Build the loop

Sentient-X turns a task into governed experience, an evaluated robot application, and a supervised deployment. The loop closes when fleet outcomes become the next round of experience.

Experience → Worlds → Autonomy → Fleet → Experience

Your fastest interface

Connect your project to a coding agent. The agent gets the project-scoped MCP projection of the same public contract used by the CLI and SDK, while you keep the decisions that carry safety, spend, or promotion risk.

Start here

Connect a project or prepare the monorepo, then produce one verified result.

Run the golden path

Follow one task contract through data, evaluation, training, and supervised deployment.

Work with agents

Give agents outcomes, boundaries, and evidence requirements that unlock real autonomy.

Understand the platform

Learn the four pillars, the handoffs, and the few objects worth remembering.

Choose your altitude

The same system should work for an intern shipping a focused fix and a senior engineer tracing a cross-pillar failure. Pick the path closest to the result you own.

Robotics engineer

Bring an embodiment and task to a safe, supervised canary.

Data engineer

Turn immutable robot evidence into governed, reproducible corpora.

Deep learning scientist

Train on exact snapshots and promote only evidence-backed applications.

Intern

Build the right mental model, use an agent well, and land a small verified change.

The operating idea

You do not need the whole repository in your head. Start from the outcome, find the owning pillar, cross one typed boundary at a time, and keep the task reference and evidence attached. Use an agent to map unfamiliar code and operate routine tools; use tests, receipts, and generated status as the proof.

Truth over confidence

The architecture describes the intended loop. The generated surface status describes what is wired now, and the user journeys name end-to-end gaps. Read both before claiming a journey is complete.