Chat Training

Train your agent on real customer conversations with automatic retraining

Chat Training#

Import your existing customer conversations from Facebook and Instagram to train your agent on real-world interactions. Enable auto-training to keep your agent learning continuously.

Why Import Conversations?#

Your past conversations are a goldmine of training data:

• Real questions: What customers actually ask
• Real answers: How you actually respond
• Your voice: Your natural communication style
• Edge cases: Unusual situations you've handled

Supported Sources#

Setting Up#

Step 1: Connect Platforms#

Before training, connect your messaging platforms:

1. Go to Sources > Chat Training
2. You'll see connection status for Messenger and Instagram
3. Click Connect for any unconnected platform
4. Complete the OAuth authorization

The interface shows dual platform icons with connection status, connected page/account names, and action buttons.

Step 2: Preview Conversations#

Before training, preview what data is available:

1. Click the eye icon next to a connected platform
2. Browse conversations with participant names and message counts
3. Click any conversation to read the full thread
4. Business owner messages appear in blue (right-aligned), customer messages in white (left-aligned)

Training Your Agent#

Starting Training#

1. Click Train Agent
2. If you had a previous incomplete training, you'll be offered to Resume or start fresh
3. If only one platform is connected, you'll see a warning explaining the benefits of training with both
4. Configure your training options

Training Options#

Data Sources: Select which connected platforms to include.

Extraction Types (toggle on/off):

• Q&A: Extract question-and-answer pairs from your conversations
• Style: Learn your communication style and tone
• Insights: Extract business insights and patterns

Additional extraction types may be available depending on your plan and connected integrations.

Training Mode:

• Append: Add new data only
• Find New: De-duplicate with existing training
• Overwrite: Full rebuild from scratch

Content Enrichment: Photos, links, videos, audio, documents (toggleable per type).

During Training#

A progress modal shows real-time status:

• Connecting > Fetching > Processing > Extracting > Saving > Completed
• Each step shows status, message, and duration
• You can cancel training at any time
• Extracted counts update in real-time (Q&A pairs, contacts, triggers, insights)

After Training#

The results view shows:

• Conversations trained (with per-platform breakdown)
• Extraction counts by type
• Integration recommendations (auto-detected needs)
• Last training timestamp

Integration Recommendations#

After training, AlonChat analyzes your conversation patterns and suggests integrations that could improve your workflow. Recommendations are based on the types of requests your customers commonly make (scheduling, payments, file sharing, etc.).

Click any recommendation to set up that integration on the Actions page.

Cache and Stats#

After connecting platforms, you'll see cached training data stats:

• Conversation count
• Message count
• Media files count
• Total cache size

Processing Time#

You'll see real-time progress during training and can view results after completion.

Privacy & Security#

Your conversation data is:

• Encrypted during upload and storage
• Private to your account only
• Not shared with any third parties
• Deletable at any time

Auto-Training#

Enable automatic retraining so your agent stays up to date without manual intervention:

1. At the top of the Chat Training page, find the Auto-train toggle
2. When enabled, your agent automatically retrains after accumulating enough new conversations
3. The conversation threshold is configurable

When auto-training is active, the toggle shows a blue highlight with a lightning bolt icon. You'll receive a notification when auto-training completes.

Best Practices#

1. Connect both platforms - Facebook and Instagram together give the best training results
2. Enable auto-training - Keep your agent learning without manual intervention
3. Select quality conversations - Skip spam or irrelevant chats
4. Include variety - Different topics and situations
5. Recent is better - Focus on conversations from the past year
6. Review extracted Q&As - Check quality before relying on auto-approved pairs