Mocks
Open in CMSThe Tool Mocks screen is where you build reusable mock sets: scripted answers for your agent's tools, so conversation simulations run against predictable responses instead of calling real tools. Found in the agent sidebar under Simulation → Mocks; this menu item appears only when the Mocks feature is enabled. You attach mock sets to a conversation in the Tool Mocks card of the Scenarios form.
Mock Set List
| New Mock Set | Opens the editor for a new library mock set. |
| Show Filters / Hide Filters | Opens or closes the filter panel. |
| Name | Filter: shows only mock sets whose name contains the text you type. |
| Tool | Filter: shows only mock sets that mock the selected tool. |
| Apply / Reset | Applies the filters, or clears them. |
| Sort By | Orders the list by Updated Date (default, newest first) or Name, Ascending or Descending. |
| Grid View / List View | Shows mock sets as cards or as a table (columns Name, Tools · cases, Used in, Updated). |
| Mock set card or row | Shows the name, description, how many tools and cases it has, the tool names, and how many conversations use it. Click it to open the editor. |
| ⋮ menu | Edit, Duplicate (creates a copy), Delete. |
| Delete | Asks for confirmation. If the set is still attached to conversations, This mock set is in use lists where, and the confirm button removes it from those conversations and then deletes it. |
| Load More | Shown when more mock sets are available. |
| Empty state | No Mock Sets Yet until you create the first one. |
Mock Set Editor: Header
The editor opens as New Mock Set, or with the set's name when editing. It always edits a Library set (shared, reusable by any conversation).
| Used in n conversations | Edit mode only. Opens a list of the conversations (and steps) that use this set. |
| Save | Saves the mock set. If someone else changed it in the meantime, you are asked to reload it. |
| Duplicate | Edit mode only. Creates a copy of the set. |
| Name | Required. For example "Doctor scheduling, happy path". |
| Description | Optional. What this mock set is for. |
Mock Set Editor: Tools in This Set
| Tools in this set | The tools this set mocks. Select one to edit its cases on the right. |
| Add tool | Opens a searchable list of the tools of the published agent (the version simulations run against). Pick a tool to add it. |
| Tool not found in the published agent | Shown on a tool that no longer exists in the published agent. Use Re-bind to… to point its cases at another tool. |
| Remove (trash icon) | Removes the tool and its cases from the set. |
Mock Set Editor: Cases
Each case is one scripted answer, used when the tool is called with matching arguments. Cases are checked in order.
| Add case | Adds a new case for the selected tool. |
| Case label | Optional name for the case (shown as "Untitled case" when empty). Drag to reorder; duplicate or delete with the icons. |
| When all of these match | The conditions on the tool's arguments. Add condition adds one (up to 20 per case). The case only answers when every condition holds; arguments without a condition can have any value. A case with no conditions matches every call, so cases below it are never reached. |
| Advanced — Match raw arguments | Optional extra match on the raw arguments JSON, checked in addition to the conditions. |
| Respond with | What the tool returns for this case. See Mock Set Editor: Response below. |
A tool can have up to 50 cases.
Mock Set Editor: Conditions
Each condition is an argument, a comparison and a value.
| Argument | One of the tool's inputs. |
| Comparison (Text, also lists, objects and unknown types) | is, is not, contains, starts with, ends with, matches pattern (regular expression), is one of (comma-separated values), is empty, is not empty. |
| Comparison (Number) | =, ≠, <, ≤, >, ≥, is between (minimum and maximum, inclusive). |
| Comparison (Yes/no) | is true, is false. |
| Comparison (Any type) | is present, is missing. |
| Value | The value to compare with. Not needed for is empty, is not empty, is true, is false, is present and is missing. |
| Aa (Match case) | Off by default, so text comparisons ignore upper and lower case. Turn it on to compare case-sensitively. |
| Remove condition (×) | Removes the condition. |
Mock Set Editor: Response
The same controls appear for a case and for the Otherwise default.
| JSON / Text | The format of the response body (up to 64 KB). |
| Success / Error | Opens ready-made templates for the tool, for example an empty list, Not found (404), Unauthorized (401), Rate limited (429), Invalid request (400) or Service down or timed out for a Custom API, Query fails or No rows found for a table query, Tool error or Empty text for an MCP tool. |
| Status | Custom API only. The HTTP status code returned (default 200 OK). A 5xx code reaches the agent as an empty result, as with a real failing API. |
| Content / MCP error | MCP tools only. Whether the body is normal content or an MCP error. |
| Suggest | Lets AI draft a response for this case. |
| Use a real response | Only for Custom APIs that use GET; fills the response from a real call. Locked for other tools because calling them could create real data. |
| Fetch a sample | Only for tools that read data; calls the real tool once and imports its shape. |
| Format | Pretty-prints the JSON. |
| Form / View as JSON | Form edits the body with fields that fit the tool's output (for example columns and rows for a table query, document hits, a form submission, a reminder or an escalation). View as JSON edits the raw body. |
Mock Set Editor: Otherwise (every other call)
What happens to a call that matches no case. Choose under Advanced.
| Respond with a default | The call gets the default response you edit here. |
| Keep looking | The call moves on to the next mock set, then to the tool's default simulation policy. In the tool list, such tools are marked "Keeps looking". |
Related guide: Test Tools Safely with Mocks