|
Download README.md from MBG0903/Interior_AI_Lead_Agent: direct link, hf CLI and curl.
- Browser
- Download file 2.12 kB
-
https://huggingface.co/spaces/MBG0903/Interior_AI_Lead_Agent/resolve/main/README.md
- Command line
-
hf download hf://spaces/MBG0903/Interior_AI_Lead_Agent/README.md
-
curl -L -o README.md https://huggingface.co/spaces/MBG0903/Interior_AI_Lead_Agent/resolve/main/README.md
2.12 kB
| title: AI Lead Conversion Prototype | |
| emoji: π€ | |
| colorFrom: blue | |
| colorTo: indigo | |
| sdk: gradio | |
| sdk_version: 5.49.1 | |
| app_file: app.py | |
| pinned: false | |
| # AI Lead Conversion Prototype β Interior Business | |
| A demo-first Hugging Face Space for showing how an interior firm can move from manual Excel lead handling to an AI-first qualification workflow. | |
| ## Prototype flow | |
| Meta/Excel Lead β AI Queue β AI Qualification β Automatic Status / Score / Next Action β WhatsApp Workflow β Human Supervisor β Owner Summary | |
| ## V1 features | |
| - Upload the client's Excel lead sheet | |
| - Normalize common lead/follow-up/remarks fields | |
| - Staff attendance and lead allocation | |
| - AI-first queue mode | |
| - Controlled AI call simulation | |
| - Customizable customer reply and language mode | |
| - Automatic lead status, priority, lead score and next action | |
| - WhatsApp action simulation | |
| - Human intervention queue | |
| - Daily owner summary | |
| ## V1 intentionally simulates | |
| - Actual outbound telephone calling | |
| - Meta webhook lead ingestion | |
| - WhatsApp Business message delivery | |
| This is deliberate: it lets the workflow be demonstrated immediately, while `services/voice_service.py` keeps the phone integration isolated for the next step. | |
| ## Hugging Face setup | |
| 1. Create a new **Gradio** Space. | |
| 2. Upload all files and folders from this project. | |
| 3. Wait for the Space to build. | |
| 4. Open the **AI Calling Agent** tab. | |
| 5. Enter a controlled test number and act as the customer in the reply box. | |
| 6. Run the AI qualification and show how status, score, summary, WhatsApp action and human queue update. | |
| ## Next implementation step | |
| Replace the simulator in `services/voice_service.py` with a real outbound voice-agent provider API. The provider should return a call transcript and final call event/webhook; the rest of the lead workflow can remain unchanged. | |
| ## Important production controls | |
| Before using real customer phone numbers, validate consent/DND/telecom requirements, AI disclosure, recording/transcription rules, WhatsApp Business template rules, data retention, and provider support for Indian outbound calling and the required languages. | |