Update a custom agent
PATCH /api/agent-definitions/custom/{id}
Updates a custom specialist agent definition. You can modify the display name, description, model, instructions, and MCP tool assignments. Changes take effect immediately — the MCP hub cache is invalidated on update.
Authorizations
Section titled “Authorizations ”Parameters
Section titled “ Parameters ”Path Parameters
Section titled “Path Parameters ”The unique identifier of the custom agent to update.
Request Body
Section titled “Request Body ”object
Updated display name.
Updated description (read by the planner for dispatch decisions).
Updated LLM model ID.
Updated instructions. Set to null to clear.
Updated MCP connections and tool assignments. Replaces existing assignments entirely.
object
Responses
Section titled “ Responses ”The agent definition was updated.
An agent definition configures an AI agent within the conversation pipeline. oHallo uses a four-layer agent model: the planner determines intent and selects specialist agents, specialists execute domain-specific tasks via MCP tools, the message agent drafts the customer-facing reply, and the validator fact-checks the draft. You can create custom specialist agents and connect them to your MCP servers.
object
Unique identifier for the agent definition.
Example
ag1a2b3c-5678-9abc-def0-1234567890abThe tenant this agent belongs to.
Example
a0b1c2d3-4567-89ab-cdef-0123456789abInternal name used to identify the agent in logs and workflow execution records.
Example
shipping_trackerHuman-readable name shown in the dashboard.
Example
Shipping TrackerDescribes what this agent does. The planner agent reads this description to decide whether to dispatch to this specialist.
Example
Looks up shipping status, delivery dates, and tracking information using the logistics MCP server.The role this agent plays in the conversation pipeline. ‘planner’ analyzes intent and selects specialists. ‘specialist’ executes domain tasks via MCP tools. ‘message’ drafts the customer-facing reply. ‘validator’ fact-checks drafts against the knowledge base and conversation context.
Example
specialistThe LLM model ID used by this agent. When null, the platform default is used.
Example
claude-sonnet-4-6Additional instructions that guide this agent’s behavior. Appended to the system prompt. Use this to customize how the agent interprets data, formats responses, or handles edge cases.
Example
Always convert tracking dates to the customer's local timezone. If the shipment is delayed, proactively mention the estimated new delivery date.The MCP server connections this agent has access to, along with which specific tools it can invoke on each connection.
object
Reference to a registered MCP connection.
Example
mc1a2b3c-5678-9abc-def0-1234567890abList of tool names this agent is permitted to call on the connection. Empty array means no tools are allowed.
Example
[ "get_shipment_status", "get_tracking_url"]Timestamp when the agent was created.
Example
2026-02-15T10:00:00.000ZTimestamp when the agent was last updated.
Example
2026-03-20T16:30:00.000ZNo custom agent exists with the given ID. Note: platform agents cannot be updated via this endpoint — use the instructions endpoint instead.
Standard error response returned by all endpoints on failure.
object
A human-readable error message describing what went wrong.
Example
Conversation not foundValidation error.
Standard error response returned by all endpoints on failure.
object
A human-readable error message describing what went wrong.
Example
Conversation not found