Safer AI chat, controlled memory, clear plan limits.

Bella is built for insurance teams that run work through chat. These controls help protect the AI provider account, keep tenant data separated, and prevent unlimited memory from being sent into every request.

Last updated: June 22, 2026

Local safety gate

Bella checks each chat message locally before memory retrieval, embeddings, tools, or OpenAI/provider calls. Unsafe prompts are stopped before they leave Bella's backend.

  • Blocks prompt-injection attempts, hidden-instruction requests, and secret extraction.
  • Blocks malware, credential theft, fake-document, fraud-evasion, weapon-harm, and oversized requests.
  • Returns a safe refusal without calling the model provider.
Read the AI safety article

Memory and context controls

Bella limits how much memory and recent context each plan can inject into a turn. She also checks stored-memory limits before creating embeddings or saving new long-term memory.

  • Starter gets lighter context, higher plans get deeper recall.
  • Chat continues when memory is full, but extra saves can be skipped.
  • Near-limit and full-limit states can show upgrade or add-on prompts.
Read the memory limits article

Normal insurance work still works.

Bella should allow normal tasks like generating an insurance card, collecting a driver license copy, preparing audit notes, reviewing possible fraud, explaining password reset, checking policy rules, or cleaning up duplicate leads. The safety gate is aimed at clearly unsafe requests, not daily agency operations.

These controls do not make public forms PHI-ready. PHI use still requires a signed BAA and approved PHI onboarding.

Ask Bella what changed.

The same explanation is available inside Bella through her Help Center and article search. Users can ask questions like "How does Bella protect OpenAI from unsafe prompts?" or "How do Bella memory limits work by plan?"

Join betaView security page