änderungen von vorherigen Codexnutzung: sollte den Agent lassen die Aufgaben zu erzeugen
This commit is contained in:
+12
-8
@@ -8,24 +8,28 @@ The Flowise agent acts as a precise A1 English teacher for German-speaking adult
|
||||
|
||||
- `target_language`
|
||||
- `cefr_level`
|
||||
- current exercise
|
||||
- Azure scores
|
||||
- learner profile
|
||||
- progress summary
|
||||
- weak words
|
||||
- recent attempts
|
||||
|
||||
## Output
|
||||
|
||||
The backend expects valid JSON:
|
||||
For task `next_exercise`, the backend expects valid JSON:
|
||||
|
||||
```json
|
||||
{
|
||||
"exercise_type": "repeat_sentence",
|
||||
"target_text": "Hello, my name is Anna.",
|
||||
"teacher_feedback": "Uebe besonders 'name'.",
|
||||
"target_language": "en-US",
|
||||
"cefr_level": "A1",
|
||||
"reference_text": "Hello, my name is Anna.",
|
||||
"display_prompt": "Sprich den Satz klar nach.",
|
||||
"tts_text": "Hello, my name is Anna.",
|
||||
"ssml": "",
|
||||
"next_recommendation": "Sprich den Satz noch einmal langsam."
|
||||
"focus_points": ["name"],
|
||||
"success_criteria": ["accuracy above 80"],
|
||||
"reason_for_choice": "Kurzer Satz fuer klare A1-Aussprache."
|
||||
}
|
||||
```
|
||||
|
||||
The agent must not create pronunciation scores. Azure is the scoring source.
|
||||
The agent must not create pronunciation scores. Azure is the scoring source. Feedback and simple
|
||||
conversation are local backend logic in this phase; Flowise is used only for exercise generation.
|
||||
|
||||
Reference in New Issue
Block a user