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

# ThoughtfulGPT API

ThoughtfulGPT API for AI-powered content generation and analysis. The API exposes 8 endpoints secured with apiKey authentication.

## For AI agents

Programmatically create completion, stream completion. Covers 8 operations with apiKey authentication.

## Scope

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

## Capabilities

- Create Completion
- Stream Completion
- Analyze Sentiment
- Summarize Text
- List Projects
- Get Project

## Use cases

### Developer Tools Operations

Use the ThoughtfulGPT API to perform developer tools operations programmatically. The API provides 8 endpoints covering core functionality including create completion, stream completion, analyze sentiment.

Example prompt: Call POST /completions to create completion

### Automated Completions Management

Automate completions operations by combining multiple ThoughtfulGPT API endpoints. Agents can stream completion and then analyze sentiment in a single workflow.

Example prompt: Call POST `/completions/stream` to stream completion, then verify the result

### AI Agent Integration via Jentic

AI agents discover and call ThoughtfulGPT 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 'create completion', load the operation schema, and execute with Jentic-managed credentials

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/completions` | Create Completion |
| POST | `/completions/stream` | Stream Completion |
| POST | `/analysis/sentiment` | Analyze Sentiment |
| POST | `/analysis/summarize` | Summarize Text |
| POST | `/projects` | Create Project |
| GET | `/projects` | List Projects |
| GET | `/projects/{projectId}` | Get Project |
| DELETE | `/projects/{projectId}` | Delete Project |

## Key resources

- **Completions** — Text completion operations
- **Analysis** — Content analysis
- **Projects** — Project management

## Why Jentic

- **Setup:** Wiring the ThoughtfulGPT API by hand means passing its X-API-Key header on every request, handling streaming completions, and coding your own retries. Through Jentic you install once, import the ThoughtfulGPT API from the API Directory, store the key once, and your agent calls it.
- **Permission scoping:** The ThoughtfulGPT API puts the project id in the URL path (`/projects/{projectId}`), so a rule can pin your agent to one project: it can read that project and nothing else. You choose the operations it may call, so writes like deleting a project are not included unless you add them.
- **Credential handling:** Your ThoughtfulGPT 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 'summarize a document' or 'analyze sentiment', and Jentic returns the matching ThoughtfulGPT operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Github** — Alternative developer tools API
- **Gitlab** — Alternative developer tools API

## FAQ

### What authentication does the ThoughtfulGPT API use?

The ThoughtfulGPT 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 create completion with the ThoughtfulGPT API?

Yes. Use the POST /completions endpoint. The API returns structured JSON responses that agents can parse and act on directly.

### What are the rate limits for the ThoughtfulGPT 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 create completion through Jentic?

Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'create completion'. Jentic returns the matching ThoughtfulGPT API operation with its input schema. Load the schema and execute the call - credentials are injected automatically.

### How many endpoints does the ThoughtfulGPT API have?

The ThoughtfulGPT API exposes 8 endpoints covering completions, analysis, projects operations.

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

Yes. Jentic One is self-hosted, so your own rules decide which ThoughtfulGPT operations and credentials the agent may use. Because the project id sits in the URL path (`/projects/{projectId}`), you can pin the agent to a single project so it reads only that project and nothing else. You pick the operations it may call, so a destructive action like deleting a project stays off the list unless you add it.