Doel
Call Dashbot from inside an Element and read the answer under the execution access context.
Elements runtime reference / AI and delivery
askDashbotCall Dashbot from inside an Element and read the answer under the execution access context.
askDashbot(prompt, responseFormat=None, allowTools=None, maxToolCalls=None, toolScope=None, contextId=None, timeoutSeconds=None, language=None, timeZone=None, localNow=None, localDate=None)
Call Dashbot from inside an Element and read the answer under the execution access context.
ask_dashbotcallDashbotcall_dashbotdashbot.askUse these fields as the Python call arguments or keyword payload for this helper.
{
"prompt": "Summarize these rows in one operational sentence.",
"allowTools": false,
"timeoutSeconds": 120,
"responseFormat": {
"type": "json_object"
}
}
| Field | Description |
|---|---|
prompt | Required prompt string. |
responseFormat | Optional JSON response-format object passed to Dashbot. |
allowTools | Optional bool. Defaults false in Element runtime to avoid recursive Element/Dashbot/tool loops. |
maxToolCalls | Optional tool-call cap when allowTools is true. |
toolScope | Optional Dashbot tool scope, usually general. |
contextId | Optional memory context id. Omit for isolated one-shot calls. |
timeoutSeconds | Optional request timeout. |
language/timeZone/localNow/localDate | Optional context forwarded to Dashbot. |
{
"message": {
"role": "assistant",
"content": "{\"summary\":\"Orders are stable.\"}"
},
"text": "{\"summary\":\"Orders are stable.\"}",
"parsed": {
"summary": "Orders are stable."
},
"usage": {
"inputTokens": 120,
"outputTokens": 12
},
"warnings": []
}
def run():
answer = askDashbot(
"Summarize this status in one sentence.",
allowTools=False,
responseFormat={"type": "json_object"},
)
return {"summary": answer.parsed.get("summary") if answer.parsed else answer.text}