Generate a scenario’s instructions text from agent context and natural-language input. Returns a progress_id — poll instructions-progress/.
Documentation Index
Fetch the complete documentation index at: https://docs.cekura.ai/llms.txt
Use this file to discover all available pages before exploring further.
API Key Authentication. It should be included in the header of each request.
Mixin for parsing restql query from request.
NOTE: We are using request.GET instead of
request.query_params because this might be
called before DRF request is created(i.e from dispatch).
This means request.query_params might not be available
when this mixin is used.
Personality ID
Example: 123
Name of the scenario
80Agent ID
Example: 2142
Alternative to agent ID - the assistant ID to use for this scenario
Example: "asst_1234567890"
Tags associated with the scenario
Example: ["tag1", "tag2"]
List of tool IDs to associate with this scenario
Example: ["TOOL_DTMF", "TOOL_END_CALL"]
List of metric IDs to associate with this scenario
Example: [123, 456]
First message to be sent to the Main Agent
1000Scenario Instructions
Structured conditional-actions object for scenario_type="conditional_actions". Use either conditional_actions (structured) or instructions (plain text) — not both.
Example:
{
"role": "You are a patient calling to schedule an appointment",
"conditions": [
{"id": 0, "condition": "FIRST_MESSAGE", "action": "Hi, I need to schedule an appointment",
"type": "standard", "fixed_message": true},
{"id": 1, "condition": "when the agent asks for your name",
"action": "Provide your full name: John Smith", "type": "standard", "fixed_message": false}
]
}Simulation Description
Information fields associated with the scenario
Example: {"user_name": "John Doe", "user_email": "john.doe@example.com", "order_id": "1234567890"}
Expected Outcome Prompt
Example: "The user should be able to complete the order"
Language of the scenario
af - Afrikaansar - Arabicbn - Bengalibg - Bulgarianzh - Chinese Simplifiedcs - Czechda - Danishnl - Dutchen - Englishet - Estonianfi - Finnishfr - Frenchde - Germanel - Greekgu - Gujaratihi - Hindihe - Hebrewhu - Hungarianid - Indonesianit - Italianja - Japanesekn - Kannadako - Koreanms - Malayml - Malayalammr - Marathimulti - Multilingualno - Norwegianpl - Polishpa - Punjabipt - Portuguesero - Romanianru - Russiansk - Slovakes - Spanishsv - Swedishth - Thaitr - Turkishtl - Tagalogta - Tamilte - Teluguuk - Ukrainianvi - Vietnameseaf, ar, bn, bg, zh, cs, da, nl, en, et, fi, fr, de, el, gu, hi, he, hu, id, it, ja, kn, ko, ms, ml, mr, multi, no, pl, pa, pt, ro, ru, sk, es, sv, th, tr, tl, ta, te, uk, vi Type of scenario (instruction, real_world_smart, or real_world_fixed)
instruction - Instructionreal_world_smart - Real World Smartreal_world_fixed - Real World Fixedconditional_actions - Conditional Actionsinstruction, real_world_smart, real_world_fixed, conditional_actions Type of predefined suite (e.g., infrastructure)
undefined - Undefinedinfrastructure - Infrastructureundefined, infrastructure Whether this is a predefined scenario (template)
Generated values for the agent's dynamic variables for this scenario. Keys are variable names; values are the generated values.
Dot-separated path of the folder to assign this evaluator to (e.g. "Sales.Inbound"). Folders must be created before use — they are not auto-created. Use scenarios_create_folder_create to create each level before assigning evaluators. Example: to use "Sales.Inbound", first create "Sales", then create "Inbound" inside it.
Max call duration in seconds for this scenario. If not provided or set to null, the scenario will use the project's max_call_duration setting.
Valid range: 10-3600 seconds (10 seconds to 60 minutes)
Example: 600 (10 minutes)
Mixin for parsing restql query from request.
NOTE: We are using request.GET instead of
request.query_params because this might be
called before DRF request is created(i.e from dispatch).
This means request.query_params might not be available
when this mixin is used.
Personality ID
Example: 123
Name of the scenario
80Agent ID
Example: 2142
Name of the personality used in this scenario
Example: "Normal Male"
Name of the agent associated with this scenario
Example: "Customer Support Agent"
Tags associated with the scenario
Example: ["tag1", "tag2"]
List of tool IDs to associate with this scenario
Example: ["TOOL_DTMF", "TOOL_END_CALL"]
List of IDs for the last run of this scenario
Example: [123, 456]
List of metric names associated with this scenario
Example: ["Metric 1", "Metric 2"]
Phone number used for outbound calls in this scenario
Example: "+1234567890"
Phone number used for outbound calls in this scenario
Example: "+1234567890"
First message to be sent to the Main Agent
1000(Deprecated) Phone number used for inbound calls in this scenario. Use outbound_phone_number_data instead.
After CEK-6517, both phone_number and inbound_phone_number fields are synced, so outbound_phone_number_data contains the unified phone number for both inbound and outbound calls.
Example: {"id": 123, "number": "+1234567890", "phone_number_id": "abc123"}
Scenario Instructions
Simulation Description
Information fields associated with the scenario
Example: {"user_name": "John Doe", "user_email": "john.doe@example.com", "order_id": "1234567890"}
Expected Outcome Prompt
Example: "The user should be able to complete the order"
Language of the scenario
af - Afrikaansar - Arabicbn - Bengalibg - Bulgarianzh - Chinese Simplifiedcs - Czechda - Danishnl - Dutchen - Englishet - Estonianfi - Finnishfr - Frenchde - Germanel - Greekgu - Gujaratihi - Hindihe - Hebrewhu - Hungarianid - Indonesianit - Italianja - Japanesekn - Kannadako - Koreanms - Malayml - Malayalammr - Marathimulti - Multilingualno - Norwegianpl - Polishpa - Punjabipt - Portuguesero - Romanianru - Russiansk - Slovakes - Spanishsv - Swedishth - Thaitr - Turkishtl - Tagalogta - Tamilte - Teluguuk - Ukrainianvi - Vietnameseaf, ar, bn, bg, zh, cs, da, nl, en, et, fi, fr, de, el, gu, hi, he, hu, id, it, ja, kn, ko, ms, ml, mr, multi, no, pl, pa, pt, ro, ru, sk, es, sv, th, tr, tl, ta, te, uk, vi Type of scenario (instruction, real_world_smart, or real_world_fixed)
instruction - Instructionreal_world_smart - Real World Smartreal_world_fixed - Real World Fixedconditional_actions - Conditional Actionsinstruction, real_world_smart, real_world_fixed, conditional_actions Type of predefined suite (e.g., infrastructure)
undefined - Undefinedinfrastructure - Infrastructureundefined, infrastructure Whether this is a predefined scenario (template)
Details of the test profile associated with this scenario Example:
{
"id": "<integer>",
"agent_id": "<integer>",
"name": "<string>",
"information": {
"user_name": "<string>",
"user_email": "<string>",
"order_id": "<string>",
},
}Generated values for the agent's dynamic variables for this scenario. Keys are variable names; values are the generated values.
Dot-separated path of the folder to assign this evaluator to (e.g. "Sales.Inbound"). Folders must be created before use — they are not auto-created. Use scenarios_create_folder_create to create each level before assigning evaluators. Example: to use "Sales.Inbound", first create "Sales", then create "Inbound" inside it.
Max call duration in seconds for this scenario. If not provided or set to null, the scenario will use the project's max_call_duration setting.
Valid range: 10-3600 seconds (10 seconds to 60 minutes)
Example: 600 (10 minutes)