canonical: https://jentic.com/apis/cloro.dev/cloro

# Cloro API

Jentic publishes the only available OpenAPI specification for Cloro API, keeping it validated and agent-ready. Cloro is a generative-AI brand monitoring service that tracks how a brand, product, or topic appears across answer engines and AI search interfaces - ChatGPT, Microsoft Copilot, Perplexity, Grok, Google Search, Gemini, Google AI Mode, and AI Overview. Each endpoint accepts a query and returns the answer engine's response so brand teams can measure presence, sentiment, and citation share. Authentication is a bearer token passed in the Authorization header.

## For AI agents

Query AI answer engines (ChatGPT, Copilot, Perplexity, Grok, Gemini, Google AI Mode/Overview) for brand monitoring and citation tracking via a single API surface.

## Scope

Does not handle traditional SEO rank tracking, paid ad analytics, or social media monitoring - use for AI answer engine and generative search visibility only.

## Capabilities

- Probe ChatGPT for a query and capture the model's response for brand presence analysis
- Run the same query across Copilot, Perplexity, Grok, and Gemini to compare answer engines
- Track brand mentions in Google Search, Google AI Mode, and Google AI Overview
- Compare citation sources returned by different generative search engines
- Schedule recurring AI search queries to detect brand mention drift over time
- Build a side-by-side answer engine matrix for share-of-voice reporting

## Use cases

### Generative Engine Optimisation Monitoring

Marketing teams now optimise for AI answer engines, not just traditional SERPs. POST /monitor/chatgpt, /monitor/perplexity, and /monitor/aioverview let an agent run the same brand or product query across each engine and compare answers, citations, and tone. The output feeds GEO dashboards in the same way rank trackers feed SEO dashboards.

Example prompt: Run the query 'best CRM for startups' against /monitor/chatgpt, /monitor/perplexity, and /monitor/aioverview and return whether 'HubSpot' appears in each response.

### Competitor Citation Tracking

Brand and PR teams need to know which competitors AI engines surface for category questions. By calling /monitor/copilot, /monitor/grok, and /monitor/gemini with a category prompt, an agent can extract the named brands and the sources cited, producing a weekly citation share report. This replaces manual prompt-and-screenshot workflows.

Example prompt: Query Copilot, Grok, and Gemini with 'top project management tools 2026' and return the ordered list of brands cited in each response.

### Crisis Detection Across AI Search

When negative coverage breaks, brand teams must know whether AI engines have ingested it. Running /monitor/aimode and /monitor/aioverview with crisis-related queries lets an agent detect when generative search starts surfacing a story and trigger downstream alerts to PR. The probe is non-destructive and can be scheduled hourly.

Example prompt: Every hour, query Google AI Mode and AI Overview with the brand name and a crisis keyword; flag responses where the crisis story is cited.

### AI Agent Brand Visibility Probe

Embed Cloro inside an AI assistant that gives marketers a one-line brand visibility score on demand. Through Jentic, the agent searches by intent, loads the right /monitor/{engine} schema, and probes the engines in parallel. The bearer token stays in your Jentic One instance so the model never receives the key.

Example prompt: Search Jentic for 'monitor brand on chatgpt', load the /monitor/chatgpt schema, and execute it with the user's brand keyword.

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | /monitor/chatgpt | Query ChatGPT and capture the response |
| POST | /monitor/perplexity | Query Perplexity and capture the response |
| POST | /monitor/copilot | Query Microsoft Copilot |
| POST | /monitor/gemini | Query Google Gemini |
| POST | /monitor/aioverview | Query Google AI Overview |
| POST | /monitor/aimode | Query Google AI Mode |
| POST | /monitor/grok | Query Grok |
| POST | /monitor/google | Query Google Search |

## Key resources

- **Monitoring** — Endpoints to query each supported AI answer engine and capture responses for analysis

## Why Jentic

- **Setup:** Wiring Cloro by hand means managing its bearer auth, mapping a monitor endpoint per answer engine, and handling retries yourself against api.cloro.dev/v1. Through Jentic you install once, import the Cloro API from the API Directory, store the token once, and your agent calls it.
- **Permission scoping:** Cloro puts the answer engine in the URL path (/monitor/{engine}), so a rule can pin your agent to one engine: it can run monitoring for that engine, such as Perplexity, and nothing else. You choose the operations it may call, so other engines are not included unless you add them.
- **Credential handling:** Your Cloro 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.
- **Discovery method:** Agents search Jentic by intent such as 'monitor brand visibility on Perplexity', and Jentic returns the matching /monitor/{engine} operation with its input schema, so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Closum API** — Marketing automation platform that can act on brand visibility signals captured from Cloro.
- **Close CRM API** — Sales CRM where Cloro signals can flag accounts with declining AI search presence.
- **Clockify API** — Time tracking for marketing teams running GEO and SEO programs.

## FAQ

### Why is there no official OpenAPI spec for Cloro API?

Cloro does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call Cloro 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 Cloro API use?

Cloro uses bearer token authentication. Pass your token in the Authorization header as 'Bearer <token>'. Through Jentic, the token is stored encrypted in your Jentic One instance and injected at execution time so agents never see the raw secret.

### Which AI answer engines can I monitor with the Cloro API?

Eight engines, each with its own POST endpoint: /monitor/chatgpt, /monitor/copilot, /monitor/perplexity, /monitor/grok, /monitor/google, /monitor/gemini, /monitor/aimode, and /monitor/aioverview. Send the same query to all eight to compare brand presence and citations.

### What are the rate limits for the Cloro API?

Rate limits are tied to your Cloro plan and are not encoded in the spec. Heavier monitoring loops should batch queries and respect any 429 responses with backoff. Jentic surfaces 429 errors back to the agent so it can pace requests.

### How do I run a multi-engine brand check through Jentic?

Run pip install jentic, search for 'cloro monitor chatgpt' (or any engine), load the schema, and execute with your query string. To compare engines, fan out search-load-execute calls across the eight monitor endpoints in parallel.

### Does the Cloro API return source citations?

Yes. The monitor responses include the answer engine's reply and, for engines that expose them, the cited sources. This lets you build citation-share reports rather than only mention counts.

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

Yes. Because Jentic One is self-hosted, you set the rules that decide which Cloro operations your agent may call and which credentials it may use. Cloro puts the answer engine in the URL path (/monitor/{engine}), so you can pin the agent to a single engine, letting it run monitoring for only /monitor/perplexity, for example, while /monitor/chatgpt, /monitor/gemini, and the other engines stay off limits unless you add them. Your bearer token is held by your own instance and injected only when an allowed operation runs, so the agent never calls an engine you have not authorized.