the brands list and a view such as kpis. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Iterant Public API

AI ReadinessAI-Aware (B-)61/100

See full scorecard

Official vendor OpenAPI document · agent-readyMarketingSeo Sembearer12 EndpointsREST

For Agents

Read a brand's pages, ranked page opportunities, Search Console performance, and AI visibility in Iterant, get internal-linking suggestions, and start Iterant's agent to build a page or run a prompt.

Use for: List the highest-priority page opportunities for my brand, Get the drafted brief for a page opportunity, Check how the pricing page performed in Search Console over 28 days, Find citation gaps where competitors are cited by ChatGPT

Not supported: Does not run paid search campaigns, manage backlinks, or host sites outside Iterant. Use for reading Iterant page, opportunity, and AI visibility data and starting Iterant agent tasks only.

The Iterant Public API reads a brand's website pages, ranked page opportunities, page performance reports, and AI visibility, and starts Iterant's agent to build or change a page. Page opportunities carry a priority score, search intent, and a drafted brief with outline and FAQ, while page reports project Search Console performance, traffic, conversions, and component anatomy for a chosen window. The AI visibility overview returns share of voice, citation gaps, and prompt scores across assistants such as ChatGPT, Gemini, and Google AI Overviews, and internal-linking advisories suggest which pages should link to a target page.

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: A-Signals: 4

17%

Example Density

How richly the API is illustrated with examples.

95%

Example Validity

Percentage of examples that conform to their schemas.

75%

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: D-Signals: 4

42%

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.

18%

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: B-Signals: 1

60%

Authentication Strength

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

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: BSignals: 1

65%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Iterant Public API to your agent

Capabilities

Start building with Iterant Public API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Iterant Public API

Jentic AI Readiness Score

Iterant Public 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