Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Alai 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%2Fgetalai.com%2Fgetalai" | shStep 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%2Fgetalai.com%2Fgetalai" | sh
jentic register # connects your agent to your Jentic One instanceJentic 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.
What an agent can do with Alai API.
Generate a full presentation from a prompt with a chosen theme and vibe
Add a slide to or delete a slide from an existing presentation
Export a presentation to a downloadable file
Produce per-slide speaker transcripts for a presentation
Upload images and assets for use in presentations
GET STARTED
List the themes, vibes, design systems, and models available
Edit a Modern presentation and poll the resulting operation
Patterns agents use Alai API for, with concrete tasks.
★ Agent-Generated Presentations
An AI agent asked to produce a slide deck can call the Alai API through Jentic to generate a full presentation from a prompt, pick a theme and vibe, and export the result to a file. The agent drives generation and export without the developer wiring the bearer auth or the generation-status polling by hand. Jentic returns the matching operation and its input schema so the agent generates the deck inline.
Generate a presentation on a given topic with a chosen theme, wait for it to finish, and export it to a file
Programmatic Deck Assembly
A tool that builds decks from structured content can create a presentation and then add slides one at a time, uploading any images it needs along the way. Alai accepts slide additions and image uploads against a presentation and exports the assembled deck, so an application can turn a content outline into a finished presentation.
Create a presentation, add a slide for each section of an outline, upload the matching images, and export the deck
Speaker Notes and Export
A workflow preparing a talk can generate speaker transcripts for every slide and then export the deck for the presenter. The Alai API produces per-slide transcripts for a presentation and exports it to a downloadable file, so a presenter gets both the slides and the notes to read alongside them.
Generate per-slide transcripts for a presentation and export the deck to a file
25 endpoints — the alai api generates and manages presentations across its classic and modern presentation engines.
METHOD
PATH
DESCRIPTION
/api/v1/generations
Generate a presentation
/api/v1/presentations
List all presentations
/api/v1/presentations/{presentation_id}/slides
Add a slide to a presentation
/api/v1/presentations/{presentation_id}/exports
Export a presentation
/api/v1/presentations/{presentation_id}/transcripts
Generate slide transcripts
/api/modern/v1/presentations/{presentation_id}/generate
Generate a Modern presentation
/api/modern/v1/presentations/{presentation_id}/edits
Edit a Modern presentation
/api/v1/generations
Generate a presentation
/api/v1/presentations
List all presentations
/api/v1/presentations/{presentation_id}/slides
Add a slide to a presentation
/api/v1/presentations/{presentation_id}/exports
Export a presentation
/api/v1/presentations/{presentation_id}/transcripts
Generate slide transcripts
/api/modern/v1/presentations/{presentation_id}/generate
Generate a Modern presentation
/api/modern/v1/presentations/{presentation_id}/edits
Edit a Modern presentation
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Alai by hand means handling its bearer API key, choosing between the Classic and Modern presentation engines, and polling the generation status or operation endpoints until a deck is ready to export. Through Jentic you install once, import Alai from the API Directory, store the key once, and your agent calls it.
Permission scoping
Alai puts the presentation id in the URL path, so a rule can pin your agent to one presentation and the operations you pick on it. You choose which operations it may call, so slide and presentation deletion are not included unless you add them.
Credential isolation
Your Alai 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 'generate a presentation' or 'export a deck', and Jentic returns the matching Alai operation with its input schema so the agent calls the right endpoint directly.
Alternatives and complements available in the Jentic catalogue.
Specific to using Alai API through Jentic.
What authentication does the Alai API use?
The Alai API authenticates with a bearer API key on every operation, per its OpenAPI spec. Through Jentic the key is stored once, encrypted, by your own Jentic One instance and injected at call time, so it never reaches the agent's prompt or logs.
Is there an Alai MCP server?
You don't need an MCP server to give your agent the Alai API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent can generate and export presentations straight away.
Can I limit what my agent is allowed to do with the Alai API?
Yes. Alai puts the presentation id in the URL path, so a rule can bound your agent to one presentation and the operations you pick on it. Allow it to generate, add slides, and export but leave slide and presentation deletion out unless you add them, and every call it makes is logged.
Can I generate a presentation from a prompt with the Alai API?
Yes. The generation operation takes a prompt along with a theme and vibe and produces a full presentation, and a status operation lets an agent poll until the generation finishes before it exports the deck.
What are the rate limits for the Alai API?
The OpenAPI spec does not publish a numeric rate limit for the Alai API. Check the Alai documentation at docs.getalai.com for the current limits on your plan.
How do I generate a presentation with the Alai API through Jentic?
Search Jentic for an intent like 'generate a presentation from a prompt' and it returns the Alai generation operation with its input schema, so your agent submits the prompt and exports the finished deck. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Generate presentations from a prompt, add or remove slides, upload images, export the deck, and produce slide transcripts across Alai's Classic and Modern presentation engines. Authenticates with a bearer API key.
Use for: Generate a presentation about a given topic, Add a slide to an existing presentation, Export a presentation to a file, List the themes available for a presentation
Not supported: Does not handle video rendering, live presenting, or team billing. Use for generating and managing presentations only.
The Alai API generates and manages presentations across its Classic and Modern presentation engines. An agent generates a deck from a prompt with a chosen theme and vibe, then lists presentations, adds or deletes individual slides, uploads images and assets, and exports the finished deck to a file. The Modern engine adds design systems, model selection, presentation edits, and long-running operations an agent can poll or cancel, and both engines can produce per-slide speaker transcripts. Responses are JSON and authentication is a bearer API key.
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.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>