2026-07-18 · 1 min read
Build auditable agent workflows with handoff
Preserve responses, stderr, manifests, and session IDs so later review does not depend on terminal scrollback.
Published field notes
Practical guides
Runnable recommendations for bounded loops, safe fan-out, durable handoff, prompt boundaries, and task truth.
2026-07-18 · 1 min read
Choose Workflow Runner or Parallel Runner
Match ordered handoffs and independent fan-out to the runner that owns their failure and artifact model.
2026-07-18 · 1 min read
Keep prompts, shell substitutions, and task context safe
Prevent hangs and accidental shell expansion while making resolved agent input visible before dispatch.
2026-07-18 · 1 min read
Run kanban tasks safely in parallel
Select dependency-ready work, cap concurrency, isolate prompts, and review structured aggregation before closing tasks.
2026-07-18 · 1 min read
Start a bounded AI-agent development loop
Use one verifiable task, explicit iteration limits, and evidence checkpoints to keep coding-agent work inspectable.
2026-07-18 · 2 min read
Use YYLO Ledger as the source of truth for agent work
Model readiness, evidence, and relationships explicitly so humans and agents share one executable task state.