Skip to main content
This page contains a set of frequently asked questions regarding the safety and security of Pagos AI. We actively monitor Pagos AI’s performance and welcome your questions and feedback. Please contact us if:
  • Information appears incorrect compared to your analyses or our documentation
  • You have questions about how Pagos AI generated a specific result
  • You’d like to disable access to specific data sets

Technical Architecture

What AI Model and Technology Does Pagos AI Use?

Claude Sonnet 5.5 powers Pagos AI by default, but users can also pick Claude Opus 5.5 for more complex questions or OpenAI’s GPT-6 Luna. Memory runs on Claude Haiku.

What Data is Pagos AI Trained On?

Pagos AI uses:
  • Claude’s base training (conducted by Anthropic)
  • System prompts that define behavior, constraints, and capabilities
  • Page-specific context about the Pagos platform features and metrics
  • Real-time access to the customer’s anonymized payments data via queries
Pagos AI saves high level information about user questions to offer a more tailored experience in future conversations. It doesn’t use stored information across users.

How Does Pagos AI Access My Payments Data?

Pagos AI uses a structured query interface that provides sandboxed, read-only access to your payments data. The system:
  • Can access our default metrics and dimensions exposed through the Pagos platform UI, and can query that data independently to calculate custom metrics upon request
  • Can access individual transaction records, but can’t access cardholder data or PII
  • Uses page-level context to understand what data is relevant to your current view
  • Queries data using the same filters, date ranges, and segments visible in your UI
This architecture ensures the AI only sees what you already see in the platform.

Data Privacy and Security

Does Pagos AI Have Access to Personally Identifiable Information (PII)?

No. Pagos AI only accesses anonymized payments data. Individual cardholder information is already removed from the data pipeline before any AI interaction occurs. The system works exclusively with:
  • Aggregated metrics (counts, rates, volumes)
  • Dimensional breakdowns (by processor, card brand, country, etc.)
  • Time-series data

What Data is Shared With the AI Vendors?

Pagos AI uses a few trusted vendors to run the assistant. Each one only gets what it needs to do its job.
  • AI model providers (Anthropic, OpenAI) get your questions, high-level summaries of past sessions and the data results needed to answer you
  • Web search (Firecrawl) gets search terms for general payments-industry questions and the public web pages Pagos AI reads
  • Analysis sandbox (Daytona) gets the data results needed for advanced calculations; that data is deleted when the analysis ends
No vendor receives full card numbers, PII, raw database access, or your organization’s full dataset. AI vendors don’t use Pagos AI data to train their models.

Can Pagos AI Identify My Organization?

Yes, but only to a limited extent. To provide you with tailored payments advice, Pagos AI has access to high-level records of your company’s payment processing setup, generated by the Pagos team. Pagos AI can also see your email address and basic user profile, including organization name, role, operating currency, and timezone. The data Pagos AI returns is anonymized and does not directly identify your organization, except in two scenarios:
  1. You explicitly mention your organization name in your query
  2. You query merchant account data where account names contain human-readable organization identifiers

What is Your Sub-Processor List for AI Services?

AWS remains the primary processor for all Pagos data. Anthropic provides the AI model but does not process cardholder data or function as a sub-processor under GDPR definitions. No cardholder PII is shared with any AI vendor.

Accuracy and Reliability

How Does Pagos AI Handle Hallucinations or Errors?

Pagos AI is designed with the following safeguards:
  • Constrained scope - System prompts strictly limit responses to payments topics and available data sources
  • Structured queries - Data requests use templated MCP tools with defined parameters, reducing ambiguity
  • Transparency - The AI explains which metrics, dimensions, and filters it used for analysis
  • Honest limits - When data is unavailable, the AI explicitly states it cannot answer
As with any AI system, we recommend treating Pagos AI as an analytical assistant rather than a source of absolute truth. Users should verify critical insights using the Pagos Insights’ direct data views and cross-check important findings with exports or custom reports.
Please report any discrepancies to Pagos Support for investigation

Can I See How Pagos AI Generates Results?

Yes. Pagos AI provides explanations with each response, describing which metrics, dimensions, filters, and time periods it queried, and whether the information came from your data, Pagos’ documentation, or general payments knowledge. When it uses synonyms or ambiguous terms, Pagos AI states its interpretation. Any significant assumptions are explicitly stated You can also ask follow-up questions like “How did you calculate this?” or “What filters did you use?” to understand the methodology.

How is Pagos AI Tested for Accuracy?

Pagos performs regular testing including:
  • Validation against known data outcomes
  • Testing with ambiguous queries to ensure proper clarification requests
  • Regular automated testing to ensure the AI does not drift over time
  • Monitoring for off-topic responses
  • Verification that safety guardrails prevent unauthorized data access
As a production system, we encourage customers to report any inaccurate or unexpected responses to help us improve the product.

Control and Oversight

Can Humans Stay in Control of AI Outputs?

Yes, Pagos AI serves as an analytical assistant, not an autonomous agent. It’s designed with the following human oversight principles:
  • Read-only access - The AI cannot modify your data, configurations, or application state
  • Recommendation-only - The AI provides insights and suggestions but takes no automated actions
  • User-initiated - All queries are explicitly triggered by users
  • Transparent - Users can validate AI analysis through direct platform exploration
  • Stoppable - Users can end any conversation and ignore recommendations

What Can Pagos AI Not Do?

Pagos AI has explicit limitations enforced through system prompts and technical architecture. It cannot perform any of the following actions:
  • Access external APIs
  • Make competitive comparisons with other companies
  • Recommend specific processors, PSPs, or vendors by name
  • Export or provide large files of raw transaction-level data (users should use Transaction Level Data Downloads add-on or the Events page)
  • Send emails, create alerts, or take automated actions
The system is designed to refuse questions unrelated to payments data analysis, payments industry knowledge, or the Pagos platform.

Conversation Context and Memory

Does Pagos AI Remember Previous Conversations?

Pagos AI maintains conversation context within a single session (multi-turn conversation support), including:
  • Previously applied filters, dimensions, and time periods
  • Referenced metrics and data points
  • User-specified preferences within the conversation
Across sessions, Pagos AI only retains a high-level summary of past conversations; it doesn’t store specific results or data values from your queries. For example, Pagos AI will remember that you asked about chargeback rates yesterday, but not the exact data or graph you requested charting chargeback rates over time.
Pagos AI’s cross-session memory is personal to your account and is not shared across users.