Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the PitchYes 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%2Fpitchyes.com.br%2Fpitchyes" | 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%2Fpitchyes.com.br%2Fpitchyes" | 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 PitchYes API.
Trigger outbound AI phone calls directly or from a CRM assistant
Send calls with custom metadata attached
Search call history and retrieve a call by its id
Create, update, delete, and bulk-import contacts
Create, edit, list, and remove AI calling agents
GET STARTED
Patterns agents use PitchYes API for, with concrete tasks.
★ AI Agent Outbound Calling
An AI agent connected through Jentic can place a voice call to a contact and attach the context it should carry, without a human dialing. The agent searches for the send-call operation, PitchYes returns its input schema, and the agent submits the contact and metadata. This supports follow-up, reminder, and qualification call flows.
Place an outbound call to a contact and attach a campaign reference as metadata
Contact Management
Create and update the contacts PitchYes calls, delete ones that are no longer needed, and bulk-import a list to seed a campaign. This keeps the calling list current without manual data entry in a dashboard.
Create a contact and import a list of additional contacts
Call History Review
Search the record of placed calls and retrieve any single call by its id to inspect its outcome and metadata. An agent can reconcile what was called and when for reporting or follow-up decisions.
Search recent call history and retrieve one call by its id
Calling Agent Configuration
Create the AI agents that run PitchYes calls, edit their configuration, list the ones that exist, and remove agents that are retired. This lets an operations tool manage the roster of calling agents programmatically.
Create a calling agent and list all configured agents
14 endpoints — the pitchyes api places outbound ai phone calls and manages the contacts and agents behind them.
METHOD
PATH
DESCRIPTION
/calls/send
Send a call with metadata
/calls/crm/{assistantId}
Trigger a call from a CRM assistant
/calls/historico
Call history
/calls/get/{id}
Get a call by id
/contatos/criar
Create a contact
/contatos/lista
Import a contact list
/agent/create
Create a calling agent
/agent/getall
List all agents
/calls/send
Send a call with metadata
/calls/crm/{assistantId}
Trigger a call from a CRM assistant
/calls/historico
Call history
/calls/get/{id}
Get a call by id
/contatos/criar
Create a contact
/contatos/lista
Import a contact list
/agent/create
Create a calling agent
/agent/getall
List all agents
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the PitchYes API by hand means setting up JWT Bearer auth and mapping its call, contact, and agent operations yourself. Through Jentic you install once, import PitchYes from the API Directory, store the token once, and your agent calls it.
Permission scoping
PitchYes separates its read operations (call history and lookups) from write operations that place calls, change contacts, and manage agents, so a rule can hold your agent to the ones it needs. You choose the operations it may call, so placing a call or deleting a contact is not included unless you add it.
Credential isolation
Your PitchYes 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 'place an outbound call' or 'create a contact', and Jentic returns the matching PitchYes operation with its input schema so the agent calls the right endpoint without reading the docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using PitchYes API through Jentic.
What authentication does the PitchYes API use?
The PitchYes API authenticates with a JWT Bearer token per its OpenAPI spec: send it in the Authorization header. Through Jentic the token is stored encrypted by your own Jentic One instance and injected at call time, so it never reaches the agent's prompt or logs.
Can I place outbound calls with the PitchYes API?
Yes. Send a call with custom metadata, or trigger one from a CRM assistant by its id, then search the call history and retrieve any call by its id to check the outcome.
Is there a PitchYes MCP server?
You don't need an MCP server to give your agent the PitchYes API. Jentic connects it directly from the API Directory: import the API, store your token once, and your agent calls the call, contact, and agent endpoints it needs.
Can I limit what my agent is allowed to do with the PitchYes API?
Yes. Write a rule that allows only the call-history and lookup reads, so a reporting agent can review calls while placing new calls, editing contacts, and deleting agents stay out of reach, and every call it makes is logged.
What are the rate limits for the PitchYes API?
The OpenAPI spec does not specify rate limits. Check pitchyes.com.br or your account dashboard for the limits that apply to your plan.
How do I place a call with the PitchYes API through Jentic?
Search Jentic for an intent like 'place an outbound call', and it returns the PitchYes send-call operation with its input schema so your agent calls it with a contact and metadata. Your stored token is injected at call time. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Know of an official OpenAPI document? Contribute it →
For Agents
Place outbound AI phone calls, attach metadata, and review call history on PitchYes. Agents can also create and manage contacts and the AI calling agents that run the calls.
Use for: Place an outbound AI call to a contact, Send a call with custom metadata, Search the history of placed calls, Retrieve a call by its id
Not supported: Does not handle SMS, email, or live chat. Use for outbound AI voice calls and their contacts only.
The PitchYes API places outbound AI phone calls and manages the contacts and agents behind them. It triggers calls directly or from a CRM assistant, attaches custom metadata to each call, and records a searchable call history retrievable by id. Contact operations create, update, delete, and bulk-import contacts, while agent operations create, edit, list, and remove the AI agents that run the calls. It is a focused interface for voice outreach and the records it produces.
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>