Security
Learn how Promptly keeps your data safe.
At Promptly, your data security and privacy aren’t just features — they’re fundamental pillars of our infrastructure. We know trust is earned, not given, and we've designed Promptly from the ground up with enterprise-grade security in mind.
✅ Our Commitment
We follow industry-leading best practices to ensure your prompts, agent configurations, and user data are safe, secure, and never misused.
Data Encryption All data in transit and at rest is protected using AES-256 encryption. Communications between clients and our servers are secured via TLS 1.3.
Prompt Isolation Each prompt and session is sandboxed at runtime. This prevents prompt injection, leakage across users, or cross-contamination between agents.
Audit Logging All user actions are logged for auditing and compliance. You can review activity history via your settings page on our telegram bot, ensuring transparency and traceability.
🔐 Compliance & Standards
While we are constantly evolving our compliance posture, Promptly is built with the following standards in mind:
SOC 2 Type I (In Progress) We are actively working toward SOC 2 Type I certification, ensuring we meet strict criteria across security, availability, and confidentiality.
GDPR-Ready Promptly is fully compliant with the EU General Data Protection Regulation (GDPR). You have full control over your data and can request deletion at any time.
ISO/IEC 27001 Inspired Our internal controls and security practices are aligned with the ISO/IEC 27001 framework, helping safeguard information assets and minimize risk.
Privacy-First Design We don’t store or retain user conversations, except for memory that your Agent uses to operate when you talk with it. Your data belongs to you — and stays that way.
🧠 AI Security Specifics
Because we work with advanced AI Models, Promptly introduces additional guardrails:
Prompt Filtering All user inputs are filtered through a custom content moderation system to detect and block malicious queries or jailbreak attempts.
Rate Limiting & Abuse Prevention Our backend applies intelligent rate limits and anomaly detection to prevent abuse or scraping.
Agent Scoping Custom agents are sandboxed with strict context limits, and can only access resources defined by the user.
You can always delete your data using /deleteaccount . This action is irreversible and your data is unable to be recovered.
Questions?
We’re happy to talk security with you. Contact our team at [email protected] if you have specific compliance needs or questions about our infrastructure.
Last updated