Create a new agent

curl --request POST \
  --url https://a.api.mindset.ai/api/v2/appuid/{appUid}/agents \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "agentName": "<string>",
  "agentPurpose": "<string>",
  "templateAgentUid": "<string>",
  "personality": {
    "preset": "friendly",
    "customText": "<string>"
  },
  "formatting": {
    "preset": "conversational",
    "customText": "<string>"
  },
  "policies": {
    "focusAndScope": {
      "enabled": false,
      "scope": "<string>"
    },
    "knowledgeLimits": {
      "enabled": false,
      "themeSpecificAllowance": "<string>"
    },
    "nonContextSegmentMessage": {
      "enabled": false,
      "message": "<string>"
    },
    "clarification": {
      "enabled": false
    },
    "recommendations": {
      "enabled": false
    },
    "neutrality": {
      "enabled": false
    },
    "professionalConduct": {
      "enabled": false
    },
    "legalFinancial": {
      "enabled": false
    },
    "safeguarding": {
      "enabled": false,
      "email": "[email protected]"
    },
    "feedback": {
      "enabled": false
    }
  },
  "additionalPolicyRules": "<string>",
  "additionalInformation": "<string>",
  "iceBreakerMessage": "<string>",
  "memory": {
    "allowAccess": false,
    "allowContribution": false,
    "miningGuidance": "<string>"
  },
  "live": false,
  "contextUids": [
    "<string>"
  ],
  "mcpserverUids": [
    "<string>"
  ],
  "tags": [
    "<string>"
  ],
  "access": "restrictedAccess",
  "externalTenantId": "<string>"
}
'

{
  "uid": "<string>",
  "agentName": "<string>",
  "agentPurpose": "<string>",
  "personality": {
    "preset": "friendly",
    "customText": "<string>"
  },
  "formatting": {
    "preset": "conversational",
    "customText": "<string>"
  },
  "policies": {
    "focusAndScope": {
      "enabled": false,
      "scope": "<string>"
    },
    "knowledgeLimits": {
      "enabled": false,
      "themeSpecificAllowance": "<string>"
    },
    "nonContextSegmentMessage": {
      "enabled": false,
      "message": "<string>"
    },
    "clarification": {
      "enabled": false
    },
    "recommendations": {
      "enabled": false
    },
    "neutrality": {
      "enabled": false
    },
    "professionalConduct": {
      "enabled": false
    },
    "legalFinancial": {
      "enabled": false
    },
    "safeguarding": {
      "enabled": false,
      "email": "[email protected]"
    },
    "feedback": {
      "enabled": false
    }
  },
  "additionalPolicyRules": "<string>",
  "additionalInformation": "<string>",
  "iceBreakerMessage": "<string>",
  "memory": {
    "allowAccess": false,
    "allowContribution": false,
    "miningGuidance": "<string>"
  },
  "live": true,
  "contextUids": [
    "<string>"
  ],
  "mcpserverUids": [
    "<string>"
  ],
  "tags": [
    "<string>"
  ],
  "access": "openAccess",
  "externalTenantId": "<string>",
  "createdAt": "2023-11-07T05:31:56Z"
}

POST

api

appuid

{appUid}

agents

Create a new agent

curl --request POST \
  --url https://a.api.mindset.ai/api/v2/appuid/{appUid}/agents \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "agentName": "<string>",
  "agentPurpose": "<string>",
  "templateAgentUid": "<string>",
  "personality": {
    "preset": "friendly",
    "customText": "<string>"
  },
  "formatting": {
    "preset": "conversational",
    "customText": "<string>"
  },
  "policies": {
    "focusAndScope": {
      "enabled": false,
      "scope": "<string>"
    },
    "knowledgeLimits": {
      "enabled": false,
      "themeSpecificAllowance": "<string>"
    },
    "nonContextSegmentMessage": {
      "enabled": false,
      "message": "<string>"
    },
    "clarification": {
      "enabled": false
    },
    "recommendations": {
      "enabled": false
    },
    "neutrality": {
      "enabled": false
    },
    "professionalConduct": {
      "enabled": false
    },
    "legalFinancial": {
      "enabled": false
    },
    "safeguarding": {
      "enabled": false,
      "email": "[email protected]"
    },
    "feedback": {
      "enabled": false
    }
  },
  "additionalPolicyRules": "<string>",
  "additionalInformation": "<string>",
  "iceBreakerMessage": "<string>",
  "memory": {
    "allowAccess": false,
    "allowContribution": false,
    "miningGuidance": "<string>"
  },
  "live": false,
  "contextUids": [
    "<string>"
  ],
  "mcpserverUids": [
    "<string>"
  ],
  "tags": [
    "<string>"
  ],
  "access": "restrictedAccess",
  "externalTenantId": "<string>"
}
'

{
  "uid": "<string>",
  "agentName": "<string>",
  "agentPurpose": "<string>",
  "personality": {
    "preset": "friendly",
    "customText": "<string>"
  },
  "formatting": {
    "preset": "conversational",
    "customText": "<string>"
  },
  "policies": {
    "focusAndScope": {
      "enabled": false,
      "scope": "<string>"
    },
    "knowledgeLimits": {
      "enabled": false,
      "themeSpecificAllowance": "<string>"
    },
    "nonContextSegmentMessage": {
      "enabled": false,
      "message": "<string>"
    },
    "clarification": {
      "enabled": false
    },
    "recommendations": {
      "enabled": false
    },
    "neutrality": {
      "enabled": false
    },
    "professionalConduct": {
      "enabled": false
    },
    "legalFinancial": {
      "enabled": false
    },
    "safeguarding": {
      "enabled": false,
      "email": "[email protected]"
    },
    "feedback": {
      "enabled": false
    }
  },
  "additionalPolicyRules": "<string>",
  "additionalInformation": "<string>",
  "iceBreakerMessage": "<string>",
  "memory": {
    "allowAccess": false,
    "allowContribution": false,
    "miningGuidance": "<string>"
  },
  "live": true,
  "contextUids": [
    "<string>"
  ],
  "mcpserverUids": [
    "<string>"
  ],
  "tags": [
    "<string>"
  ],
  "access": "openAccess",
  "externalTenantId": "<string>",
  "createdAt": "2023-11-07T05:31:56Z"
}

Authorizations

x-api-key

string

header

required

Path Parameters

appUid

string

required

Your application's uid

Minimum string length: 1

Body

application/json

agentName

string

required

Name of the agent

Required string length: 1 - 50

agentPurpose

string

required

Purpose of the agent

Required string length: 1 - 1000

templateAgentUid

string

UID of an existing agent to use as a template for sources presentation options (citations, references etc)

personality

object

Agent personality configuration

Show child attributes

personality.preset

enum<string>

default:friendly

Personality preset. Use 'custom' to provide your own personality text.

Available options:

friendly,

professional,

analytical,

strict,

custom

personality.customText

string

Custom personality text (required if preset is 'custom', ignored otherwise)

Required string length: 1 - 500

formatting

object

Agent response formatting configuration

Show child attributes

formatting.preset

enum<string>

default:conversational

Formatting preset. Use 'custom' to provide your own formatting instructions.

Available options:

conversational,

structured,

storytelling,

technical,

custom

formatting.customText

string

Custom formatting text (required if preset is 'custom', ignored otherwise)

Required string length: 1 - 500

policies

object

Agent policy configuration with 10 toggleable policies

Show child attributes

policies.focusAndScope

object

Focus and Scope policy - restricts agent to specific topics

Show child attributes

policies.focusAndScope.enabled

boolean

default:false

policies.focusAndScope.scope

string

The scope of topics the agent should focus on (required when enabled)

Maximum string length: 65535

policies.knowledgeLimits

object

Knowledge Limits and Apologies policy - handles out-of-context queries

Show child attributes

policies.knowledgeLimits.enabled

boolean

default:false

policies.knowledgeLimits.themeSpecificAllowance

string

Themes the agent can discuss when out of context (optional)

Maximum string length: 65535

policies.nonContextSegmentMessage

object

Non-Context Segment Message policy - custom message for out-of-context responses

Show child attributes

policies.nonContextSegmentMessage.enabled

boolean

default:false

policies.nonContextSegmentMessage.message

string

Message to display for non-context segments (required when enabled)

Maximum string length: 65535

policies.clarification

object

Clarification and User Understanding policy - helps users understand responses better

Show child attributes

policies.clarification.enabled

boolean

default:false

policies.recommendations

object

Recommendations and Examples policy - provides suggestions and examples in responses

Show child attributes

policies.recommendations.enabled

boolean

default:false

policies.neutrality

object

Neutrality policy - uses gender-neutral speaker references

Show child attributes

policies.neutrality.enabled

boolean

default:false

policies.professionalConduct

object

Professional Conduct and Bias policy - maintains professional tone and avoids bias

Show child attributes

policies.professionalConduct.enabled

boolean

default:false

policies.legalFinancial

object

Avoid Legal and Financial Advice policy - prevents giving legal or financial guidance

Show child attributes

policies.legalFinancial.enabled

boolean

default:false

policies.safeguarding

object

Safeguarding policy - handles sensitive/mental health disclosures

Show child attributes

policies.safeguarding.enabled

boolean

default:false

policies.safeguarding.email

string<email>

Contact email for safeguarding issues (required when enabled)

Maximum string length: 65535

policies.feedback

object

Feedback Encouragement policy - encourages users to provide feedback

Show child attributes

policies.feedback.enabled

boolean

default:false

additionalPolicyRules

string

Additional free-form policy rules

Maximum string length: 500

additionalInformation

string

Additional context information for the agent

Maximum string length: 65535

iceBreakerMessage

string

Invisible instruction to prompt the agent to greet users in a specific way

Maximum string length: 1000

memory

object

Agent memory configuration. Note: Memory access must be enabled at the app level for these settings to take effect.

Show child attributes

memory.allowAccess

boolean

default:false

Allow agent to access memory

memory.allowContribution

boolean

default:false

Allow agent to contribute to memory

memory.miningGuidance

string

Guidance for memory mining

Maximum string length: 500

live

boolean

default:false

Agent is active and live for end users

contextUids

string[]

Array of existing context UIDs (max 30)

Maximum array length: 30

mcpserverUids

string[]

Array of existing MCP server UIDs (max 5)

Maximum array length: 5

Response

Agent created successfully

uid

string

Unique ID of the agent

agentName

string

Name of the agent

agentPurpose

string

Purpose of the agent

personality

object

Agent personality configuration

Show child attributes

personality.preset

enum<string>

default:friendly

Personality preset. Use 'custom' to provide your own personality text.

Available options:

friendly,

professional,

analytical,

strict,

custom

personality.customText

string

Custom personality text (required if preset is 'custom', ignored otherwise)

Required string length: 1 - 500

formatting

object

Agent response formatting configuration

Show child attributes

formatting.preset

enum<string>

default:conversational

Formatting preset. Use 'custom' to provide your own formatting instructions.

Available options:

conversational,

structured,

storytelling,

technical,

custom

formatting.customText

string

Custom formatting text (required if preset is 'custom', ignored otherwise)

Required string length: 1 - 500

policies

object

Agent policy configuration with 10 toggleable policies

Show child attributes

policies.focusAndScope

object

Focus and Scope policy - restricts agent to specific topics

Show child attributes

policies.focusAndScope.enabled

boolean

default:false

policies.focusAndScope.scope

string

The scope of topics the agent should focus on (required when enabled)

Maximum string length: 65535

policies.knowledgeLimits

object

Knowledge Limits and Apologies policy - handles out-of-context queries

Show child attributes

policies.knowledgeLimits.enabled

boolean

default:false

policies.knowledgeLimits.themeSpecificAllowance

string

Themes the agent can discuss when out of context (optional)

Maximum string length: 65535

policies.nonContextSegmentMessage

object

Non-Context Segment Message policy - custom message for out-of-context responses

Show child attributes

policies.nonContextSegmentMessage.enabled

boolean

default:false

policies.nonContextSegmentMessage.message

string

Message to display for non-context segments (required when enabled)

Maximum string length: 65535

policies.clarification

object

Clarification and User Understanding policy - helps users understand responses better

Show child attributes

policies.clarification.enabled

boolean

default:false

policies.recommendations

object

Recommendations and Examples policy - provides suggestions and examples in responses

Show child attributes

policies.recommendations.enabled

boolean

default:false

policies.neutrality

object

Neutrality policy - uses gender-neutral speaker references

Show child attributes

policies.neutrality.enabled

boolean

default:false

policies.professionalConduct

object

Professional Conduct and Bias policy - maintains professional tone and avoids bias

Show child attributes

policies.professionalConduct.enabled

boolean

default:false

policies.legalFinancial

object

Avoid Legal and Financial Advice policy - prevents giving legal or financial guidance

Show child attributes

policies.legalFinancial.enabled

boolean

default:false

policies.safeguarding

object

Safeguarding policy - handles sensitive/mental health disclosures

Show child attributes

policies.safeguarding.enabled

boolean

default:false

policies.safeguarding.email

string<email>

Contact email for safeguarding issues (required when enabled)

Maximum string length: 65535

policies.feedback

object

Feedback Encouragement policy - encourages users to provide feedback

Show child attributes

policies.feedback.enabled

boolean

default:false

additionalPolicyRules

string

Additional free-form policy rules

additionalInformation

string

Additional context information for the agent

iceBreakerMessage

string

Invisible instruction to prompt the agent to greet users in a specific way

memory

object

Agent memory configuration. Note: Memory access must be enabled at the app level for these settings to take effect.

Show child attributes

memory.allowAccess

boolean

default:false

Allow agent to access memory

memory.allowContribution

boolean

default:false

Allow agent to contribute to memory

memory.miningGuidance

string

Guidance for memory mining

Maximum string length: 500

live

boolean

Agent is active and live for end users

contextUids

string[]

Array of context UIDs

mcpserverUids

string[]

Array of MCP server UIDs

Overview

Integrate Agent Chat SDK 2

MCP Server Integration

AMS SDK Integration

API Overview

API playground

Webhooks

Create a new agent

Authorizations

Path Parameters

Body

Response