Skip to main content

System design

Architecture you can inspect

The same layered model shown on the landing page, expanded for technical readers. Each layer maps to a coherent set of capabilities behind one proof culture.

Architecture

Layered. Coherent. Inspectable.

Midcore stacks deterministic execution below adaptive intelligence — so "move fast" never means "skip proof." Expand each layer to see what you get.

Atomic I/O, model routing, offline enforcement, and runtime adapters.

  • Atomic writes & crash-safe checkpoints
  • Multi-provider LLM routing & harness
  • Offline-first policy enforcement

Conceptual request path

Not every deployment enables every stage; this is the maximal path through the autonomy and delivery surfaces.

  1. Ingress — prompts, tools, and policy context enter the prompt harness.
  2. Planning & tools — agentic loop, policy-aware tool routing, and sandboxed execution.
  3. Intelligence services — retrieval, memory, compaction, and ranking.
  4. Operational layer — autonomy levels, streaming, hooks, and human gates.
  5. Outcome Compiler — contracts, gates, evidence ledger, capability passports, packaging.
  6. Robotics / PubLE — fleet registry, brain pipeline (sense / think / act / learn), safety envelopes, telemetry, simulation, and training exports with the same evidence shape.
  7. Scientific research — Scout / Simulation / Survey / Surveillance tracks, wizard-driven studies, multi-scenario bundles, and resumable long runs under shared identity and billing.

Go deeper