Best practices for handling data with Lindy AI. Use when managing sensitive data, implementing data privacy, or ensuring data compliance. Trigger with phrases like "lindy data", "lindy...
Lindy agents process data through triggers, LLM calls, actions, knowledge bases, and memory. Data flows through Lindy's managed infrastructure with AES-256 encryption at rest and in transit. This skill covers data classification, PII handling, prompt-level data controls, and regulatory compliance.
| Component | Data Storage | Retention |
|---|---|---|
| Tasks | Task inputs, outputs, step data | Visible in dashboard |
| Memory | Persistent snippets across tasks | Until manually deleted |
| Context | Per-task accumulated context | Task lifetime only |
| Knowledge Base | Uploaded files, crawled sites | Until manually removed |
| Integrations | OAuth tokens, connection data | Until disconnected |
| Computer Use | Browser session, screenshots | 30 days after last use |
Map what data each agent processes:
| Data Category | Examples | Handling |
|---|---|---|
| Public | Product info, FAQs, pricing | No restrictions |
| Internal | Sales reports, meeting notes | Limit to authorized agents |
| Confidential | Customer emails, CRM data | Access controls + audit |
| Restricted | PII, PHI, payment data | Minimize exposure + compliance |
Add data handling instructions directly to agent prompts:
## Data Handling Rules
- Never include full email addresses in summaries — use "[name]@[domain]"
- Redact phone numbers in logs — show only last 4 digits
- Do not forward customer personal information to Slack channels
- When storing to spreadsheet, omit columns: email, phone, address
- If asked to share customer data externally, decline and escalate
Knowledge base files are searchable by the agent. Control what goes in:
DO upload:
DO NOT upload:
Resync considerations: KB auto-refreshes every 24 hours. If you upload sensitive content by mistake, remove it AND trigger a manual Resync.
Agent memories persist across all future tasks. Be deliberate:
Safe memory: "Customer prefers email communication over phone"
Safe memory: "Billing questions should escalate to finance@company.com"
Risky memory: "John Smith's SSN is 123-45-6789" ← NEVER store PII in memory
Risky memory: "API key for Stripe: sk_live_xxxx" ← NEVER store secrets
Add to agent prompt:
## Memory Rules
- Never store personally identifiable information (PII) in memory
- Never store credentials, API keys, or passwords in memory
- Memories should contain preferences, patterns, and procedures only
If using Computer Use (browser automation):
GDPR (EU Data Protection):
CCPA (California Consumer Privacy):
HIPAA (Healthcare):
Agent Prompt Addition:
## Data Retention
- Do not reference data from tasks older than 30 days
- Clear task context after each run (do not accumulate indefinitely)
- When updating memory, remove outdated entries
- Summarize customer interactions, do not store verbatim transcripts
Produce a data-handling record for each agent that identifies its data classification, permitted integrations, memory policy, retention decision, and the owner responsible for periodic review. Escalate restricted-data workflows that lack a documented legal basis, BAA, or deletion path before enabling them.
For a lead-routing agent, record customer email as confidential, prohibit it from agent memory and public Slack channels, limit the CRM integration to a service account, and retain only an aggregate routing metric. If the workflow starts processing health information, stop deployment until the Enterprise BAA and minimum-necessary controls are confirmed.
| Issue | Cause | Solution |
|---|---|---|
| PII in Slack channel | Agent forwarded customer email | Add "never forward PII to Slack" to prompt |
| Sensitive file in KB | Uploaded by mistake | Remove file + trigger KB resync immediately |
| Memory contains PII | Agent auto-created memory | Delete memory + add "never store PII" to prompt |
| Audit finding | Agent accessing unnecessary data | Remove unused integrations from agent |
Proceed to lindy-enterprise-rbac for access control.