Install Jentic One Beta

Connect the Opteo API to your agent

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

List Opteo customer accounts linked to the calling agency

Read or update the monthly budget for a Google Ads customer

Configure the performance mode that drives Opteo's optimisation behaviour

Set or read performance goals such as target CPA or ROAS

Retrieve the active improvement suggestions Opteo has surfaced for an account

GET STARTED

Start building with Opteo API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Opteo API for, with concrete tasks.

★ Agency-wide budget syncing

PPC agencies running many client accounts can keep Opteo budgets in step with the source of truth in their finance system. A scheduled agent calls GET /customers to enumerate accounts and POST /customers/{customerId}/budget to push the latest monthly budget figures, so Opteo's optimisation guardrails always reflect what each client has actually approved.

GET /customers, then for each customerId POST /customers/{customerId}/budget with the monthly_budget value pulled from the finance system.

Goal-driven optimisation

When an account changes objective from cost-per-acquisition to return-on-ad-spend, the responsible analyst can update the Opteo performance goals via POST /customers/{customerId}/performance-goals so subsequent improvement suggestions align with the new target. The matching GET endpoint lets an agent read back the configuration before pushing further changes.

POST /customers/{customerId}/performance-goals with target_roas=4 and primary_metric=conversion_value to switch the account to ROAS-led optimisation.

Surfacing improvement suggestions

PPC managers reviewing their book can pull the queue of unaddressed Opteo suggestions across every account by calling GET /customers/{customerId}/improvements per account, then sort them by impact in their own dashboard. The /improvements/completed endpoint provides the matching record of decisions taken, which is useful for monthly reviews with clients.

Iterate over GET /customers/{customerId}/improvements for each managed account and surface the top three by estimated impact.

AI agent for paid search

Through Jentic, a paid-search assistant agent can answer 'what should I do this week' by calling GET /customers/{customerId}/improvements and summarising the top suggestions in plain language, with an option to drill into linking state via GET /customers/{customerId}/linking. The Opteo bearer token sits in your Jentic One instance, so the agent never handles the secret.

Search Jentic for 'list opteo improvements for a customer', execute GET /customers/{customerId}/improvements, and present the top suggestions to the user.

Key Endpoints

12 endpoints — jentic publishes the only available openapi specification for opteo api, keeping it validated and agent-ready.

METHOD

PATH

DESCRIPTION

GET

/customers

List managed customer accounts

GET

/customers/{customerId}/budget

Get a customer's monthly budget

POST

/customers/{customerId}/budget

Update a customer's monthly budget

POST

/customers/{customerId}/performance-goals

Update performance goals

GET

/customers/{customerId}/improvements

Get active improvements

GET

/customers/{customerId}/improvements/completed

Get completed improvements

GET

/customers

List managed customer accounts

GET

/customers/{customerId}/budget

Get a customer's monthly budget

POST

/customers/{customerId}/budget

Update a customer's monthly budget

POST

/customers/{customerId}/performance-goals

Update performance goals

GET

/customers/{customerId}/improvements

Get active improvements

GET

/customers/{customerId}/improvements/completed

Get completed improvements

Why Jentic?

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

Setup

Wiring the Opteo API by hand means sending its bearer token on every call and keeping the customer budget, performance-goal, and improvement routes straight yourself. Through Jentic you install once, import the Opteo API from the API Directory, store the token once, and your agent calls it.

Permission scoping

Opteo puts the customer id in the URL path (/customers/{customerId}/...), so a rule can pin your agent to one customer account: it can read that account's improvements and nothing else. You choose the operations it may call, so writes like setting a budget or a performance goal are not included unless you add them.

Credential isolation

Your Opteo bearer token is stored once, encrypted, by your own Jentic One instance and injected as the Authorization header at execution time. It never enters the agent's prompt, logs, or context.

Intent-based discovery

Agents search Jentic by intent such as 'list opteo customer accounts' or 'get opteo improvements', and Jentic returns the matching operation under /customers with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using Opteo API through Jentic.

Why is there no official OpenAPI spec for Opteo API?

Opteo does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call Opteo API via structured tooling. It is validated against the live API and kept up to date. Get started with Jentic One, the self-hosted execution layer.

What authentication does the Opteo API use?

Opteo uses an HTTP bearer token issued by the Opteo team. Through Jentic the token is stored encrypted in the vault and supplied as Authorization at execution time, so an agent never sees or stores the credential itself.

Can I push changes back to Google Ads through this API?

No. Opteo's API exposes Opteo's own configuration (budgets, performance goals, improvements) - it does not act as a write path into Google Ads. Changes you accept inside Opteo are applied to Google Ads through Opteo's own connection, not through this API.

What are the rate limits for the Opteo API?

The spec does not document fixed rate limits; these are governed by Opteo's commercial agreement with the calling agency. Treat 429 responses with backoff and ask the Opteo account team for ceilings before running large batch syncs.

How do I retrieve active improvements for a customer through Jentic?

Search Jentic for 'list opteo improvements for a customer', load GET /customers/{customerId}/improvements, and execute it with the customer ID. The vaulted bearer token is supplied automatically.

Can I update the budget for many customers in one call?

Not directly. POST /customers/{customerId}/budget operates on a single customer. Agencies typically iterate the call across the customers returned by GET /customers, which is straightforward to chain in a Jentic agent.

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

Yes. Because Opteo puts the customer id in the URL path (/customers/{customerId}/...), a rule in your self-hosted Jentic One instance can pin the agent to a single customer account, so it reads that account's improvements and touches nothing else. You decide which operations the agent may call, so read routes like GET /customers/{customerId}/improvements can be allowed while writes such as POST /customers/{customerId}/budget or POST /customers/{customerId}/performance-goals stay off unless you add them. Your own rules govern which endpoints and credentials the agent may use, so it can never reach an operation you have not granted.

Opteo API

AI ReadinessAI-Aware (B+)67/100

See full scorecard

Agent-ready OpenAPI document · curated by JenticMarketingAdvertisingbearer12 EndpointsREST

Know of an official OpenAPI document? Contribute it →

For Agents

Configure Opteo customer budgets, performance goals, and modes, and retrieve Google Ads improvement suggestions through 12 REST endpoints.

Use for: List all Google Ads accounts managed through Opteo, Get the active improvement suggestions for a specific customer, Update the monthly budget for a customer to 5,000 USD, I need to set a target CPA performance goal for an account

Not supported: Does not handle Google Ads writes, billing, or campaign creation - use for Opteo customer configuration and improvement retrieval only.

Jentic publishes the only available OpenAPI specification for Opteo API, keeping it validated and agent-ready. Opteo is a Google Ads optimisation platform that surfaces improvement suggestions, performance goals, and budget controls for paid-search accounts. The API exposes endpoints for managing customer accounts, configuring budgets and performance modes, setting goals, and retrieving active and completed improvement suggestions. Authentication is a bearer token issued by Opteo to each agency or in-house team.

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).

75%

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: DSignals: 4

31%

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.

57%

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).

100

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: A+Signals: 1

100%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Opteo API to your agent

Capabilities

Start building with Opteo API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Opteo API

Jentic AI Readiness Score

Opteo 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