Update agent v1

curl --request PATCH \
  --url https://flow.seekr.com/v1/flow/agents/{agent_id} \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "My Agent",
  "instructions": "You are a helpful assistant that can search files, browse the web, and run Python code.",
  "model_id": "deployment-123",
  "temperature": 0.4,
  "reasoning_effort": "medium",
  "tool_ids": [
    "tool-123",
    "tool-456"
  ]
}
'

{
  "id": "<string>",
  "name": "<string>",
  "instructions": "<string>",
  "status": "Inactive",
  "reasoning_effort": "low",
  "user_id": "<string>",
  "team_id": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "model_id": "<string>",
  "planner_model_id": "<string>",
  "tool_model_id": "<string>",
  "output": {
    "frequency": "always",
    "instructions": "<string>",
    "model_id": "<string>",
    "temperature": 1
  },
  "temperature": 1,
  "planner_temperature": 1,
  "tools": [
    {
      "name": "file_search",
      "tool_env": {
        "FILE_SEARCH_INDEX": "<string>",
        "DOCUMENT_TOOL_DESC": "<string>",
        "EMBEDDING_MODEL": "<string>",
        "TOP_K": 10,
        "SCORE_THRESHOLD": 0
      },
      "id": "<string>"
    }
  ],
  "last_deployed_at": "2023-11-07T05:31:56Z",
  "active_duration": 0
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

PATCH

flow

agents

{agent_id}

curl --request PATCH \
  --url https://flow.seekr.com/v1/flow/agents/{agent_id} \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "My Agent",
  "instructions": "You are a helpful assistant that can search files, browse the web, and run Python code.",
  "model_id": "deployment-123",
  "temperature": 0.4,
  "reasoning_effort": "medium",
  "tool_ids": [
    "tool-123",
    "tool-456"
  ]
}
'

{
  "id": "<string>",
  "name": "<string>",
  "instructions": "<string>",
  "status": "Inactive",
  "reasoning_effort": "low",
  "user_id": "<string>",
  "team_id": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "model_id": "<string>",
  "planner_model_id": "<string>",
  "tool_model_id": "<string>",
  "output": {
    "frequency": "always",
    "instructions": "<string>",
    "model_id": "<string>",
    "temperature": 1
  },
  "temperature": 1,
  "planner_temperature": 1,
  "tools": [
    {
      "name": "file_search",
      "tool_env": {
        "FILE_SEARCH_INDEX": "<string>",
        "DOCUMENT_TOOL_DESC": "<string>",
        "EMBEDDING_MODEL": "<string>",
        "TOP_K": 10,
        "SCORE_THRESHOLD": 0
      },
      "id": "<string>"
    }
  ],
  "last_deployed_at": "2023-11-07T05:31:56Z",
  "active_duration": 0
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

Use PATCH /v2/flow/agents/{agent_id} instead of this deprecated endpoint.

Active agents transition to Updating during the patch and return to Active once complete. If redeployment fails, the agent status is set to Failed. Agents in Inactive or Failed states remain in their current state after a patch. To activate an updated agent, promote it manually. The tool_ids parameter accepts IDs for any tool type, including agent-as-tools. Agent-as-tools must be created before adding them to tool_ids. See Agent as tool for setup instructions.

Authorizations

Authorization

string

header

required

Your Seekr API key, sent in the Authorization header with no 'Bearer' prefix.

Path Parameters

agent_id

string

required

ID of the agent.

Body

application/json

name

string | null

New name for the agent.

Maximum string length: 256

instructions

string | null

Instructions that tell the agent how to behave.

Maximum string length: 32768

model_id

string | null

ID of the model the agent uses to respond.

Maximum string length: 32768

planner_model_id

string | null

ID of the model the agent uses to plan its work.

Maximum string length: 32768

tool_model_id

string | null

ID of the model the agent uses when it calls tools.

Maximum string length: 32768

output

AgentOutputConfig · object | null

Optional configuration for the agent's final response. Overrides the top-level settings for response generation.

Show child attributes

temperature

number | null

Controls the predictability of the agent's reasoning. Accepts a value from 0 to 2. Defaults to 0.6. Lower values produce more consistent results, and higher values introduce more variation.

Required range: 0 <= x <= 2

tool_ids

string[] | null

IDs of the tools the agent can use.

Maximum string length: 32768

reasoning_effort

enum<string> | null

Controls how much reasoning the agent uses when it works through a request.

Available options:

low,

medium,

high,

speed_optimized,

performance_optimized

Response

Success

string

required

ID of the agent.

name

string

required

Name of the agent.

instructions

string

required

Instructions that tell the agent how to behave.

status

enum<string>

required

Available options:

Inactive,

Pending,

Active,

Updating,

Failed

reasoning_effort

enum<string>

required

Controls how much reasoning the agent uses when working through a request. Accepts low, medium, or high, where higher levels produce more thorough reasoning. The speed_optimized and performance_optimized values are only supported for backward compatibility. speed_optimized maps to low, and performance_optimized maps to high.

Available options:

low,

medium,

high,

speed_optimized,

performance_optimized

user_id

string

required

ID of the user who owns the agent.

team_id

string | null

required

ID of the team the agent belongs to.

created_at

string<date-time>

required

Time the agent was created, in ISO 8601 format.

updated_at

string<date-time>

required

Time the agent was last updated, in ISO 8601 format.

model_id

string | null

ID of the model the agent uses to respond.

planner_model_id

string | null

ID of the model the agent uses to plan its work.

tool_model_id

string | null

ID of the model the agent uses when it calls tools.

output

AgentOutputConfig · object | null

Optional configuration for the agent's final response. Overrides the top-level settings for response generation.

Show child attributes

temperature

number | null

Controls the predictability of the agent's reasoning. Accepts a value from 0 to 2. Defaults to 0.6. Lower values produce more consistent results, and higher values introduce more variation.

Required range: 0 <= x <= 2

planner_temperature

number | null

Controls the predictability of the agent's planning. Lower values produce more consistent plans, and higher values introduce more variation.

Required range: 0 <= x <= 2

tools

(FileSearch · object | WebSearch · object | RunPython · object | AgentAsTool · object | MCPConnectorTool · object)[]

Tools the agent can use.

FileSearch
WebSearch
RunPython
AgentAsTool
MCPConnectorTool

Show child attributes

last_deployed_at

string<date-time> | null

Time the agent was last deployed, in ISO 8601 format.

active_duration

integer

default:0

Required range: x >= 0

Last modified on November 4, 2026

⌘I

Overview

Endpoints

Authorizations

Path Parameters

Body

Response