Install Jentic One Beta

Connect the publishwith.ai API to your agent

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

Publish a static artifact from index.html or index.md files, or a dynamic one from a YAML manifest and Liquid templates

Republish an artifact by name, resolving a VERSION_CHANGED conflict with the confirmation_token from the 409 response

Full-text search and list artifacts in your tenant, and fetch an artifact's raw source files by version

Share an artifact with a tenant user, group, audience, or external email at view, edit, or own access, with an expiring link for external recipients

GET STARTED

Start building with publishwith.ai API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use publishwith.ai API for, with concrete tasks.

★ Agent-published reports

An AI agent that writes an analysis can publish it straight to publishwith.ai as an index.md file, which the service renders to a styled page, and then share the result with the person who asked for it. Because publish is idempotent by the name-derived slug, the agent re-running the same report updates the page rather than creating a duplicate, and a 409 VERSION_CHANGED response protects a newer edit by someone else.

Publish an artifact named 'Weekly Churn Report' in static mode with files containing index.md, then share it with principal priya@example.com at view access

Data-backed dynamic dashboards

Teams that want a dashboard to stay current publish in dynamic mode: a YAML manifest defines the data and Liquid templates render it server-side. The generic call endpoint also exposes actions such as list_tables and execute_sql, so an agent can inspect the available data before writing the manifest.

Call the action list_tables through the generic call endpoint, then publish an artifact named 'Pipeline Dashboard' with mode dynamic, a manifest, and templates

Controlled sharing with outside reviewers

When a report must go to a client, the share operation grants one principal at a time. Internal users open the canonical in-app URL, while an external email receives a tokenized, expiring link capped at view access, so reviewers outside the tenant can read a report but cannot edit or own it. Sharing never changes the artifact's document-wide visibility.

Share the artifact with slug q3-board-pack with external email client@example.org at view access with ttl_days 7

Key Endpoints

9 endpoints — the publishwith.

METHOD

PATH

DESCRIPTION

POST

/api/v1/publish

Publish or update an artifact

GET

/api/v1/artifacts

List artifacts in your tenant

GET

/api/v1/search

Full-text search across artifacts

GET

/api/v1/artifacts/{slug}/source

Get an artifact's source files

POST

/api/v1/artifacts/{slug}/share

Share an artifact with a principal

GET

/api/v1/people

Resolve a person in your directory

POST

/api/v1/call

Invoke any publishwith.ai action

POST

/api/v1/publish

Publish or update an artifact

GET

/api/v1/artifacts

List artifacts in your tenant

GET

/api/v1/search

Full-text search across artifacts

GET

/api/v1/artifacts/{slug}/source

Get an artifact's source files

POST

/api/v1/artifacts/{slug}/share

Share an artifact with a principal

GET

/api/v1/people

Resolve a person in your directory

POST

/api/v1/call

Invoke any publishwith.ai action

Why Jentic?

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

Setup

Wiring publishwith.ai by hand means creating a personal API key for its Bearer auth, handling 409 VERSION_CHANGED retries with a confirmation token, and choosing between typed endpoints and the generic action call. Through Jentic you install once, import publishwith.ai from the API Directory, store the key once, and your agent calls it.

Permission scoping

The typed publishwith.ai operations put the artifact slug in the URL path (/api/v1/artifacts/{slug}/...), so a rule can pin your agent to one artifact for source reads and sharing. The generic /api/v1/call endpoint carries its action in the request body, so allowing it allows every action; you choose the operations the agent may call, and that endpoint is not included unless you add it.

Credential isolation

Your publishwith.ai 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 'publish a report as a web page' or 'share a dashboard with a colleague', and Jentic returns the matching publishwith.ai operation with its input schema so the agent calls the right endpoint without reading the reference docs.

FAQs

Specific to using publishwith.ai API through Jentic.

What authentication does the publishwith.ai API use?

The publishwith.ai API authenticates with a Bearer token in the Authorization header, using a personal API key generated from Connect, per its OpenAPI spec. Enterprise workspaces may restrict or disable key creation. The file upload operation is the exception: it is authenticated by the upload token in its path and needs no Bearer header. Through Jentic the API key is stored once and injected at call time, so it never appears in your agent's prompt or logs.

What is the difference between static and dynamic publishing in publishwith.ai?

Static mode uploads files, with index.html as HTML or index.md as Markdown that is auto-rendered to a styled page. Dynamic mode supplies a YAML manifest and Liquid templates that the service renders server-side. Both go through POST /api/v1/publish and are idempotent by the slug derived from the artifact name.

What are the rate limits for the publishwith.ai API?

The OpenAPI spec does not specify rate limits for the publishwith.ai API. Check https://publishwith.ai for current limits on your workspace.

How do I publish a report with the publishwith.ai API through Jentic?

Search Jentic for 'publish a report as a web page', which returns POST /api/v1/publish with its input schema, then send a name and files with an index.md or index.html. If it returns 409 VERSION_CHANGED, re-send with the confirmation_token to overwrite deliberately. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Is there a publishwith.ai MCP server?

You don't need an MCP server to give your agent the publishwith.ai API. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls it, discovering the publish, search, and share operations by intent rather than holding their tool definitions in context.

Can I limit what my agent is allowed to do with the publishwith.ai API?

Yes. Write a rule that allows only POST /api/v1/publish, GET /api/v1/search, and GET /api/v1/artifacts, so the agent can publish and find reports but cannot share them or reach actions like delete_artifact, and every call it makes is logged. Leave POST /api/v1/call out of the rule, since that one endpoint carries every action in its request body.

publishwith.ai API

AI ReadinessAI-Aware (B+)69/100

See full scorecard

Official vendor OpenAPI document · agent-readyMarketingContent Managementbearer9 EndpointsREST

For Agents

Publish an HTML or Markdown report as a governed artifact, update it by name, search and list artifacts, and share one with a person, group, or external email at view, edit, or own access. A generic action call reaches the rest of the action set.

Use for: Publish this Markdown report as a page my team can open, Share the Q3 dashboard with priya@example.com as a viewer, Search for artifacts that mention churn, Find the person named Alex Chen in our directory

Not supported: Does not handle report generation from raw prompts, public website hosting on your own domain, or email delivery campaigns. Use for publishing, finding, and sharing governed reports and dashboards in a publishwith.ai workspace only.

The publishwith.ai API publishes AI-generated reports and dashboards as governed HTML artifacts inside your workspace and controls who can see them. A static artifact is uploaded as HTML or Markdown files, while a dynamic one is rendered server-side from a YAML manifest and Liquid templates. You can then search artifacts, fetch their source for editing, and share them with a tenant user, group, audience, or external email at view, edit, or own access. A generic action endpoint exposes the complete action set, including SQL execution and access management.

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

98%

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: BSignals: 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: C-Signals: 4

52%

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.

55%

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: A-Signals: 1

74%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the publishwith.ai API to your agent

Capabilities

Start building with publishwith.ai API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

publishwith.ai API

Jentic AI Readiness Score

publishwith.ai 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