/goal: Building big features with dcode
dcode's /goal command enables one-shot large feature builds via persistent acceptance-criteria-driven agent loops
“I started this goal at 3pm and I came back around 7 and during that time I didn't have to continuously restate the task or maintain a mental checklist of everything dcode was supposed to do.”
LangChain's dcode introduces a /goal command that wraps the standard agent react loop with a durable outer loop tied to explicit acceptance criteria, keeping the agent aligned on large tasks without human re-prompting. The demo shows adding native Playwright browser control to dcode itself in a single unattended 4-hour run. This matters because it directly addresses the alignment-drift problem in long agentic coding sessions, shifting correction effort upfront rather than post-completion.