Managing Prompts via Confident AI SDK

Every Prompts method in the Confident AI Python and TypeScript SDKs.

Overview

The Confident AI SDK exposes every Prompt method on the platform. This page documents how to call these methods in all supported languages. See the introduction to install the SDK and set your API key.

Prompt

client.prompt() returns a Prompt object that stands for one prompt. This object stores the fields listed below, and passes the prompt's id to every method called on it, so you don't need to pass the id nor the stored fields as arguments.

push is the exception, because it sends the stored fields rather than calling a route that names the id. Open the object with alias to call it.

from confident_ai import ConfidentAI

client = ConfidentAI()

prompt = client.prompt(prompt_id="<PROMPT-ID>")

Properties

These are the fields a Prompt stores. A method that loads the prompt fills them in, and a method that saves it sends whichever of them you have set, so set them before you save and read them after you load.

Parameter	Type	Description
`prompt_id`	`Optional[str]`	The unique id of the prompt.
`text`	`Optional[str]`	This is the text content of the prompt.
`alias`	`Optional[str]`	This is the alias of the prompt, which is unique within your project.
`id`	`Optional[str]`	This is the id of the commit pulled, generated by Confident AI, not to be confused with the prompt id, the version number, or the commit hash.
`hash`	`Optional[str]`	This is the commit hash of the prompt pulled.
`version`	`Optional[str]`	The version number of the prompt, present when the commit pulled has been released as a version.
`label`	`Optional[str]`	The user-defined label of the version pulled, present when the version carries one.
`type`	`Optional[PromptType]`	See PromptType.
`interpolation_type`	`Optional[PromptInterpolationType]`	See PromptInterpolationType.
`model_settings`	`Optional[ModelSettings]`	See ModelSettings.
`output_type`	`Optional[PromptOutputType]`	See PromptOutputType.
`output_schema`	`Optional[Dict[str, Any]]`	The JSON Schema the prompt's output must match, used when `outputType` is `SCHEMA`. It can describe objects (`properties` and `required`), arrays (`items`), and `string`, `integer`, `number`, `boolean` and `null` values. `title` names it, `additionalProperties` can only be `false`, and any other keyword is rejected.
`tools`	`Optional[List[Tool]]`	The tools available to the prompt, at the versions this commit pinned. See Tool.
`messages`	`Optional[List[PromptMessage]]`	This is the list of messages that make up the prompt. See PromptMessage.
`images_mapping`	`Optional[Dict[str, MLLMImageInput]]`	—

import { ConfidentAI } from "confident-ai";

const client = new ConfidentAI();

const prompt = client.prompt("<PROMPT-ID>");

Properties

Parameter	Type	Description
`promptId`	`string`	The unique id of the prompt.
`text`	`string`	This is the text content of the prompt.
`alias`	`string`	This is the alias of the prompt, which is unique within your project.
`id`	`string`	This is the id of the commit pulled, generated by Confident AI, not to be confused with the prompt id, the version number, or the commit hash.
`hash`	`string`	This is the commit hash of the prompt pulled.
`version`	`string`	The version number of the prompt, present when the commit pulled has been released as a version.
`label`	`string`	The user-defined label of the version pulled, present when the version carries one.
`type`	`PromptType`	See PromptType.
`interpolationType`	`PromptInterpolationType`	See PromptInterpolationType.
`modelSettings`	`ModelSettings`	See ModelSettings.
`outputType`	`PromptOutputType`	See PromptOutputType.
`outputSchema`	`Record<string, unknown>`	The JSON Schema the prompt's output must match, used when `outputType` is `SCHEMA`. It can describe objects (`properties` and `required`), arrays (`items`), and `string`, `integer`, `number`, `boolean` and `null` values. `title` names it, `additionalProperties` can only be `false`, and any other keyword is rejected.
`tools`	`Tool[]`	The tools available to the prompt, at the versions this commit pinned. See Tool.
`messages`	`PromptMessage[]`	This is the list of messages that make up the prompt. See PromptMessage.
`imagesMapping`	`Record<string, MLLMImageInput>`	—

Methods

Push Prompt

Creates a new commit for the prompt with the given alias, creating the prompt first when it does not exist. Send text for a text prompt or messages for a messages prompt, not both.

from confident_ai import ConfidentAI

client = ConfidentAI()

prompt = client.prompt(alias="greeting")
prompt.text = "Hello, {{name}}! How can I help you today?"
result = prompt.push(branch="main")

For async mode, call a_push and await it as shown below:

result = await prompt.a_push(...)

Parameters

Parameter	Type	Description
`branch`	`Optional[str]`	The name of the branch to push the new commit to. The branch is created from `main` when it does not exist yet.

import { ConfidentAI } from "confident-ai";

const client = new ConfidentAI();

const prompt = client.prompt(undefined, { alias: "greeting" });
prompt.text = "Hello, {{name}}! How can I help you today?";
const result = await prompt.push({ branch: "main" });

Parameters

Parameter	Type	Description
`branch`	`string`	The name of the branch to push the new commit to. The branch is created from `main` when it does not exist yet.

Returns

This method returns an object of type PushPromptResult.

Pull Prompt

Pull the prompt from Confident AI, and keep it current.

Pass at most one of commit, version, label. The commit that comes back is cached on disk and re-pulled in the background every refresh seconds, so editing the prompt on Confident AI reaches a running process without a deploy.

from confident_ai import ConfidentAI

client = ConfidentAI()

prompt = client.prompt(prompt_id="<PROMPT-ID>")
result = prompt.pull(
    commit="<COMMIT>",
    branch="main",
    refresh=60,
    fallback_to_cache=True,
    write_to_cache=True,
    default_to_cache=True,
)

For async mode, call a_pull and await it as shown below:

result = await prompt.a_pull(...)

Parameters

Parameter	Type	Description
`commit`	`Optional[str]`	The hash of the commit to pull. Defaults to `latest`.
`version`	`Optional[str]`	The version number of the prompt to pull.
`label`	`Optional[str]`	The label of the version to pull.
`branch`	`Optional[str]`	The name of the branch to read from. Defaults to `main` when omitted. Only valid with `commit`.
`refresh`	`Optional[int]`	How often, in seconds, to re-pull the prompt in the background. `0` turns off the refresh and the cache together, so that every pull calls the API — which is what you want while you are still editing the prompt. Defaults to `60`.
`fallback_to_cache`	`bool`	Serve the cached commit when the API cannot be reached, instead of raising. Defaults to `True`.
`write_to_cache`	`bool`	Write the pulled commit to the cache. The background refresh writes it either way. Defaults to `True`.
`default_to_cache`	`bool`	Return the cached commit when there is one, rather than waiting for the API. Defaults to `True`.

import { ConfidentAI } from "confident-ai";

const client = new ConfidentAI();

const prompt = client.prompt("<PROMPT-ID>");
const result = await prompt.pull(
  {
    commit: "<COMMIT>",
    branch: "main",
    refresh: 60,
    fallbackToCache: true,
    writeToCache: true,
    defaultToCache: true
  },
);

Parameters

Parameter	Type	Description
`commit`	`string`	The hash of the commit to pull. Defaults to `latest`.
`version`	`string`	The version number of the prompt to pull.
`label`	`string`	The label of the version to pull.
`branch`	`string`	The name of the branch to read from. Defaults to `main` when omitted. Only valid with `commit`.
`refresh`	`number`	How often, in seconds, to re-pull the prompt in the background. `0` turns off the refresh and the cache together, so that every pull calls the API — which is what you want while you are still editing the prompt. Defaults to `60`.
`fallbackToCache`	`boolean`	Serve the cached commit when the API cannot be reached, instead of raising. Defaults to `true`.
`writeToCache`	`boolean`	Write the pulled commit to the cache. The background refresh writes it either way. Defaults to `true`.
`defaultToCache`	`boolean`	Return the cached commit when there is one, rather than waiting for the API. Defaults to `true`.

Returns

This method returns an object of type Prompt.

Interpolate Prompt

Render the prompt's template with values, without calling the API.

Returns the interpolated text for a text prompt, and the interpolated messages for a messages prompt.

from confident_ai import ConfidentAI

client = ConfidentAI()

prompt = client.prompt(prompt_id="<PROMPT-ID>")
prompt.pull()
result = prompt.interpolate()

Parameters

Parameter	Type	Description
`**values`	`Any`	—

import { ConfidentAI } from "confident-ai";

const client = new ConfidentAI();

const prompt = client.prompt("<PROMPT-ID>");
await prompt.pull();
const result = await prompt.interpolate();

Parameters

Parameter	Type	Description
`values`	`Record<string, unknown>`	—

Returns

This method returns an object of type InterpolatedPrompt.

Methods (Stateless)

These methods take every argument themselves, so a caller reaches them through client.prompts without opening a Prompt first.

List Prompts

Lists all the prompts in your Confident AI project.

from confident_ai import ConfidentAI

client = ConfidentAI()

result = client.prompts.list()

For async mode, call a_list and await it as shown below:

result = await client.prompts.a_list(...)

import { ConfidentAI } from "confident-ai";

const client = new ConfidentAI();

const result = await client.prompts.list();

Returns

This method returns an object of type PromptList.

Text Prompt Input

Creates a new commit for the prompt with the given alias, creating the prompt first when it does not exist. Send text for a text prompt or messages for a messages prompt, not both.

Pushes a commit to a text prompt. interpolationType defaults to FSTRING when omitted.

from confident_ai import ConfidentAI
from confident_ai.common import ModelProvider
from confident_ai.prompts import (
    ModelSettings,
    PromptInterpolationType,
    PromptOutputType,
    ReasoningEffort,
    TextPromptInput,
    ToolInput,
    Verbosity,
)

client = ConfidentAI()

result = client.prompts.push(
    prompt=TextPromptInput(
        text="Hello, {{name}}! How can I help you today?",
        alias="greeting",
        interpolation_type=PromptInterpolationType.MUSTACHE,
        model_settings=ModelSettings(
            provider=ModelProvider.OPEN_AI,
            name="gpt-4o",
            temperature=0.7,
            max_tokens=1024,
            top_p=1,
            top_k=40,
            frequency_penalty=0,
            presence_penalty=0,
            stop_sequence=["\n\nHuman:", "###"],
            reasoning_effort=ReasoningEffort.MINIMAL,
            verbosity=Verbosity.LOW
        ),
        output_type=PromptOutputType.TEXT,
        output_schema={
            "title": "Greeting",
            "type": "object",
            "properties": {"greeting": {"type": "string"}},
            "required": ["greeting"],
            "additionalProperties": False
        },
        tools=[
            ToolInput(
                id="<TOOL-ID>",
                version="00.00.01"
            )
        ],
        branch="main",
        images_mapping={}
    ),
)

For async mode, call a_push and await it as shown below:

result = await client.prompts.a_push(...)

Parameters

Parameter	Type	Description
`prompt`	`PromptInput`	Required. The commit to push. Send `text` for a text prompt or `messages` for a messages prompt, never both. The kind must match the existing prompt's type. Pass a TextPromptInput or a MessagesPromptInput. See PromptInput.

import { ConfidentAI } from "confident-ai";
import { ModelProvider } from "confident-ai/common";
import {
  PromptInterpolationType,
  PromptOutputType,
  ReasoningEffort,
  Verbosity,
} from "confident-ai/prompts";

const client = new ConfidentAI();

const result = await client.prompts.push(
  {
    text: "Hello, {{name}}! How can I help you today?",
    alias: "greeting",
    interpolationType: PromptInterpolationType.MUSTACHE,
    modelSettings: {
        provider: ModelProvider.OPEN_AI,
        name: "gpt-4o",
        temperature: 0.7,
        maxTokens: 1024,
        topP: 1,
        topK: 40,
        frequencyPenalty: 0,
        presencePenalty: 0,
        stopSequence: ["\n\nHuman:", "###"],
        reasoningEffort: ReasoningEffort.MINIMAL,
        verbosity: Verbosity.LOW
      },
    outputType: PromptOutputType.TEXT,
    outputSchema: {
        title: "Greeting",
        type: "object",
        properties: { greeting: { type: "string" } },
        required: ["greeting"],
        additionalProperties: false
      },
    tools: [
        {
          id: "<TOOL-ID>",
          version: "00.00.01"
        }
      ],
    branch: "main",
    imagesMapping: {}
  },
);

Parameters

Parameter	Type	Description
`prompt`	`PromptInput`	Required. The commit to push. Send `text` for a text prompt or `messages` for a messages prompt, never both. The kind must match the existing prompt's type. Pass a TextPromptInput or a MessagesPromptInput. See PromptInput.

Returns

This method returns an object of type PushPromptResult.

Messages Prompt Input

Creates a new commit for the prompt with the given alias, creating the prompt first when it does not exist. Send text for a text prompt or messages for a messages prompt, not both.

Pushes a commit to a messages prompt. interpolationType defaults to FSTRING when omitted.

from confident_ai import ConfidentAI
from confident_ai.common import ModelProvider
from confident_ai.prompts import (
    MessagesPromptInput,
    ModelSettings,
    PromptInterpolationType,
    PromptMessage,
    PromptOutputType,
    ReasoningEffort,
    ToolInput,
    Verbosity,
)

client = ConfidentAI()

result = client.prompts.push(
    prompt=MessagesPromptInput(
        messages=[
            PromptMessage(
                role="system",
                content="You are a helpful assistant."
            ),
            PromptMessage(
                role="user",
                content="Hello, {{name}}! How can I help you today?"
            )
        ],
        alias="greeting",
        interpolation_type=PromptInterpolationType.MUSTACHE,
        model_settings=ModelSettings(
            provider=ModelProvider.OPEN_AI,
            name="gpt-4o",
            temperature=0.7,
            max_tokens=1024,
            top_p=1,
            top_k=40,
            frequency_penalty=0,
            presence_penalty=0,
            stop_sequence=["\n\nHuman:", "###"],
            reasoning_effort=ReasoningEffort.MINIMAL,
            verbosity=Verbosity.LOW
        ),
        output_type=PromptOutputType.TEXT,
        output_schema={
            "title": "Greeting",
            "type": "object",
            "properties": {"greeting": {"type": "string"}},
            "required": ["greeting"],
            "additionalProperties": False
        },
        tools=[
            ToolInput(
                id="<TOOL-ID>",
                version="00.00.01"
            )
        ],
        branch="main",
        images_mapping={}
    ),
)

For async mode, call a_push and await it as shown below:

result = await client.prompts.a_push(...)

Parameters

Parameter	Type	Description
`prompt`	`PromptInput`	Required. The commit to push. Send `text` for a text prompt or `messages` for a messages prompt, never both. The kind must match the existing prompt's type. Pass a TextPromptInput or a MessagesPromptInput. See PromptInput.

import { ConfidentAI } from "confident-ai";
import { ModelProvider } from "confident-ai/common";
import {
  PromptInterpolationType,
  PromptOutputType,
  ReasoningEffort,
  Verbosity,
} from "confident-ai/prompts";

const client = new ConfidentAI();

const result = await client.prompts.push(
  {
    messages: [
        {
          role: "system",
          content: "You are a helpful assistant."
        },
        {
          role: "user",
          content: "Hello, {{name}}! How can I help you today?"
        }
      ],
    alias: "greeting",
    interpolationType: PromptInterpolationType.MUSTACHE,
    modelSettings: {
        provider: ModelProvider.OPEN_AI,
        name: "gpt-4o",
        temperature: 0.7,
        maxTokens: 1024,
        topP: 1,
        topK: 40,
        frequencyPenalty: 0,
        presencePenalty: 0,
        stopSequence: ["\n\nHuman:", "###"],
        reasoningEffort: ReasoningEffort.MINIMAL,
        verbosity: Verbosity.LOW
      },
    outputType: PromptOutputType.TEXT,
    outputSchema: {
        title: "Greeting",
        type: "object",
        properties: { greeting: { type: "string" } },
        required: ["greeting"],
        additionalProperties: false
      },
    tools: [
        {
          id: "<TOOL-ID>",
          version: "00.00.01"
        }
      ],
    branch: "main",
    imagesMapping: {}
  },
);

Parameters

Parameter	Type	Description
`prompt`	`PromptInput`	Required. The commit to push. Send `text` for a text prompt or `messages` for a messages prompt, never both. The kind must match the existing prompt's type. Pass a TextPromptInput or a MessagesPromptInput. See PromptInput.

Returns

This method returns an object of type PushPromptResult.

Get By Label

Retrieves the prompt version carrying label.

from confident_ai import ConfidentAI

client = ConfidentAI()

result = client.prompts.get_by_label(
    prompt_id="<PROMPT-ID>",
    label="production",
)

For async mode, call a_get_by_label and await it as shown below:

result = await client.prompts.a_get_by_label(...)

Parameters

Parameter	Type	Description
`prompt_id`	`str`	Required. The unique id of the prompt.
`label`	`str`	Required. The label of the version to pull.

import { ConfidentAI } from "confident-ai";

const client = new ConfidentAI();

const result = await client.prompts.getByLabel("<PROMPT-ID>", "production");

Parameters

Parameter	Type	Description
`promptId`	`string`	Required. The unique id of the prompt.
`label`	`string`	Required. The label of the version to pull.

Returns

This method returns an object of type Prompt.

Get By Commit

Retrieves the prompt commit with the given hash. The commit is looked up on main unless a branch is given.

from confident_ai import ConfidentAI

client = ConfidentAI()

result = client.prompts.get_by_commit(
    prompt_id="<PROMPT-ID>",
    hash="bab04ce",
    branch="main",
)

For async mode, call a_get_by_commit and await it as shown below:

result = await client.prompts.a_get_by_commit(...)

Parameters

Parameter	Type	Description
`prompt_id`	`str`	Required. The unique id of the prompt.
`hash`	`str`	Required. The hash of the commit to pull.
`branch`	`Optional[str]`	The name of the branch to read from. Defaults to `main` when omitted.

import { ConfidentAI } from "confident-ai";

const client = new ConfidentAI();

const result = await client.prompts.getByCommit(
  "<PROMPT-ID>",
  "bab04ce",
  "main",
);

Parameters

Parameter	Type	Description
`promptId`	`string`	Required. The unique id of the prompt.
`hash`	`string`	Required. The hash of the commit to pull.
`branch`	`string`	The name of the branch to read from. Defaults to `main` when omitted.

Returns

This method returns an object of type Prompt.

Get By Version

Retrieves the prompt commit released as version.

from confident_ai import ConfidentAI

client = ConfidentAI()

result = client.prompts.get_by_version(
    prompt_id="<PROMPT-ID>",
    version="00.00.01",
)

For async mode, call a_get_by_version and await it as shown below:

result = await client.prompts.a_get_by_version(...)

Parameters

Parameter	Type	Description
`prompt_id`	`str`	Required. The unique id of the prompt.
`version`	`str`	Required. The version number of the prompt to pull.

import { ConfidentAI } from "confident-ai";

const client = new ConfidentAI();

const result = await client.prompts.getByVersion("<PROMPT-ID>", "00.00.01");

Parameters

Parameter	Type	Description
`promptId`	`string`	Required. The unique id of the prompt.
`version`	`string`	Required. The version number of the prompt to pull.

Returns

This method returns an object of type Prompt.

Types

MLLMImageInput

An image referenced from a text field by a [DEEPEVAL:IMAGE:<key>] marker. Send either a public url or the bytes in base64.

class MLLMImageInput:
    url: str
    local: bool
    base64: Optional[str] = None
    filename: Optional[str] = None
    mime_type: Optional[str] = Field(default=None, alias="mimeType")
    data_base64: Optional[str] = Field(default=None, alias="dataBase64")

urlstrRequired

This is the URL of the image.

Example: "https://example.com/everest.png"

localboolRequired

This is true when the image is your local file.

Example: false

base64Optional[str]

The base64 data of the image.

Example: "iVBORw0KGgo="

filenameOptional[str]

The original file name.

Example: "everest.png"

mime_typeOptional[str]

The image's MIME type.

Example: "image/png"

data_base64Optional[str]

The image encoded as a base64 data URL.

Example: "data:image/png;base64,iVBORw0KGgo="

interface MLLMImageInput {
  url: string;
  local: boolean;
  base64?: string;
  filename?: string;
  mimeType?: string;
  dataBase64?: string;
}

urlstringRequired

This is the URL of the image.

Example: "https://example.com/everest.png"

localbooleanRequired

This is true when the image is your local file.

Example: false

base64string

The base64 data of the image.

Example: "iVBORw0KGgo="

filenamestring

The original file name.

Example: "everest.png"

mimeTypestring

The image's MIME type.

Example: "image/png"

dataBase64string

The image encoded as a base64 data URL.

Example: "data:image/png;base64,iVBORw0KGgo="

ModelProvider

This is the provider of the model.

class ModelProvider(Enum):
    OPEN_AI = "OPEN_AI"
    CUSTOM = "CUSTOM"
    CONFIDENT_AI = "CONFIDENT_AI"
    BEDROCK = "BEDROCK"
    ANTHROPIC = "ANTHROPIC"
    GEMINI = "GEMINI"
    X_AI = "X_AI"
    DEEPSEEK = "DEEPSEEK"
    MOONSHOT_AI = "MOONSHOT_AI"
    VERTEX_AI = "VERTEX_AI"
    AZURE = "AZURE"
    MISTRAL = "MISTRAL"
    PERPLEXITY = "PERPLEXITY"
    OPEN_ROUTER = "OPEN_ROUTER"
    PORTKEY = "PORTKEY"
    LITE_LLM = "LITE_LLM"
    TRUE_FOUNDRY = "TRUE_FOUNDRY"
    HUGGING_FACE = "HUGGING_FACE"
    TYPE_SAFE = "TYPE_SAFE"
    FAL = "FAL"
    Z_AI = "Z_AI"

enum ModelProvider {
  OPEN_AI = "OPEN_AI",
  CUSTOM = "CUSTOM",
  CONFIDENT_AI = "CONFIDENT_AI",
  BEDROCK = "BEDROCK",
  ANTHROPIC = "ANTHROPIC",
  GEMINI = "GEMINI",
  X_AI = "X_AI",
  DEEPSEEK = "DEEPSEEK",
  MOONSHOT_AI = "MOONSHOT_AI",
  VERTEX_AI = "VERTEX_AI",
  AZURE = "AZURE",
  MISTRAL = "MISTRAL",
  PERPLEXITY = "PERPLEXITY",
  OPEN_ROUTER = "OPEN_ROUTER",
  PORTKEY = "PORTKEY",
  LITE_LLM = "LITE_LLM",
  TRUE_FOUNDRY = "TRUE_FOUNDRY",
  HUGGING_FACE = "HUGGING_FACE",
  TYPE_SAFE = "TYPE_SAFE",
  FAL = "FAL",
  Z_AI = "Z_AI",
}

OPEN_AI · CUSTOM · CONFIDENT_AI · BEDROCK · ANTHROPIC · GEMINI · X_AI · DEEPSEEK · MOONSHOT_AI · VERTEX_AI · AZURE · MISTRAL · PERPLEXITY · OPEN_ROUTER · PORTKEY · LITE_LLM · TRUE_FOUNDRY · HUGGING_FACE · TYPE_SAFE · FAL · Z_AI

ModelSettings

This is the model settings the prompt was authored for.

class ModelSettings:
    provider: Optional[ModelProvider] = None
    name: Optional[str] = None
    temperature: Optional[float] = None
    max_tokens: Optional[float] = Field(default=None, alias="maxTokens")
    top_p: Optional[float] = Field(default=None, alias="topP")
    top_k: Optional[float] = Field(default=None, alias="topK")
    frequency_penalty: Optional[float] = Field(default=None, alias="frequencyPenalty")
    presence_penalty: Optional[float] = Field(default=None, alias="presencePenalty")
    stop_sequence: Optional[List[str]] = Field(default=None, alias="stopSequence")
    reasoning_effort: Optional[ReasoningEffort] = Field(default=None, alias="reasoningEffort")
    verbosity: Optional[Verbosity] = None

providerOptional[ModelProvider]

See ModelProvider.

nameOptional[str]

This is the name of the model.

Example: "gpt-4o"

temperatureOptional[float]

This controls randomness in the model's output. Higher values make output more random.

Example: 0.7

max_tokensOptional[float]

This is the maximum number of tokens to generate.

Example: 1024

top_pOptional[float]

This controls diversity via nucleus sampling. Lower values focus on more likely tokens.

Example: 1

top_kOptional[float]

This limits sampling to the K most likely tokens at each step.

Example: 40

frequency_penaltyOptional[float]

This is the penalty for tokens based on their frequency in the text so far.

Example: 0

presence_penaltyOptional[float]

This is the penalty for tokens based on whether they appear in the text so far.

Example: 0

stop_sequenceOptional[List[str]]

This is the sequences where the model will stop generating further tokens.

Example: ["\n\nHuman:","###"]

reasoning_effortOptional[ReasoningEffort]

See ReasoningEffort.

verbosityOptional[Verbosity]

See Verbosity.

interface ModelSettings {
  provider?: ModelProvider;
  name?: string;
  temperature?: number;
  maxTokens?: number;
  topP?: number;
  topK?: number;
  frequencyPenalty?: number;
  presencePenalty?: number;
  stopSequence?: string[];
  reasoningEffort?: ReasoningEffort;
  verbosity?: Verbosity;
}

providerModelProvider

See ModelProvider.

namestring

This is the name of the model.

Example: "gpt-4o"

temperaturenumber

This controls randomness in the model's output. Higher values make output more random.

Example: 0.7

maxTokensnumber

This is the maximum number of tokens to generate.

Example: 1024

topPnumber

This controls diversity via nucleus sampling. Lower values focus on more likely tokens.

Example: 1

topKnumber

This limits sampling to the K most likely tokens at each step.

Example: 40

frequencyPenaltynumber

This is the penalty for tokens based on their frequency in the text so far.

Example: 0

presencePenaltynumber

This is the penalty for tokens based on whether they appear in the text so far.

Example: 0

stopSequencestring[]

This is the sequences where the model will stop generating further tokens.

Example: ["\n\nHuman:","###"]

reasoningEffortReasoningEffort

See ReasoningEffort.

verbosityVerbosity

See Verbosity.

Prompt

A single commit of a prompt, as pulled by version, commit hash, or label. It carries text when the prompt is a text prompt and messages when it is a messages prompt, never both.

Prompt = Union[
    TextPrompt,
    MessagesPrompt,
]

type Prompt =
  | TextPrompt
  | MessagesPrompt;

A Prompt is one of the shapes below. Send the fields of one of them, never a mix of both.

A pulled prompt whose content is a single text template.

class TextPrompt:
    text: str
    alias: str
    id: str
    hash: str
    version: Optional[str] = None
    label: Optional[str] = None
    type: PromptType
    interpolation_type: PromptInterpolationType = Field(alias="interpolationType")
    model_settings: Optional[ModelSettings] = Field(default=None, alias="modelSettings")
    output_type: PromptOutputType = Field(alias="outputType")
    output_schema: Optional[Dict[str, Any]] = Field(default=None, alias="outputSchema")
    tools: Optional[List[Tool]] = None

textstrRequired

This is the text content of the prompt.

Example: "Hello, {{name}}! How can I help you today?"

aliasstrRequired

This is the alias of the prompt, which is unique within your project.

Example: "greeting"

idstrRequired

This is the id of the commit pulled, generated by Confident AI, not to be confused with the prompt id, the version number, or the commit hash.

Example: "<COMMIT-ID>"

hashstrRequired

This is the commit hash of the prompt pulled.

Example: "bab04ce"

versionOptional[str]

The version number of the prompt, present when the commit pulled has been released as a version.

Example: "00.00.01"

labelOptional[str]

The user-defined label of the version pulled, present when the version carries one.

Example: "production"

typePromptTypeRequired

See PromptType.

interpolation_typePromptInterpolationTypeRequired

See PromptInterpolationType.

model_settingsOptional[ModelSettings]

See ModelSettings.

output_typePromptOutputTypeRequired

See PromptOutputType.

output_schemaOptional[Dict[str, Any]]

The JSON Schema the prompt's output must match, used when outputType is SCHEMA. It can describe objects (properties and required), arrays (items), and string, integer, number, boolean and null values. title names it, additionalProperties can only be false, and any other keyword is rejected.

Example: {"title":"Greeting","type":"object","properties":{"greeting":{"type":"string"}},"required":["greeting"],"additionalProperties":false}

toolsOptional[List[Tool]]

The tools available to the prompt, at the versions this commit pinned.

See Tool.

interface TextPrompt {
  text: string;
  alias: string;
  id: string;
  hash: string;
  version?: string;
  label?: string;
  type: PromptType;
  interpolationType: PromptInterpolationType;
  modelSettings?: ModelSettings;
  outputType: PromptOutputType;
  outputSchema?: Record<string, unknown>;
  tools?: Tool[];
}

textstringRequired

This is the text content of the prompt.

Example: "Hello, {{name}}! How can I help you today?"

aliasstringRequired

This is the alias of the prompt, which is unique within your project.

Example: "greeting"

idstringRequired

This is the id of the commit pulled, generated by Confident AI, not to be confused with the prompt id, the version number, or the commit hash.

Example: "<COMMIT-ID>"

hashstringRequired

This is the commit hash of the prompt pulled.

Example: "bab04ce"

versionstring

The version number of the prompt, present when the commit pulled has been released as a version.

Example: "00.00.01"

labelstring

The user-defined label of the version pulled, present when the version carries one.

Example: "production"

typePromptTypeRequired

See PromptType.

interpolationTypePromptInterpolationTypeRequired

See PromptInterpolationType.

modelSettingsModelSettings

See ModelSettings.

outputTypePromptOutputTypeRequired

See PromptOutputType.

outputSchemaRecord<string, unknown>

Example: {"title":"Greeting","type":"object","properties":{"greeting":{"type":"string"}},"required":["greeting"],"additionalProperties":false}

toolsTool[]

The tools available to the prompt, at the versions this commit pinned.

See Tool.

A pulled prompt whose content is a list of messages.

class MessagesPrompt:
    messages: List[PromptMessage]
    alias: str
    id: str
    hash: str
    version: Optional[str] = None
    label: Optional[str] = None
    type: PromptType
    interpolation_type: PromptInterpolationType = Field(alias="interpolationType")
    model_settings: Optional[ModelSettings] = Field(default=None, alias="modelSettings")
    output_type: PromptOutputType = Field(alias="outputType")
    output_schema: Optional[Dict[str, Any]] = Field(default=None, alias="outputSchema")
    tools: Optional[List[Tool]] = None

messagesList[PromptMessage]Required

This is the list of messages that make up the prompt.

See PromptMessage.

Example: [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Hello, {{name}}! How can I help you today?"}]

aliasstrRequired

This is the alias of the prompt, which is unique within your project.

Example: "greeting"

idstrRequired

This is the id of the commit pulled, generated by Confident AI, not to be confused with the prompt id, the version number, or the commit hash.

Example: "<COMMIT-ID>"

hashstrRequired

This is the commit hash of the prompt pulled.

Example: "bab04ce"

versionOptional[str]

The version number of the prompt, present when the commit pulled has been released as a version.

Example: "00.00.01"

labelOptional[str]

The user-defined label of the version pulled, present when the version carries one.

Example: "production"

typePromptTypeRequired

See PromptType.

interpolation_typePromptInterpolationTypeRequired

See PromptInterpolationType.

model_settingsOptional[ModelSettings]

See ModelSettings.

output_typePromptOutputTypeRequired

See PromptOutputType.

output_schemaOptional[Dict[str, Any]]

Example: {"title":"Greeting","type":"object","properties":{"greeting":{"type":"string"}},"required":["greeting"],"additionalProperties":false}

toolsOptional[List[Tool]]

The tools available to the prompt, at the versions this commit pinned.

See Tool.

interface MessagesPrompt {
  messages: PromptMessage[];
  alias: string;
  id: string;
  hash: string;
  version?: string;
  label?: string;
  type: PromptType;
  interpolationType: PromptInterpolationType;
  modelSettings?: ModelSettings;
  outputType: PromptOutputType;
  outputSchema?: Record<string, unknown>;
  tools?: Tool[];
}

messagesPromptMessage[]Required

This is the list of messages that make up the prompt.

See PromptMessage.

Example: [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Hello, {{name}}! How can I help you today?"}]

aliasstringRequired

This is the alias of the prompt, which is unique within your project.

Example: "greeting"

idstringRequired

This is the id of the commit pulled, generated by Confident AI, not to be confused with the prompt id, the version number, or the commit hash.

Example: "<COMMIT-ID>"

hashstringRequired

This is the commit hash of the prompt pulled.

Example: "bab04ce"

versionstring

The version number of the prompt, present when the commit pulled has been released as a version.

Example: "00.00.01"

labelstring

The user-defined label of the version pulled, present when the version carries one.

Example: "production"

typePromptTypeRequired

See PromptType.

interpolationTypePromptInterpolationTypeRequired

See PromptInterpolationType.

modelSettingsModelSettings

See ModelSettings.

outputTypePromptOutputTypeRequired

See PromptOutputType.

outputSchemaRecord<string, unknown>

Example: {"title":"Greeting","type":"object","properties":{"greeting":{"type":"string"}},"required":["greeting"],"additionalProperties":false}

toolsTool[]

The tools available to the prompt, at the versions this commit pinned.

See Tool.

PromptInput

The commit to push. Send text for a text prompt or messages for a messages prompt, never both. The kind must match the existing prompt's type.

PromptInput = Union[
    TextPromptInput,
    MessagesPromptInput,
]

type PromptInput =
  | TextPromptInput
  | MessagesPromptInput;

A PromptInput is one of the shapes below. Send the fields of one of them, never a mix of both.

Pushes a commit to a text prompt. interpolationType defaults to FSTRING when omitted.

class TextPromptInput:
    text: str
    alias: str
    interpolation_type: Optional[PromptInterpolationType] = Field(default=None, alias="interpolationType")
    model_settings: Optional[ModelSettings] = Field(default=None, alias="modelSettings")
    output_type: Optional[PromptOutputType] = Field(default=None, alias="outputType")
    output_schema: Optional[Dict[str, Any]] = Field(default=None, alias="outputSchema")
    tools: Optional[List[ToolInput]] = None
    branch: Optional[str] = None
    images_mapping: Optional[Dict[str, MLLMImageInput]] = Field(default=None, alias="imagesMapping")

textstrRequired

The text content of the prompt.

Example: "Hello, {{name}}! How can I help you today?"

aliasstrRequired

The alias of the prompt, unique within your project. A new prompt is created when no prompt with this alias exists.

Example: "greeting"

interpolation_typeOptional[PromptInterpolationType]

See PromptInterpolationType.

model_settingsOptional[ModelSettings]

See ModelSettings.

output_typeOptional[PromptOutputType]

See PromptOutputType.

output_schemaOptional[Dict[str, Any]]

Example: {"title":"Greeting","type":"object","properties":{"greeting":{"type":"string"}},"required":["greeting"],"additionalProperties":false}

toolsOptional[List[ToolInput]]

The tools available to the prompt. The commit pins each one at a version.

See ToolInput.

Example: [{"id":"<TOOL-ID>","version":"00.00.01"}]

branchOptional[str]

The name of the branch to push the new commit to. The branch is created from main when it does not exist yet.

Example: "main"

images_mappingOptional[Dict[str, MLLMImageInput]]

Images placed in the prompt's text or message contents with [CONFIDENT:IMAGE:<key>] markers, keyed by each marker's <key>. When you send it, Confident AI stores its own copy of every image the prompt contains; without it, the prompt is stored as sent.

See MLLMImageInput.

interface TextPromptInput {
  text: string;
  alias: string;
  interpolationType?: PromptInterpolationType;
  modelSettings?: ModelSettings;
  outputType?: PromptOutputType;
  outputSchema?: Record<string, unknown>;
  tools?: ToolInput[];
  branch?: string;
  imagesMapping?: Record<string, MLLMImageInput>;
}

textstringRequired

The text content of the prompt.

Example: "Hello, {{name}}! How can I help you today?"

aliasstringRequired

The alias of the prompt, unique within your project. A new prompt is created when no prompt with this alias exists.

Example: "greeting"

interpolationTypePromptInterpolationType

See PromptInterpolationType.

modelSettingsModelSettings

See ModelSettings.

outputTypePromptOutputType

See PromptOutputType.

outputSchemaRecord<string, unknown>

Example: {"title":"Greeting","type":"object","properties":{"greeting":{"type":"string"}},"required":["greeting"],"additionalProperties":false}

toolsToolInput[]

The tools available to the prompt. The commit pins each one at a version.

See ToolInput.

Example: [{"id":"<TOOL-ID>","version":"00.00.01"}]

branchstring

The name of the branch to push the new commit to. The branch is created from main when it does not exist yet.

Example: "main"

imagesMappingRecord<string, MLLMImageInput>

See MLLMImageInput.

Pushes a commit to a messages prompt. interpolationType defaults to FSTRING when omitted.

class MessagesPromptInput:
    messages: List[PromptMessage]
    alias: str
    interpolation_type: Optional[PromptInterpolationType] = Field(default=None, alias="interpolationType")
    model_settings: Optional[ModelSettings] = Field(default=None, alias="modelSettings")
    output_type: Optional[PromptOutputType] = Field(default=None, alias="outputType")
    output_schema: Optional[Dict[str, Any]] = Field(default=None, alias="outputSchema")
    tools: Optional[List[ToolInput]] = None
    branch: Optional[str] = None
    images_mapping: Optional[Dict[str, MLLMImageInput]] = Field(default=None, alias="imagesMapping")

messagesList[PromptMessage]Required

The list of messages that make up the prompt.

See PromptMessage.

Example: [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Hello, {{name}}! How can I help you today?"}]

aliasstrRequired

The alias of the prompt, unique within your project. A new prompt is created when no prompt with this alias exists.

Example: "greeting"

interpolation_typeOptional[PromptInterpolationType]

See PromptInterpolationType.

model_settingsOptional[ModelSettings]

See ModelSettings.

output_typeOptional[PromptOutputType]

See PromptOutputType.

output_schemaOptional[Dict[str, Any]]

Example: {"title":"Greeting","type":"object","properties":{"greeting":{"type":"string"}},"required":["greeting"],"additionalProperties":false}

toolsOptional[List[ToolInput]]

The tools available to the prompt. The commit pins each one at a version.

See ToolInput.

Example: [{"id":"<TOOL-ID>","version":"00.00.01"}]

branchOptional[str]

The name of the branch to push the new commit to. The branch is created from main when it does not exist yet.

Example: "main"

images_mappingOptional[Dict[str, MLLMImageInput]]

See MLLMImageInput.

interface MessagesPromptInput {
  messages: PromptMessage[];
  alias: string;
  interpolationType?: PromptInterpolationType;
  modelSettings?: ModelSettings;
  outputType?: PromptOutputType;
  outputSchema?: Record<string, unknown>;
  tools?: ToolInput[];
  branch?: string;
  imagesMapping?: Record<string, MLLMImageInput>;
}

messagesPromptMessage[]Required

The list of messages that make up the prompt.

See PromptMessage.

Example: [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Hello, {{name}}! How can I help you today?"}]

aliasstringRequired

The alias of the prompt, unique within your project. A new prompt is created when no prompt with this alias exists.

Example: "greeting"

interpolationTypePromptInterpolationType

See PromptInterpolationType.

modelSettingsModelSettings

See ModelSettings.

outputTypePromptOutputType

See PromptOutputType.

outputSchemaRecord<string, unknown>

Example: {"title":"Greeting","type":"object","properties":{"greeting":{"type":"string"}},"required":["greeting"],"additionalProperties":false}

toolsToolInput[]

The tools available to the prompt. The commit pins each one at a version.

See ToolInput.

Example: [{"id":"<TOOL-ID>","version":"00.00.01"}]

branchstring

The name of the branch to push the new commit to. The branch is created from main when it does not exist yet.

Example: "main"

imagesMappingRecord<string, MLLMImageInput>

See MLLMImageInput.

PromptInterpolationType

The type of interpolation format used in the prompt to insert dynamic variables.

class PromptInterpolationType(Enum):
    MUSTACHE = "MUSTACHE"
    MUSTACHE_WITH_SPACE = "MUSTACHE_WITH_SPACE"
    FSTRING = "FSTRING"
    DOLLAR_BRACKETS = "DOLLAR_BRACKETS"
    JINJA = "JINJA"

enum PromptInterpolationType {
  MUSTACHE = "MUSTACHE",
  MUSTACHE_WITH_SPACE = "MUSTACHE_WITH_SPACE",
  FSTRING = "FSTRING",
  DOLLAR_BRACKETS = "DOLLAR_BRACKETS",
  JINJA = "JINJA",
}

MUSTACHE · MUSTACHE_WITH_SPACE · FSTRING · DOLLAR_BRACKETS · JINJA

PromptList

class PromptList:
    prompts: List[PromptSummary]

promptsList[PromptSummary]Required

This is the list of prompts in your project.

See PromptSummary.

interface PromptList {
  prompts: PromptSummary[];
}

promptsPromptSummary[]Required

This is the list of prompts in your project.

See PromptSummary.

PromptMessage

class PromptMessage:
    role: str
    content: str
    tool_calls: Optional[List[PromptMessageToolCall]] = None
    tool_call_id: Optional[str] = None

rolestrRequired

This is the role of the message, which can be user, assistant, system, or developer.

Example: "user"

contentstrRequired

This is the text content of the message.

Example: "Hello, {{name}}! How can I help you today?"

tool_callsOptional[List[PromptMessageToolCall]]

Tool calls made by an assistant message, in the OpenAI chat format.

See PromptMessageToolCall.

tool_call_idOptional[str]

For tool messages, the id of the assistant tool call this result answers.

Example: "call_abc123"

interface PromptMessage {
  role: string;
  content: string;
  tool_calls?: PromptMessageToolCall[];
  tool_call_id?: string;
}

rolestringRequired

This is the role of the message, which can be user, assistant, system, or developer.

Example: "user"

contentstringRequired

This is the text content of the message.

Example: "Hello, {{name}}! How can I help you today?"

tool_callsPromptMessageToolCall[]

Tool calls made by an assistant message, in the OpenAI chat format.

See PromptMessageToolCall.

tool_call_idstring

For tool messages, the id of the assistant tool call this result answers.

Example: "call_abc123"

PromptMessageToolCall

class PromptMessageToolCall:
    id: str
    type: Literal["function"]
    function: PromptMessageToolCallFunction

idstrRequired

Example: "call_abc123"

typeLiteral["function"]Required

functionPromptMessageToolCallFunctionRequired

interface PromptMessageToolCall {
  id: string;
  type: "function";
  function: PromptMessageToolCallFunction;
}

idstringRequired

Example: "call_abc123"

type"function"Required

functionPromptMessageToolCallFunctionRequired

PromptOutputType

The type of output expected from the prompt.

class PromptOutputType(Enum):
    TEXT = "TEXT"
    JSON = "JSON"
    SCHEMA = "SCHEMA"

enum PromptOutputType {
  TEXT = "TEXT",
  JSON = "JSON",
  SCHEMA = "SCHEMA",
}

TEXT · JSON · SCHEMA

PromptSummary

A prompt as it appears in your project's prompt list, without any version content.

class PromptSummary:
    id: str
    alias: str
    type: PromptType

idstrRequired

This is the unique id of the prompt.

Example: "<PROMPT-ID>"

aliasstrRequired

This is the alias of the prompt, which is unique within your project.

Example: "greeting"

typePromptTypeRequired

See PromptType.

interface PromptSummary {
  id: string;
  alias: string;
  type: PromptType;
}

idstringRequired

This is the unique id of the prompt.

Example: "<PROMPT-ID>"

aliasstringRequired

This is the alias of the prompt, which is unique within your project.

Example: "greeting"

typePromptTypeRequired

See PromptType.

PromptType

This is the type of the prompt, which can be either a simple text or a list of messages.

class PromptType(Enum):
    TEXT = "TEXT"
    LIST = "LIST"

enum PromptType {
  TEXT = "TEXT",
  LIST = "LIST",
}

TEXT · LIST

PushPromptResult

class PushPromptResult:
    prompt_id: str = Field(alias="promptId")
    hash: str

prompt_idstrRequired

This is the id of the prompt generated by Confident AI, not to be confused with the alias you supplied.

Example: "<PROMPT-ID>"

hashstrRequired

This is the hash of the commit created by this push, not to be confused with a version number.

Example: "bab04ce"

interface PushPromptResult {
  promptId: string;
  hash: string;
}

promptIdstringRequired

This is the id of the prompt generated by Confident AI, not to be confused with the alias you supplied.

Example: "<PROMPT-ID>"

hashstringRequired

This is the hash of the commit created by this push, not to be confused with a version number.

Example: "bab04ce"

ReasoningEffort

This is the level of reasoning effort for the model.

class ReasoningEffort(Enum):
    MINIMAL = "MINIMAL"
    LOW = "LOW"
    MEDIUM = "MEDIUM"
    HIGH = "HIGH"

enum ReasoningEffort {
  MINIMAL = "MINIMAL",
  LOW = "LOW",
  MEDIUM = "MEDIUM",
  HIGH = "HIGH",
}

MINIMAL · LOW · MEDIUM · HIGH

Tool

A tool your prompts can call. Changing its mode or schema creates a new version.

class Tool:
    id: str
    name: str
    description: Optional[str]
    mode: ToolMode
    version: str
    schema_: Dict[str, Any] = Field(alias="schema")

idstrRequired

The id of the tool, generated by Confident AI.

Example: "<TOOL-ID>"

namestrRequired

The name of the tool, unique within the project.

Example: "get_customer_name"

descriptionOptional[str]Required

What the tool does.

Example: "Looks up the customer's name by id."

modeToolModeRequired

See ToolMode.

versionstrRequired

The version of the tool. A pulled prompt returns the version its commit pinned.

Example: "00.00.01"

schema_Dict[str, Any]Required

The JSON Schema for the tool's input. List each parameter under properties with a type, and name the mandatory ones in required. A parameter can also have a description, an enum of allowed values, or items for an array. Whether extra properties are allowed is set by mode.

Example: {"type":"object","properties":{"customerId":{"type":"string","description":"The id of the customer to look up."},"nameFormat":{"type":"string","enum":["FULL","FIRST"],"description":"Whether to return the full name or only the first name."}},"required":["customerId"]}

interface Tool {
  id: string;
  name: string;
  description: string | null;
  mode: ToolMode;
  version: string;
  schema: Record<string, unknown>;
}

idstringRequired

The id of the tool, generated by Confident AI.

Example: "<TOOL-ID>"

namestringRequired

The name of the tool, unique within the project.

Example: "get_customer_name"

descriptionstring | nullRequired

What the tool does.

Example: "Looks up the customer's name by id."

modeToolModeRequired

See ToolMode.

versionstringRequired

The version of the tool. A pulled prompt returns the version its commit pinned.

Example: "00.00.01"

schemaRecord<string, unknown>Required

ToolInput

A tool for the commit to pin. Omitted fields keep the values of the version being pinned, and a changed mode or schema creates a new version.

class ToolInput:
    id: Optional[str] = None
    version: Optional[str] = None
    name: Optional[str] = None
    description: Optional[str] = None
    mode: Optional[ToolMode] = None
    schema_: Optional[Dict[str, Any]] = Field(default=None, alias="schema")

idOptional[str]

The id of an existing tool. Omit it to use name instead.

Example: "<TOOL-ID>"

versionOptional[str]

The version to pin. Omit it to use the latest version.

Example: "00.00.01"

nameOptional[str]

The name of the tool. Without id, the tool with this name is used or created; with id, a new name renames it.

Example: "get_customer_name"

descriptionOptional[str]

What the tool does.

Example: "Looks up the customer's name by id."

modeOptional[ToolMode]

See ToolMode.

schema_Optional[Dict[str, Any]]

interface ToolInput {
  id?: string;
  version?: string;
  name?: string;
  description?: string | null;
  mode?: ToolMode;
  schema?: Record<string, unknown>;
}

idstring

The id of an existing tool. Omit it to use name instead.

Example: "<TOOL-ID>"

versionstring

The version to pin. Omit it to use the latest version.

Example: "00.00.01"

namestring

The name of the tool. Without id, the tool with this name is used or created; with id, a new name renames it.

Example: "get_customer_name"

descriptionstring | null

What the tool does.

Example: "Looks up the customer's name by id."

modeToolMode

See ToolMode.

schemaRecord<string, unknown>

ToolMode

This is the mode for your tool input fields, which controls whether fields outside the schema are allowed.

class ToolMode(Enum):
    ALLOW_ADDITIONAL = "ALLOW_ADDITIONAL"
    NO_ADDITIONAL = "NO_ADDITIONAL"
    STRICT = "STRICT"

enum ToolMode {
  ALLOW_ADDITIONAL = "ALLOW_ADDITIONAL",
  NO_ADDITIONAL = "NO_ADDITIONAL",
  STRICT = "STRICT",
}

ALLOW_ADDITIONAL · NO_ADDITIONAL · STRICT

Verbosity

This is the verbosity level for model output.

class Verbosity(Enum):
    LOW = "LOW"
    MEDIUM = "MEDIUM"
    HIGH = "HIGH"

enum Verbosity {
  LOW = "LOW",
  MEDIUM = "MEDIUM",
  HIGH = "HIGH",
}

LOW · MEDIUM · HIGH

Building a production pipeline?Design a scalable API workflow for evals, datasets, traces, and promptsTalk to an engineer

Last updated on October 19, 2026

Built byConfident AI