> For the complete documentation index, see [llms.txt](https://docs.stackai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.stackai.com/integrations/catalog/typesafe-ai.md).

# TypeSafe AI

Make fast, calibrated decisions with TypeSafe's System One model: pick an option, score against a rubric, or answer yes/no with a probability.

## Connectors

Choose the connector that matches your authentication method. The options below use the names shown in StackAI.

| Connector   | Authentication |
| ----------- | -------------- |
| TypeSafe AI | API Key        |

### TypeSafe AI

Connect to TypeSafe's System One decision API.

#### Set up in TypeSafe AI

1. Sign up or log in at <https://console.typesafe.ai>.
2. Open Settings and select API Keys.
3. Create an API key and copy it (it is shown only once).

#### Set up in StackAI

1. Open **Settings → Connections**, add a connection, and select **TypeSafe AI**.
2. Enter the credentials and connection details in the fields below.
3. Save the connection and check its connection status. Select this saved connection when configuring an action or feature that uses it.

**Connection fields**

| StackAI field     | Required                 | What to enter                                                                                                                            |
| ----------------- | ------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------- |
| API Key           | Yes                      | Your TypeSafe API key. [Provider instructions](https://console.typesafe.ai/settings/keys).                                               |
| Endpoint Base URL | Optional / as applicable | Override to point at a dedicated TypeSafe gateway instead of the hosted API. Must be https unless the host is an allowlisted private IP. |

**Provider documentation:** [Setup reference](https://docs.typesafe.ai/api).

### Verify the connection

Check that the connection is healthy. Then run a read operation against a resource the connected account can access. A successful connection check confirms authentication; it does not guarantee permission for every action.

If access is denied, check the credential or OAuth permissions, the selected account or environment, and access to the specific resource. Update expired credentials or reconnect after permissions change.

## Use an action

1. Add the required **TypeSafe AI** action to the workflow.
2. Select a connection when the action requests one.
3. Complete the required fields. Use the reference picker when a value comes from another workflow step.
4. Run the workflow and inspect the action’s output. Check the result before using it in a later step.

## Actions

### Ask Yes/No

Answer a yes/no question about the state with a calibrated probability.

#### Inputs

| Field        | Type     | Required | Description                                                                       |
| ------------ | -------- | -------- | --------------------------------------------------------------------------------- |
| State        | textarea | Yes      | The content the model evaluates. Plain text, or JSON text for a structured state. |
| Instructions | textarea | Yes      | The question to ask about the state.                                              |
| Yes Criteria | textarea | No       | Optional description of what counts as yes.                                       |
| No Criteria  | textarea | No       | Optional description of what counts as no.                                        |
| Model        | string   | No       | TypeSafe model identifier. Default: jev-latest.                                   |

#### Outputs

| Field              | Type    | Description                                          |
| ------------------ | ------- | ---------------------------------------------------- |
| Model              | string  | The model that answered.                             |
| Input Tokens       | number  | Input tokens billed for the request, when reported.  |
| Output Tokens      | number  | Output tokens billed for the request, when reported. |
| Probability of Yes | number  | Probability that the answer is yes, from 0 to 1.     |
| Is Yes             | boolean | True when the probability of yes is at least 0.5.    |

### Ask Choice

Select one option from a defined set, with calibrated probabilities.

#### Inputs

| Field        | Type     | Required | Description                                                                       |
| ------------ | -------- | -------- | --------------------------------------------------------------------------------- |
| State        | textarea | Yes      | The content the model evaluates. Plain text, or JSON text for a structured state. |
| Instructions | textarea | Yes      | The question to ask about the state.                                              |
| Options      | object   | Yes      | JSON object mapping each option label to a short description.                     |
| Model        | string   | No       | TypeSafe model identifier. Default: jev-latest.                                   |

#### Outputs

| Field         | Type   | Description                                          |
| ------------- | ------ | ---------------------------------------------------- |
| Model         | string | The model that answered.                             |
| Input Tokens  | number | Input tokens billed for the request, when reported.  |
| Output Tokens | number | Output tokens billed for the request, when reported. |
| Choice        | string | The selected option label.                           |
| Confidence    | number | Calibrated confidence in the selection, from 0 to 1. |
| Probabilities | dict   | Probability assigned to each option label.           |

### Ask Score

Rate content against ordered, descriptive levels with calibrated probabilities.

#### Inputs

| Field        | Type     | Required | Description                                                                       |
| ------------ | -------- | -------- | --------------------------------------------------------------------------------- |
| State        | textarea | Yes      | The content the model evaluates. Plain text, or JSON text for a structured state. |
| Instructions | textarea | Yes      | The question to ask about the state.                                              |
| Levels       | array    | Yes      | Ordered list describing each level, lowest first. Scores start at 0.              |
| Model        | string   | No       | TypeSafe model identifier. Default: jev-latest.                                   |

#### Outputs

| Field         | Type   | Description                                          |
| ------------- | ------ | ---------------------------------------------------- |
| Model         | string | The model that answered.                             |
| Input Tokens  | number | Input tokens billed for the request, when reported.  |
| Output Tokens | number | Output tokens billed for the request, when reported. |
| Score         | number | Expected score. May fall between integer levels.     |
| Confidence    | number | Calibrated confidence in the score, from 0 to 1.     |
| Probabilities | dict   | Probability assigned to each level index.            |
| Legend        | dict   | Level descriptions keyed by level index.             |

### Ask Questions

Ask several yes/no, choice, and score questions about one state at once.

#### Inputs

| Field     | Type     | Required | Description                                                                       |
| --------- | -------- | -------- | --------------------------------------------------------------------------------- |
| State     | textarea | Yes      | The content the model evaluates. Plain text, or JSON text for a structured state. |
| Questions | object   | Yes      | JSON object of named questions in TypeSafe's question format.                     |
| Model     | string   | No       | TypeSafe model identifier. Default: jev-latest.                                   |

#### Outputs

| Field         | Type   | Description                                          |
| ------------- | ------ | ---------------------------------------------------- |
| Model         | string | The model that answered.                             |
| Input Tokens  | number | Input tokens billed for the request, when reported.  |
| Output Tokens | number | Output tokens billed for the request, when reported. |
| Answers       | dict   | Answer objects keyed by question name.               |

## Important behavior

Actions that create, update, send, or delete data can change the connected service. Review their inputs before running them. A retry can repeat an operation; consider this when configuring retries for actions that change data.

The catalog lists the fields and capabilities available in the supplied provider definition. Availability can also depend on your deployment and organization’s Feature Access settings.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.stackai.com/integrations/catalog/typesafe-ai.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
