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

# Pandorabots AIaaS

The Pandorabots AIaaS API creates and runs AIML chatbots, so an application can hold a conversation with a bot and manage the files that define its responses. You send a message to a bot and receive its reply, and you can create a bot, upload the AIML, set, map, and substitution files that make up its knowledge, compile it, and list or delete those files. Bots are organised under an application, and each request names the application and the bot it targets. A separate debug talk endpoint returns extra detail about how a reply was produced.

## For AI agents

Send messages to a Pandorabots chatbot and receive replies, create bots, upload the AIML and related files that define them, compile them, and list or delete bot files. Authenticates with an API key passed as the user_key query parameter alongside the application id.

## Scope

Does not handle account billing, model training beyond AIML, or analytics. Use for talking to Pandorabots bots and managing their files only.

## Capabilities

- Send a message to a chatbot and receive its reply
- List the chatbots that belong to an application
- Create a chatbot and compile it before use
- Upload the AIML, set, map, and substitution files that define a bot
- Retrieve or delete a bot's files
- Debug a bot conversation to see how a reply was produced

## Use cases

### Agent-Driven Chatbot Conversations

An AI agent connected through Jentic sends a user's message to a Pandorabots bot and returns the reply, so the bot's scripted responses can be surfaced inside a larger agent workflow. The agent names the application and bot on each call and passes the message text to receive an answer.

Example prompt: Send the user's question to my support bot and return the bot's reply

### Bot Authoring and Deployment

A tool builds a chatbot by creating it, uploading the AIML and related files that define its responses, and compiling it so it is ready to answer. The workflow lists a bot's files to check what is deployed and replaces individual files as the bot's script changes.

Example prompt: Create a bot named 'greeter', upload its AIML file, and compile it so it is ready to talk

### Conversation Debugging

A developer uses the debug talk endpoint to see how a bot arrived at a particular reply, so they can trace which pattern matched and adjust the underlying files. This shortens the loop between editing a bot's AIML and understanding its behaviour.

Example prompt: Run the message through the debug endpoint and show which pattern the bot matched

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/atalk/{app_id}/{botname}` | Talk to a bot |
| GET | `/bot/{app_id}` | List of bots |
| PUT | `/bot/{app_id}/{botname}` | Create a bot |
| GET | `/bot/{app_id}/{botname}/verify` | Compile a bot |
| PUT | `/bot/{app_id}/{botname}/{file-kind}/{filename}` | Upload a bot file |
| GET | `/bot/{app_id}/{botname}` | List of bot files |

## Key resources

- **Bots** — The chatbots that hold conversations, each created and compiled under an application
- **Bot files** — The AIML, set, map, and substitution files that define a bot's responses
- **Applications** — The account-level container that groups a set of bots under an application id

## AI readiness

This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.

- **Score:** 49 / 100
- **Maturity:** Foundational
- **Dimensions:**
  - Foundational Compliance: 100 / 100
  - Developer Experience & Jentic Compatibility: 56 / 100
  - AI-Readiness & Agent Experience: 56 / 100
  - Agent Usability: 94 / 100
  - Security: 15 / 100
  - AI Discoverability: 100 / 100
- **View full report:** https://jentic.com/apis/pandorabots.com/pandorabots/scorecard
- **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/
- **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview

### Score it yourself

Every API in the directory is allowlisted, so you can re-score it with no key required.

- **Score your own API:** https://jentic.com/scorecard.md
- **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md

```sh
npx @jentic/api-scorecard-cli score <openapi-url>
```

## Why Jentic

- **Setup:** Wiring the Pandorabots AIaaS API by hand means passing the application id and bot name on every path, keeping the API key on each query, and compiling a bot after each file change. Through Jentic you install once, import Pandorabots from the API Directory, store the key once, and your agent calls it.
- **Permission scoping:** Pandorabots puts the application id and bot name in the URL path, so a rule can pin your agent to one bot: it can hold conversations and read that bot's files and nothing else. You choose the operations it may call, so deleting files or bots is left out unless you add it.
- **Credential handling:** Your Pandorabots application id and API key are stored once, encrypted, by your own Jentic One instance and injected at execution time. They never enter the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'send a message to a bot' or 'upload an AIML file', and Jentic returns the matching Pandorabots operation with its input schema so the agent calls the right endpoint without reading the reference docs.

## Related APIs

- **OpenAI API** — Large language models for chat completion and text generation
- **Hugging Face API** — Hosted inference for open models across text, vision, and audio tasks

## FAQ

### Is there a Pandorabots MCP server?

You don't need an MCP server to give your agent the Pandorabots AIaaS API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent can talk to bots and manage their files straight away, with no extra server to run and no tool definitions to load into the agent's context.

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

Yes. Because Pandorabots puts the application id and bot name in the URL path, you can write a rule that pins your agent to one bot, so it can hold conversations with that bot and touch no others, and every call it makes is logged. You also choose which operations it may call, so file deletion need not be included.

### What authentication does the Pandorabots AIaaS API use?

The Pandorabots AIaaS API authenticates with an API key passed as the user_key query parameter, together with your application id, per its OpenAPI spec. Through Jentic the key is stored encrypted by your own instance and added to each request at call time, so it never appears in the agent's prompt or logs.

### Can I upload AIML files to a bot with the Pandorabots AIaaS API?

Yes. The API uploads the AIML, set, map, and substitution files that define a bot's responses, and it compiles the bot so the changes take effect. You can also list and delete a bot's files, so an agent can manage the knowledge behind a bot end to end.

### What are the rate limits for the Pandorabots AIaaS API?

The OpenAPI spec does not specify rate limits for the Pandorabots AIaaS API. For current limits and plan details, see the Pandorabots documentation at https://www.pandorabots.com/docs/.

### How do I talk to a Pandorabots bot through Jentic?

Import the Pandorabots AIaaS API from the Jentic API Directory, then have your agent issue a request such as 'send this message to my support bot'. Jentic matches the intent to the talk operation and returns its input schema so the agent builds the correct request, with your stored key injected at call time. To run it on your own infrastructure, install Jentic One from its GitHub repo.