Update Agent

Beta

PATCH/v1/ai/agents/{id}

Idempotent with Idempotency-Key header. Learn more

Updates a custom agent.

Only the fields provided in the request are changed. Augno's system agents cannot be edited — the only thing you can change about them is whether they are enabled for your account, with the Update Agent Status endpoint.

Permissions requiredValues:agents:update

The role behind your API key or agent must grant every one of these permissions.

idstring

Agent definition ID.

include[]optional arrayenumValues:configtoolsrole

Sub-objects to expand in the response. When omitted, sub-objects are returned as null.

nameoptional string

Human-readable name of the agent.

slugoptional string

URL-friendly identifier for the agent.

descriptionoptional stringnullable

Description of what the agent does.

Send null to clear the description; omit to leave it unchanged. Send null to clear.

category_codeoptional string

Category grouping for the agent (e.g. order_processing), used to organize agents in the UI.

trigger_typeoptional stringenumValues:scheduledmanualevent

How runs of this agent are initiated.

When changing the trigger type, also provide a config with a trigger_config appropriate for the new type (a cron schedule for scheduled, at least one event filter for event).

configoptional object

Agent-level configuration controlling LLM behavior and trigger settings.

Replaces the stored configuration in full rather than merging into it, so send every setting you want to keep — anything you leave out is cleared.

system_promptoptional string

Instructions that define the agent's role and how it should behave.

Sent to the model on every turn of a run, alongside the platform guidance Augno adds automatically.

tieroptional stringenumValues:frontierhighbalanced

Intelligence and cost tier for the agent's reasoning. Defaults to high.

Selects how capable (and how expensive) a model the agent uses without pinning a specific model, so the agent keeps working as the underlying model catalog changes.

frontier: the most capable and most expensive; multi-step planning, ambiguous work, tool-heavy workflows.
high: normal planning, synthesis, and customer-facing reasoning.
balanced: research, summarization, classification, structured extraction, and light tool use.
cheap: simple transforms, validation, formatting, keyword lookup, and routing.
legacy: older models kept for compatibility and regression comparison; avoid unless you specifically need them.

temperatureoptional number

How much randomness the model uses when generating text.

Lower values make the agent's output more repeatable; higher values make it more varied.

trigger_configoptional object

Trigger-specific configuration.

Required contents depend on the agent's trigger_type; see the trigger config schema.

cron_scheduleoptional string

Cron expression for scheduled triggers (e.g. 0 9 * * *).

timezoneoptional string

IANA timezone for the cron schedule (e.g. America/New_York).

event_filtersoptional array of string

Event types that trigger this agent (e.g. ["email.received", "order.created"]).

endpoint_tool_slugsoptional array of string

API-endpoint tools the agent may discover and use, by slug (e.g. create_account_group).

These are the tools listed by the List Tools endpoint with category api_endpoint. The single entry * grants the entire endpoint-tool catalog. Omit or leave empty to grant none.

endpoint_tool_reviewoptional object

Per-endpoint-tool human-review overrides, keyed by tool slug.

Set a slug to true to require human approval before the agent may execute that endpoint-tool; the run pauses in awaiting_approval until approved via the Continue Agent Run endpoint. Slugs omitted from the map do not require review.

toolsoptional array of object

Built-in tools to attach to the agent.

Replaces the existing tool set when provided.

toolstringenumValues:create_artifactread_docfetch_url

The built-in tool to attach.

Only Augno's built-in tools are attached here. Access to API-endpoint tools (creating a customer, listing orders, and so on) is granted separately through config.endpoint_tool_slugs. The List Tools endpoint (GET /v1/ai/tools) returns both kinds, with API-endpoint tools in the api_endpoint category.

config_jsonoptional string

JSON-encoded configuration for this tool instance.

The expected structure depends on the tool (see the tool's config_schema).

sort_orderoptional integer

Display order among the agent's tools (lower values appear first).

require_reviewoptional boolean

Whether actions from this tool require human review before they execute.

When review is required, a call to this tool pauses the run in awaiting_approval and records an action in pending_review until someone approves or rejects it through the Continue Agent Run endpoint. Approvals are one-time, so a later call to the same tool pauses again.

role_idoptional stringnullable

ID of the role that defines the permissions the agent operates with.

Send null to detach the role; omit to leave it unchanged. An agent with no role cannot execute, so detaching the role makes its runs fail immediately. Send null to clear.

idstring

Agent definition ID.

objectstringenumValues:agent_definition

Resource type identifier.

definition_typestringenumValues:systemcustom

Whether the agent is provided by Augno or created in this account.

system: provided by Augno; cannot be edited or deleted.
custom: created by a user in this account.

category_codestring

Category grouping for the agent (e.g. order_processing), used to organize agents in the UI.

trigger_typestringenumValues:scheduledmanualevent

How runs of this agent are initiated.

scheduled: runs on a cron schedule (see config.trigger_config.cron_schedule).
event: runs in response to platform events (see config.trigger_config.event_filters).
manual: runs only when explicitly invoked.
chat: runs in response to a chat message; the run is linked to a conversation and posts its reply back into it.

namestring

Human-readable name of the agent.

slugstring

URL-friendly identifier for the agent.

Unique within the account.

descriptionstringnullable

Description of what the agent does.

editabilitystringenumValues:editableread_only

Whether this agent definition can be edited.

Always read_only for system definitions.

statusstringenumValues:activeinactive

Whether this agent is enabled for the current account.

Activation is per-account: a system agent shared across accounts can be active for one account and inactive for another. An inactive agent cannot be triggered.

roleroleExpandablenullable

Role defining the permissions the agent operates with.

The agent acts as its own actor, and everything it does is authorized against this role — it can never reach data or actions the role does not grant. An agent with no role cannot execute: its runs fail immediately.

idstring

Role ID.

objectstringenumValues:role

Resource type identifier.

namestring

Display name of the role.

Unique within the account.

typestringenumValues:adminuserscanner

The kind of role.

The type gates behavior that individual permissions do not cover, and some actions are reserved for a single role type.

admin: full administrative access. Sensitive areas such as API keys, billing, and third-party integrations are restricted to admins no matter what permissions another role holds.
user: a custom role tailored to a specific need, with its permissions defined explicitly. Roles created through the API always have this type.
scanner: the role used by shop-floor scanning stations, assigned automatically when a scanning-station user is created.
sales_rep: a role for sales representatives. Order analytics are scoped to the rep's own orders.
agent: a role assigned to an automated agent rather than a person.

ownerownernullable

Provenance of this role.

System-owned roles are platform-provided defaults shared across all accounts and cannot be updated or deleted; account-owned roles are custom to your account.

Always returned as null in this endpoint.

permissionsarray of stringExpandablenullable

Permissions granted by this role, in {permission}:{action} format, such as customers:read.

created_atstring (date-time)

Creation timestamp.

updated_atstring (date-time)

Last updated timestamp.

configagent_definition_configExpandablenullable

Agent-level configuration controlling LLM behavior and trigger settings.

objectstringenumValues:agent_definition_config

Resource type identifier.

system_promptstringnullable

Standing instructions that define the agent's role and how it should behave on every run.

tierstringnullableenumValues:frontierhighbalanced

Intelligence and cost tier for the agent's reasoning.

Selects how capable and expensive a model the agent uses without pinning a specific model; higher tiers reason better but cost more. Each tier resolves to an ordered chain of equivalent models, so a run automatically fails over to another provider's model if the preferred one is unavailable.

frontier: the most capable tier, for multi-step planning, ambiguous agent work, and hard coding or architecture tasks.
high: for normal planning, code edits, synthesis, and customer-facing reasoning.
balanced: for research, summarization, classification, structured extraction, and light tool use.
cheap: for simple transforms, validation, formatting, and routing.
legacy: older-generation models kept for compatibility and regression comparison; avoid unless you specifically need them.

Leaving the tier unset picks one from how the agent is triggered: chat and manual runs use high, while scheduled and event-driven runs use balanced so background work stays cheap.

temperaturenumbernullable

LLM sampling temperature between 0 and 1.

Lower values make the agent's output more repeatable and literal; higher values make it more varied.

trigger_configtrigger_confignullable

Trigger-specific configuration.

Shape depends on the agent's trigger_type.

Always returned as null in this endpoint.

endpoint_tool_slugsarray of string

API-endpoint tools the agent may discover and use, by slug (e.g. create_account_group).

These correspond to tools listed by the List Tools endpoint with category api_endpoint. A single entry * grants the entire endpoint-tool catalog.

endpoint_tool_reviewobject

Per-endpoint-tool human-review overrides, keyed by tool slug.

When an entry is true, the run pauses in awaiting_approval each time the agent calls that endpoint-tool until it is approved via the Continue Agent Run endpoint. Slugs absent from the map do not require review.

toolslistExpandablenullable

Tools attached to this agent.

objectstringenumValues:list

Resource type identifier.

page_infoobject

Pagination metadata.

next_page_urlstringnullable

Relative URL that fetches the next page of results.

previous_page_urlstringnullable

Relative URL that fetches the previous page of results.

has_next_pageboolean

Whether more results exist after this page.

has_prev_pageboolean

Whether results exist before this page.

dataarray of agent_definition_tool

Resources in this page.

idstring

Agent definition tool ID.

objectstringenumValues:agent_definition_tool

Resource type identifier.

toolavailable_tool

Attached tool.

Always returned as null in this endpoint.

review_requirementstringenumValues:not_requiredrequired

Whether calls to this tool must be approved by a user before they execute.

When required, the run pauses in the awaiting_approval status each time the agent invokes this tool; approve or allow the tool via the Continue Agent Run endpoint to proceed. A tool whose mutating flag is true still pauses for approval even when this is not_required.

configobjectnullable

Instance-specific configuration for this tool.

Must conform to the tool's config_schema.

Encoded as a JSON value (object, array, string, number, boolean, or null), not a JSON-encoded string.

sort_orderinteger

Sort order within the agent.

created_atstring (date-time)

Creation timestamp.

updated_atstring (date-time)

Last updated timestamp.

Responses

200

Successful response for Update Agent

Update Agent

import Augno from '@augno/sdk';

const client = new Augno({
  bearerToken: 'YOUR_API_KEY', // Your API key goes here
});

const agentDefinition = await client.ai.agents.update('agdf_ah7tkyfxk8jl', {
  name: 'Inventory Monitor',
});

console.log(agentDefinition.id);

import Augno from '@augno/sdk';

const client = new Augno({
  bearerToken: 'YOUR_API_KEY', // Your API key goes here
});

const agentDefinition = await client.ai.agents.update('agdf_ah7tkyfxk8jl', {
  name: 'Inventory Monitor',
});

console.log(agentDefinition.id);

200 example

{
  "id": "agdf_ah7tkyfxk8jl",
  "object": "agent_definition",
  "definition_type": "system",
  "category_code": "order_processing",
  "trigger_type": "event",
  "name": "Email Order Agent",
  "slug": "email_order",
  "description": "Processes incoming emails and creates draft orders.",
  "editability": "read_only",
  "status": "inactive",
  "role": {
    "id": "rl_3xknmfqflhvb",
    "object": "role",
    "name": "Admin",
    "type": "admin",
    "owner": null,
    "permissions": [
      "customers:create",
      "customers:read",
      "customers:update",
      "customers:delete"
    ],
    "created_at": "2026-05-10T00:00:00Z",
    "updated_at": "2026-05-10T00:23:00Z"
  },
  "config": {
    "object": "agent_definition_config",
    "system_prompt": "You are an order processing agent. Parse incoming emails and create draft orders.",
    "tier": "high",
    "temperature": 0.2,
    "trigger_config": null,
    "endpoint_tool_slugs": [
      "create_account_group"
    ],
    "endpoint_tool_review": {
      "create_account_group": true
    }
  },
  "tools": {
    "object": "list",
    "page_info": {
      "next_page_url": null,
      "previous_page_url": null,
      "has_next_page": false,
      "has_prev_page": false
    },
    "data": [
      {
        "id": "agdftl_iyc1asmsg1pu",
        "object": "agent_definition_tool",
        "tool": null,
        "review_requirement": "not_required",
        "config": {},
        "sort_order": 0
      }
    ]
  },
  "created_at": "2026-05-10T00:00:00Z",
  "updated_at": "2026-05-10T00:23:00Z"
}

{
  "id": "agdf_ah7tkyfxk8jl",
  "object": "agent_definition",
  "definition_type": "system",
  "category_code": "order_processing",
  "trigger_type": "event",
  "name": "Email Order Agent",
  "slug": "email_order",
  "description": "Processes incoming emails and creates draft orders.",
  "editability": "read_only",
  "status": "inactive",
  "role": {
    "id": "rl_3xknmfqflhvb",
    "object": "role",
    "name": "Admin",
    "type": "admin",
    "owner": null,
    "permissions": [
      "customers:create",
      "customers:read",
      "customers:update",
      "customers:delete"
    ],
    "created_at": "2026-05-10T00:00:00Z",
    "updated_at": "2026-05-10T00:23:00Z"
  },
  "config": {
    "object": "agent_definition_config",
    "system_prompt": "You are an order processing agent. Parse incoming emails and create draft orders.",
    "tier": "high",
    "temperature": 0.2,
    "trigger_config": null,
    "endpoint_tool_slugs": [
      "create_account_group"
    ],
    "endpoint_tool_review": {
      "create_account_group": true
    }
  },
  "tools": {
    "object": "list",
    "page_info": {
      "next_page_url": null,
      "previous_page_url": null,
      "has_next_page": false,
      "has_prev_page": false
    },
    "data": [
      {
        "id": "agdftl_iyc1asmsg1pu",
        "object": "agent_definition_tool",
        "tool": null,
        "review_requirement": "not_required",
        "config": {},
        "sort_order": 0
      }
    ]
  },
  "created_at": "2026-05-10T00:00:00Z",
  "updated_at": "2026-05-10T00:23:00Z"
}

Update Agent

Authorization

Path Parameters

Query Parameters

Request Body

Returns

Responses