canonical: https://jentic.com/apis/brainshop.ai/brainshop

# Brainshop.ai API

Jentic publishes the only available OpenAPI specification for Brainshop.ai API, keeping it validated and agent-ready. Brainshop.ai is a chatbot platform that lets developers send a user message to a configured AI brain and receive a natural-language reply, with conversation context maintained per user identifier. The service is exposed through a single GET /get endpoint that takes a brain ID, API key, user ID, and message as query parameters. It suits lightweight chatbot integrations in messaging apps, support widgets, and prototype assistants where a hosted NLP brain is preferable to running a local model.

## For AI agents

Send a user message to a Brainshop AI brain and get back an intelligent text response, with conversation state tracked per user ID.

## Scope

Does not handle voice transcription, image generation, or model fine-tuning - use for sending text messages to a hosted chatbot brain only.

## Capabilities

- Send a user message to a Brainshop AI brain via GET /get and receive a generated reply
- Maintain per-user conversation context by passing a stable uid query parameter on each call
- Route messages to a specific brain configuration using the bid (brain ID) parameter
- Authenticate every request with an API key passed as the key query parameter
- Power chatbot widgets and messaging-app integrations with a single hosted endpoint

## Use cases

### Customer support chatbot widget

Embed a lightweight support assistant on a website by forwarding visitor messages to a Brainshop brain and rendering the reply in a chat bubble. Each visitor session uses a stable uid so the brain keeps multi-turn context across messages. This avoids hosting a local language model and keeps integration to a single GET request per turn.

Example prompt: Call GET /get with bid=178, key={API_KEY}, uid=visitor_42, msg=What are your business hours? and return the cnt field from the JSON response.

### Messaging-app conversational bot

Bridge a messaging platform like Telegram, Discord, or Slack to a Brainshop brain by forwarding inbound user messages to GET /get and posting the reply back to the channel. Using the platform user ID as uid preserves conversational state per person across sessions.

Example prompt: On every inbound message in Discord, call GET /get with bid={BRAIN_ID}, uid={discord_user_id}, msg={message_text} and post the reply text back to the channel.

### Prototype assistant for product validation

Stand up a working conversational prototype in hours rather than days by pointing a frontend at Brainshop instead of training or hosting a model. Useful for validating chatbot UX, scripting demo flows, or running internal pilots before committing to a full LLM stack.

Example prompt: Wire a React form input to GET /get with a fixed bid and uid, then display the returned cnt field below the input as the assistant reply.

### AI agent integration via Jentic

An agent that needs to ask a hosted conversational brain a question can discover Brainshop through Jentic search, load the schema for the sendMessage operation, and execute it without storing the API key in agent memory. Jentic handles credential isolation and parameter validation.

Example prompt: Through Jentic, search for 'send a message to a chatbot brain', load the sendMessage operation, and execute it with the brain ID and user message supplied by the caller.

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| GET | `/get` | Send a message to a Brainshop AI brain and receive an intelligent reply |

## Key resources

- **Messages** — Send a user message to a Brainshop brain via GET /get and receive the AI-generated reply in the cnt field of the JSON response.

## Why Jentic

- **Setup:** Wiring Brainshop by hand means passing your API key plus the bid and uid identifiers on the /get query and parsing the chatbot response yourself. Through Jentic you install once, import the Brainshop.ai API from the API Directory, store the key once, and your agent calls it.
- **Permission scoping:** Brainshop exposes a single message operation whose brain id, user id, and message travel in the query string rather than a resource path, so scope the agent to that one operation, sending a message to a brain, which is the only capability it needs. Every operation you allow is one you have explicitly chosen.
- **Credential handling:** Your Brainshop API key is stored once, encrypted, by your own Jentic One instance and injected as the key query parameter at execution time. It never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'send a message to a chatbot brain', and Jentic returns the Brainshop operation with its bid, uid, and msg input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Braze API** — Use Braze for multi-channel customer messaging campaigns alongside Brainshop's conversational replies
- **Breeze API** — Pair Breeze CRM with Brainshop to log conversational interactions back to a contact record
- **Breadcrumbs API** — Score leads in Breadcrumbs based on chatbot engagement captured through Brainshop

## FAQ

### Why is there no official OpenAPI spec for Brainshop.ai API?

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

The API uses a simple API key passed as the key query parameter on GET /get, alongside the brain ID (bid). Jentic stores the key in its credential vault and injects it at execution time, so the raw key is never exposed to agent prompts or logs.

### How do I keep conversation context across turns with the Brainshop.ai API?

Pass a stable uid query parameter on every call to GET /get. The brain associates messages with that uid to preserve dialogue state, so reuse the same uid for the same end user across turns and start a new uid for a new conversation.

### What are the rate limits for the Brainshop.ai API?

The OpenAPI spec does not declare rate limits. Brainshop applies per-brain limits tied to the plan attached to your bid; check your account at brainshop.ai for current quotas before high-volume use.

### How do I send a chatbot message with the Brainshop.ai API through Jentic?

Search Jentic for 'send a message to a chatbot brain', load the sendMessage operation, then execute with bid, uid, and msg. Install with pip install jentic and use the async pattern: await client.search, await client.load, await client.execute.

### Is the Brainshop.ai API free?

Brainshop.ai offers a free tier sufficient for prototyping with a single brain and limited daily traffic. Paid plans on brainshop.ai raise the request quota and unlock additional brain configurations.

### Can I limit what my agent is allowed to do with the Brainshop.ai API?

Yes. Jentic One is self-hosted, so you run the execution layer and your own rules decide which operations and credentials the agent may use. The Brainshop.ai API exposes a single operation, sending a message to a brain via GET /get with the bid, uid, and msg query parameters, so you scope the agent to just that one call and nothing else. Every operation the agent can reach is one you have explicitly allowed, and the API key stays under your control rather than in the agent's prompt.