Skip to content

YOLO Mode

YOLO mode controls how much autonomy agents have during workflow execution. When enabled, agents work without asking for validation at each step — like a senior team that you trust to get things done.

LevelActivationStops forBest for
YOLOyolo: true in .assemble.yamlProduction actions, missing info, external effectsDaily development
Hardcore/yolo-hardcore commandProduction onlyTrusted environments, fast iteration
Full/yolo-full commandNothingMaximum speed, accepts all risk

The default autonomous mode. Agents execute without intermediate validation but pause when:

  • An action would affect production (deploy, database migration, etc.)
  • Required information is missing and can’t be inferred
  • An action has external side effects (sending emails, API calls, etc.)
.assemble.yaml
yolo: true
Without YOLOWith YOLO
Jarvis asks permission at each stepJarvis executes the full workflow
Each deliverable requires validationDeliverables are produced continuously
User controls the paceAgents work at maximum speed
More oversightMore speed

Escalation beyond standard YOLO. Agents work with near-full autonomy:

  • Stop only for production-impacting actions
  • Infer information that can reasonably be deduced from context
  • Skip intermediate validations entirely
/yolo-hardcore

This is a runtime command — not configurable in .assemble.yaml. Only a human can activate it, never an agent.

  • Agents interpret ambiguous requirements instead of asking
  • Decisions are made autonomously based on best practices
  • Only truly irreversible production actions trigger a pause

Maximum autonomy. Agents stop for nothing. Full trust, full speed, maximum risk.

/yolo-full

This is also runtime-only and human-activated only.

  • Prototyping where speed matters more than perfection
  • Sandbox environments with no production risk
  • When you want to see what the team produces without any guardrails

Regardless of YOLO level, these rules are non-negotiable:

  1. Hardcore and Full can only be activated by typing the command directly — no agent can activate them for you
  2. Agents must still follow their anti-patterns — YOLO doesn’t override quality rules
  3. The manifest is always updated — you can review what happened after the fact
  4. Deliverables are always produced in assemble-output/ — nothing is lost

YOLO mode and governance are complementary:

GovernanceYOLO offYOLO on
noneManual validation at each stepFull autonomous execution
standardDecision gates at phase transitionsAutonomous within phases, gates between
strictFull audit trail + gatesAutonomous within phases, strict gates + audit

With governance: strict + yolo: true, agents work autonomously within each phase but must still pass through formal decision gates between phases.

yolo: true
governance: none
yolo: true
governance: standard
yolo: false
governance: strict