canonical: https://jentic.com/apis/tiliter.com/tiliter

# Tiliter Vision AI - Agent API

AI-powered vision analysis API for retail and industrial applications. Supports multiple agents for cleanliness scoring, damage detection, label reading, object counting, and more. The API exposes 1 endpoints secured with apiKey authentication.

## For AI agents

Programmatically execute ai vision agent. Covers 1 operations with apiKey authentication.

## Scope

Does not handle payments, communications, or developer tools - use for crm only.

## Capabilities

- Execute AI vision agent
- Manage crm data programmatically
- Integrate Tiliter Vision AI - Agent API into automated workflows
- Query and filter Tiliter Vision AI - Agent API records by parameters
- Monitor Tiliter Vision AI - Agent API operational status and events

## Use cases

### CRM Operations

Use the Tiliter Vision AI - Agent API to perform crm operations programmatically. The API provides 1 endpoints covering core functionality including execute ai vision agent.

Example prompt: Call POST `/api/v1/inference/{agent_code}` to execute ai vision agent

### Data Retrieval and Monitoring

Query Tiliter Vision AI - Agent API resources on a schedule to track changes, generate alerts, or feed downstream dashboards. Agents poll relevant endpoints, compare against previous state, and trigger actions when thresholds are crossed.

Example prompt: Poll the primary Tiliter Vision AI - Agent API endpoint, compare response to last known state, and alert if changed

### AI Agent Integration via Jentic

AI agents discover and call Tiliter Vision AI - Agent API endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle apiKey tokens manually.

Example prompt: Search Jentic for 'execute ai vision agent', load the operation schema, and execute with Jentic-managed credentials

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/api/v1/inference/{agent_code}` | Execute AI vision agent |

## Key resources

- **Inference** — Operations related to Inference

## Why Jentic

- **Setup:** Wiring the Tiliter Vision AI - Agent API by hand means setting up its X-API-Key header and building the request handling around a single inference call yourself. Through Jentic you install once, import the Tiliter Vision AI - Agent API from the API Directory, store the API key once, and your agent calls it.
- **Permission scoping:** This API exposes one operation, POST `/api/v1/inference/{agent_code}`, with the agent code in the URL path, so a rule can pin your agent to one Tiliter vision agent and nothing else. There are no other operations to grant unless you add other APIs.
- **Credential handling:** Your Tiliter Vision 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.
- **Discovery method:** Agents search Jentic by intent such as 'run a vision inference for an agent', and Jentic returns the matching Tiliter Vision AI - Agent API operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Hubspot** — Alternative crm API
- **Salesforce** — Alternative crm API
- **Pipedrive** — Complementary crm API
- **Zoho** — Complementary crm API

## FAQ

### What authentication does the Tiliter Vision AI - Agent API use?

The Tiliter Vision AI - Agent API uses an API key passed in the `X-API-Key` header. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.

### Can I execute ai vision agent with the Tiliter Vision AI - Agent API?

Yes. Use the POST `/api/v1/inference/{agent_code}` endpoint. The API returns structured JSON responses that agents can parse and act on directly.

### What are the rate limits for the Tiliter Vision AI - Agent API?

Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.

### How do I execute ai vision agent through Jentic?

Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'execute ai vision agent'. Jentic returns the matching Tiliter Vision AI - Agent API operation with its input schema. Load the schema and execute the call - credentials are injected automatically.

### How many endpoints does the Tiliter Vision AI - Agent API have?

The Tiliter Vision AI - Agent API exposes 1 endpoints covering inference operations.

### Can I limit what my agent is allowed to do with the Tiliter Vision AI API?

Yes. Because Jentic One is self-hosted, you set the rules that decide which operations and credentials your agent may use. The Tiliter Vision AI API exposes a single operation, POST `/api/v1/inference/{agent_code}`, with the vision agent identified by the agent_code in the URL path, so your rule can pin your agent to one specific Tiliter vision agent and nothing else. Your Tiliter API key is stored encrypted by your own instance and injected only at execution time, so the agent can call the inference endpoint you allow without ever seeing the raw key.