Advanced Usage FAQs

Yes! You can select which language model powers each agent in Abundly.

To configure: Go to your Agent settings and choose from providers like Anthropic Claude, OpenAI GPT, or Google Gemini.

Quick tips:

• Use (no preference) to let Abundly auto-select the best model for you
• Choose model aliases (e.g., "Claude Sonnet Latest") for automatic upgrades
• Pick specific versions when you need full control and consistency

For the full list of available models, thinking token options, and use-case recommendations, see our Model Selection documentation.

Yes! As of June 2025, the Abundly team has implemented significant improvements that reduce credit consumption by 25-50% across all agent interactions.

What changed

• Reduced credit consumption for all agent activities (chat, autonomous tasks, scheduled operations)
• The exact reduction varies based on how interactions take place, but most users see 25-50% savings
• This improvement affects all types of agent usage regardless of context

When it took effect

• The changes have been live on the platform for several days as of June 26, 2025
• You do not need to take any action to benefit from these improvements
• All existing agents automatically benefit from the reduced credit consumption

User action required

None - This improvement is automatic and applies to all agents immediately. No configuration changes or updates are needed.

When planning to run large batch operations (processing hundreds or thousands of items), proper preparation can prevent interruptions and ensure successful completion.

Credit Requirements

Cost per item:

• Typically 25-50 credits per item processed
• Cost varies depending on whether "thinking" is enabled and complexity of processing
• For example: 3,500 items would require approximately 87,500-175,000 credits

Pre-operation Checklist

1. Calculate credit needs:

• Estimate total items × 25-50 credits per item
• Add a buffer for unexpected complexity or retries
• Check your current credit balance in your dashboard

2. Top up credits before starting:

• Purchase sufficient credits to complete the entire batch
• Avoid running out mid-operation, which could require restarting
• Better to over-estimate than to run short

3. Identify completed vs. incomplete items:

• If an operation is interrupted, you'll need to identify which items were not processed
• Consider organizing your batch data to track progress
• Plan how you'll resume or restart if needed

Why This Matters

• Avoid interrupted operations: Running out of credits mid-batch means stopping and restarting
• Save time: Completing operations in one go is more efficient
• Reduce complexity: Fewer manual interventions needed to track progress

Getting Help

If you need help estimating exact credit requirements based on your specific settings and data, contact us at support@abundly.ai. We can help you calculate more precise estimates for your use case.

Chat conversations are stored in our MongoDB database hosted in Stockholm, Sweden (EU). You have full control—delete a conversation anytime and it's permanently removed.

For details on data residency, encryption, and compliance, see our Infrastructure documentation.

It depends on the source. Agent documents (created in Abundly) are stored in EU data centers in Stockholm. External documents (Google Drive, SharePoint, etc.) remain on their original provider's servers—the agent accesses them through your permission but doesn't copy them.

For more details, see our Documents documentation.

All customer data is stored in EU data centers in Stockholm, Sweden (database on AWS eu-north-1, services on GCP europe-north2). Static files are served via CDN. Data does not leave the EU.

For full details on infrastructure, encryption, and compliance, see our Infrastructure documentation.