Install Jentic One Beta

Connect the Presenton AI API to your agent

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

Generate complete slide presentations from natural language prompts or topic descriptions

Create presentations from structured JSON data with precise content control

Generate presentation outlines before committing to full deck creation

Export finished presentations in downloadable formats

Browse and preview smart design layouts and standard templates

GET STARTED

Start building with Presenton AI API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Presenton AI API for, with concrete tasks.

★ Automated Report Presentations

Generate polished slide decks from structured data outputs like quarterly reports, analytics summaries, or project status updates. The Presenton API accepts JSON-formatted content with slide structure definitions and produces professionally designed presentations using AI-powered layout selection. This eliminates the manual work of formatting data into slides while maintaining consistent visual quality across recurring report cycles.

Submit a JSON payload with 5 slides of quarterly metrics data to the /api/v3/presentation/from-json endpoint and export the generated presentation

AI-Powered Pitch Deck Generation

Create investor pitch decks or sales presentations by describing the topic and letting the AI handle slide structure, content expansion, and visual design. Presenton generates outlines first via the outline endpoint, allowing review before full generation. The async generation path with webhooks enables handling complex decks that take longer to produce without blocking the calling application.

Generate an outline via /api/v3/presentation/outlines/generate for a startup pitch deck, then trigger async full generation via /api/v3/presentation/generate/async and poll status until complete

Template-Based Content Production

Produce consistent branded presentations using standard templates that define visual styles, layouts, and structure. Browse available templates via the API, preview examples, and generate presentations that conform to a chosen template style. This is suited for organizations that need volume presentation production with consistent branding without per-deck design effort.

List all standard templates via /api/v3/standard-template/all, retrieve an example for a chosen template using /api/v3/standard-template/{id}/example, then generate a presentation using that template

AI Agent Presentation Pipeline

AI agents use Presenton through Jentic to generate presentations as part of larger content production workflows. An agent can search for presentation generation operations, upload supporting images, generate outlines for review, and produce final decks - all through structured API calls without manual design work. Webhook integration allows agents to handle async generation as background tasks.

Search Jentic for 'generate presentation from prompt', load the presentation/generate operation schema, and execute with a topic description to produce a complete slide deck

Key Endpoints

20 endpoints — presenton ai generates complete slide presentations from text prompts, uploaded files, or structured json input.

METHOD

PATH

DESCRIPTION

POST

/api/v3/presentation/generate

Generate a presentation from a text prompt

POST

/api/v3/presentation/generate/async

Generate a presentation asynchronously

POST

/api/v3/presentation/outlines/generate

Generate a presentation outline

POST

/api/v3/presentation/from-json

Create presentation from structured JSON

POST

/api/v3/presentation/export

Export a presentation to downloadable format

GET

/api/v3/async-task/status/{id}

Check async generation task status

GET

/api/v3/standard-template/all

List all standard templates

POST

/api/v3/webhook/subscribe

Subscribe to generation event webhooks

POST

/api/v3/presentation/generate

Generate a presentation from a text prompt

POST

/api/v3/presentation/generate/async

Generate a presentation asynchronously

POST

/api/v3/presentation/outlines/generate

Generate a presentation outline

POST

/api/v3/presentation/from-json

Create presentation from structured JSON

POST

/api/v3/presentation/export

Export a presentation to downloadable format

GET

/api/v3/async-task/status/{id}

Check async generation task status

GET

/api/v3/standard-template/all

List all standard templates

POST

Why Jentic?

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

Setup

Wiring the Presenton AI API by hand means putting your sk-presenton token in a bearer Authorization header against api.presenton.ai and polling async task status for generated decks yourself. Through Jentic you install once, import the Presenton AI API from the API Directory, store the bearer token once, and your agent calls it.

Permission scoping

Presenton takes the prompt and slide content in the request body and returns a task id you poll, so scoping is by operation: you limit the agent to the operations it needs, such as generating a presentation or checking task status. Exporting a deck or subscribing a webhook is included only if you add those operations.

Credential isolation

Your Presenton 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 'generate a slide presentation from a topic' or 'check the status of a generation task', and Jentic returns the matching Presenton operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using Presenton AI API through Jentic.

What authentication does the Presenton AI API use?

The Presenton AI API uses Bearer token authentication with API keys in the format sk-presenton-xxxxxxxx or JWT tokens. Through Jentic, your Presenton credentials are stored encrypted in your Jentic One instance and agents receive scoped Bearer tokens automatically.

Can I generate a presentation from structured JSON data?

Yes. The POST /api/v3/presentation/from-json endpoint accepts a JSON payload defining slide content, structure, and layout preferences. This gives precise control over what appears on each slide, unlike the prompt-based generation which lets the AI determine content structure.

How do I track the progress of an async presentation generation?

Use POST /api/v3/presentation/generate/async to start generation, which returns a task ID. Poll GET /api/v3/async-task/status/{id} to check progress. Alternatively, subscribe to webhooks via POST /api/v3/webhook/subscribe to receive notifications when generation completes.

What are the rate limits for the Presenton AI API?

Rate limits depend on your Presenton subscription tier. The async generation endpoints are designed for heavier workloads - use them instead of synchronous generation when producing multiple presentations. Monitor HTTP 429 responses to detect throttling.

How do I generate a presentation through Jentic?

Install the SDK with pip install jentic, set your JENTIC_AGENT_API_KEY, then search for 'generate presentation from prompt'. Jentic returns the presentation/generate operation with its schema. Execute with a topic description to produce a complete deck. For structured input, search for 'create presentation from JSON data' instead.

Can I preview templates before using them?

Yes. List all templates with GET /api/v3/standard-template/all, then retrieve a rendered example of any template using GET /api/v3/standard-template/{id}/example. Smart design layouts are also browsable via GET /api/v3/smart-design/all.

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

Yes. Because you run Jentic One yourself, your own rules decide which Presenton operations the agent may call, so scoping is done per operation. You can allow only what the task needs, such as generating a presentation or checking async task status, while leaving out exporting a deck or subscribing a webhook. Those operations are available to the agent only if you add them.

Presenton AI API

Name: Presenton AI API
Brand: Presenton AI API
Availability: InStock

AI ReadinessAI-Aware (B+)68/100

See full scorecard

Official vendor OpenAPI document · agent-readyAI/MLLanguage Modelsbearer20 EndpointsREST

For Agents

Generate complete slide presentations from text prompts or structured data, browse templates, manage images, and export finished decks.

Use for: I need to generate a presentation from a text prompt, I want to create slides from structured JSON data, Generate an outline for a presentation on a given topic, List all available presentation templates

Not supported: Does not handle video creation, document editing, or collaborative real-time slide editing - use for one-shot presentation generation and export only.

Presenton AI generates complete slide presentations from text prompts, uploaded files, or structured JSON input. The API provides 20 endpoints covering presentation generation (synchronous and asynchronous), outline creation, template browsing, image management, file uploads, export functionality, and webhook subscriptions for tracking generation progress. It supports both smart AI-designed layouts and standard templates with customizable styling.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

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).

21%

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

72%

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.

50%

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

71%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Presenton AI API to your agent

Capabilities

Start building with Presenton AI API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Presenton AI API

Jentic AI Readiness Score

Presenton 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