How Farmer.CHAT turns conversations to structured data

Our https://gooey.ai/copilot workflow let's anyone build WhatsApp/FB/Web/Voice powered chat bots, by just swapping out their own documents and LLM prompts. Additionally, we also enable you to analyze the user's message and bot's answer to create structured data from the raw conversational messages.

Each Gooey.AI copilot will have their own conversational analysis script like this one to help analyze the user's questions and the bot's ability to answer them well.

In this case, our Farmer.CHAT partner DigitalGreen.org wants to analyze the user's messages and categorize them based on their own logic. Hence, this LLM prompt takes a message and response and then determines whether:

We should update the user's profile object (because they mentioned their location, crop or gender)
The user's question was answered
The topic of the user's question.

7mo ago

👩‍💻 Prompt

🧠 Language Models

💪 Capabilities

🛠️ Developer Tools and Functions

Variables

assistant_msg

string

user_msg

string

⚙️ Settings

Run cost = 3 credits

Breakdown: 2Cr for GPT-4o + 1Cr/run

With each run, you agree to Gooey.AI's terms & privacy policy.

GPT-4o

```json
{
  "intent": "asking",
  "domain_context": "farming_related",
  "task_tier_category": "pest_disease_management",
  "task_subcategory": "prevention",
  "production_system_category": "horticultural_crops",
  "production_system_subcategory": "chilli",
  "interaction_context": {
    "interaction_language": null,
    "interaction_modality": "text",
    "conversation_type": "new",
    "user_prompt_clarity": "clear",
    "personalization_level": "generic",
    "interaction_pattern": "directive",
    "temporal_context": null,
    "urgency_signal": "normal",
    "sophistication_level": "basic"
  },
  "user_profile": {
    "user_gender": "unknown",
    "user_age_group": "unknown",
    "user_role": "unknown",
    "geo_region": null,
    "farm_size": "unknown",
    "farm_crop": "chilli"
  },
  "legacy": {
    "user": {
      "crop": "chilli",
      "subject": "Plant Death (Infestation and Infection)",
      "location": null,
      "gender": "unspecified"
    },
    "assistant": {
      "answer": "Found"
    }
  }
}
```

🐞 Debug

How to Use This Recipe

🙋🏽‍♀️ Need more help? Join our Discord

How Farmer.CHAT turns conversations to structured data

👩‍💻 Prompt

🧠 Language Models

💪 Capabilities

🛠️ Developer Tools and Functions

Variables

Response Format

Max Output Tokens

Creativity (aka Sampling Temperature)

Answer Outputs

How to Use This Recipe

Related Workflows

Create a perfect SEO-optimized Title & Paragraph

Profile Lookup + GPT4 for AI-Personalized Emails

Copilot Builder

Lipsync with Text-to-Speech

GET STARTED

LEARN

DEVELOPERS

SOCIAL

CONNECT

EXTRAS