Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Reveula 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%2Freveula.com%2Freveula" | 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%2Freveula.com%2Freveula" | 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 Reveula API.
List the brands an API token can access, with name, handle, website, and role
List a brand's testimonial collection forms with title, slug, and publicUrl
Send testimonial invitations to a batch of recipients, each with a name and email, for one form
Read sent and skipped counts after each invite, including skippedUnsubscribed, skippedRecentlyCollected, and skippedFormPaused
Patterns agents use Reveula API for, with concrete tasks.
GET STARTED
★ AI agent that requests testimonials after a milestone
A developer wants their agent to ask happy customers for a testimonial when an order ships or a project closes, without handing it a token that can do more than send invites. Through Jentic the agent searches by intent, gets the triggerFormInvites operation with its input schema, and posts the recipient's name and email to one form, with the Reveula token injected at execution time. The response says whether the invite was sent or skipped.
Call GET /v1/brands/forms, pick the form titled 'Customer feedback', then call POST /v1/brands/forms/{formId}/invites with recipients [{name: 'Dana Fox', email: 'dana@example.com'}] and report the sent and skipped counts
Batch invitations from a CRM export
A small team exports recently closed customers from their CRM and wants each one asked for a testimonial. POST /v1/brands/forms/{formId}/invites accepts an array of recipients in one call, and Reveula skips people who unsubscribed, declined, were recently collected from, or already have an invite in flight. The returned counts show exactly how many invitations went out.
Post a recipients array of ten customers, each with name and email, to POST /v1/brands/forms/{formId}/invites and log sent, skippedUnsubscribed, and skippedRecentlyCollected from the response
Sharing the right collection form link
Support staff often want to drop a testimonial link into a ticket reply rather than trigger an email. GET /v1/brands/forms returns every collection form with its title, slug, and publicUrl, plus the owning brand, so an agent can look up the right public link for a brand and paste it into the reply.
Call GET /v1/brands/forms and return the publicUrl of the form whose slug is 'customer-feedback'
3 endpoints — the reveula api sends testimonial collection invitations from a brand's collection forms to a list of customers.
METHOD
PATH
DESCRIPTION
/v1/brands
List brands available to the token
/v1/brands/forms
List collection forms
/v1/brands/forms/{formId}/invites
Send testimonial invitations for a form
/v1/brands
List brands available to the token
/v1/brands/forms
List collection forms
/v1/brands/forms/{formId}/invites
Send testimonial invitations for a form
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Reveula by hand means sending its bearer token, looking up form ids from the forms list, and reading the sent and skipped counts in its success, status, message, and data envelope. Through Jentic you install once, import Reveula from the API Directory, store the token once, and your agent calls it.
Permission scoping
Reveula puts the form id in the URL path (/v1/brands/forms/{formId}/invites), so a rule can pin your agent to one collection form: it can send invites for that form and no other. The spec exposes only list and invite operations, so you decide whether the agent may send at all or only read the forms.
Credential isolation
Your Reveula API 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 'send a testimonial invitation' or 'list testimonial forms', and Jentic returns the matching Reveula operation with its input schema, including the recipients array shape, so the agent calls it without reading the docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Reveula API through Jentic.
What authentication does the Reveula API use?
The Reveula API authenticates with an HTTP bearer API token per its OpenAPI spec, sent as the Authorization header. Through Jentic the token is stored by your own Jentic One instance and attached at call time, so the agent never sees it.
Can I send testimonial invitations to several customers in one call?
Yes. POST /v1/brands/forms/{formId}/invites takes a required recipients array, and each recipient needs a name and an email. The response reports sent alongside skippedUnsubscribed, skippedDeclined, skippedRecentlyCollected, skippedInFlight, skippedUndelivered, and skippedFormPaused, so you can see why any invite did not go out.
What are the rate limits for the Reveula API?
The OpenAPI spec does not specify rate limits. Check the Reveula documentation at https://docs.reveula.com for current limits before sending large invite batches.
Is there a Reveula MCP server?
You don't need an MCP server to give your agent Reveula. Jentic connects it directly from the API Directory: import it, store your API token once, and your agent can list forms and send invites without another server's tool definitions sitting in its context.
How do I send a testimonial invite through Jentic?
Search Jentic for 'send a testimonial invitation', call GET /v1/brands/forms to find the form id, then execute POST /v1/brands/forms/{formId}/invites with the recipient's name and email. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I limit what my agent is allowed to do with the Reveula API?
Yes. Write a rule that allows POST /v1/brands/forms/{formId}/invites under the id of your 'Customer feedback' form only, plus GET /v1/brands/forms if the agent needs to look forms up. It can then invite customers to that one form and nothing else, and each call it makes is logged.
For Agents
List a Reveula brand's testimonial collection forms and send invitations to customers by name and email, with a per-call count of sent and skipped invites.
Use for: Send a testimonial request to customers who just completed onboarding, List all collection forms for my brand on Reveula, Get the public URL of the customer feedback form, Check how many testimonial invites were skipped because the customer unsubscribed
Not supported: Does not retrieve submitted testimonials, publish review widgets, or edit forms. Use for listing collection forms and sending testimonial invitations only.
The Reveula API sends testimonial collection invitations from a brand's collection forms to a list of customers. It lists the brands an API token can reach, with each brand's name, handle, website, and the caller's role, and lists the brand's collection forms with their title, slug, and publicUrl. A single invite call takes recipients with a name and email and reports how many invitations were sent and how many were skipped because the recipient unsubscribed, declined, was recently collected from, already had an invite in flight, or the form was paused.
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>