AI-Powered Fixes
Rivet uses AI to generate fix suggestions for quantum-vulnerable code findings. Suggestions are provided as diffs for you to review and apply manually.
How It Works
- Detection — Code analyzer finds a quantum-vulnerable pattern
- Generation — AI generates a replacement using a NIST PQC algorithm
- Review — You review the suggested diff
- Apply — Apply the changes manually to your codebase
Supported Fix Types
- RSA key generation → ML-KEM / ML-DSA
- ECC operations → ML-DSA
- Weak hash functions → SHA-3 / BLAKE3
- Insecure random → OS-level CSPRNG
- Deprecated TLS configs → TLS 1.3 with PQC cipher suites
Notes
- Suggestions are provided as guidance only — always review before applying to your codebase
- Staleness detection — if the file changed since the scan, the suggestion is invalidated and must be regenerated
- Use Discard to remove a suggestion and start fresh
- Use Regenerate to produce a new suggestion for the same finding
LLM Configuration
| Provider | Notes |
|---|---|
| Google Gemini | Default — requires a Google AI API key |
| Anthropic Claude | Requires an Anthropic API key |
| OpenAI GPT | Requires an OpenAI API key |
| Custom / On-Premise | Ollama, LM Studio, Azure OpenAI, vLLM — for air-gapped or self-hosted deployments (Enterprise) |
Configure in Settings → AI Configuration.