Trust & Safety

Daedalus’s progressive learning capability — the core of its value — is also the source of its responsibility. An AI that improves over time needs guardrails that improve with it.

Three-layer safety model

Layer 1: Behavioral (Values) — Golden Rules, ASK→OFFER→CONFIRM pattern, steering files. These guide behavior when the agent is functioning well. They’re necessary but not sufficient — they rely on the agent choosing to follow them.

Layer 2: Structural (Architecture) — Hard constraints enforced by the Go platform layer, not by the AI model. Write-ahead logging, approval queues, scope boundaries, rollback capability. The agent cannot bypass these because they’re in a separate process with separate authority.

Layer 3: Observational (Transparency) — Audit trail, trust tiers for self-modification, anomaly detection, behavioral drift monitoring. The user sees exactly what changed, when, and why.

The key insight

The intelligence layer (Python/model) and the platform layer (Go) are separate processes with separate authority. The agent can propose changes but cannot execute them without the platform’s approval. This means forgetting a behavioral rule doesn’t result in unconstrained action — the architecture prevents it.

Open source safety

Making Daedalus open source means someone could fork it and strip the safety layer. Our approach: make the safety architecture so deeply integrated that removing it breaks functionality. The approval queue is how specs flow to execution, not a gate in front of it. Audit logging is part of the state transition logic, not a side effect.

The responsible path should be the easy path. The irresponsible path should require deliberate effort.

Foundational doctrines

Daedalus rests on three foundational doctrines. Together they make the case for why it exists, how it stays safe, and who it answers to:

• Landscape & Rationale — Why Daedalus exists: progressive learning is already deployed at scale with little or no safety architecture.
• Trust & Safety Abstract — The full technical paper on the layered, structurally-enforced safety model summarized above.
• Data Sovereignty & Identity — Why the user’s accumulated record is theirs, and why the supervisory core must be accountable to that shared record above any provider or delegate model.