Claude Code Dynamic Workflows: Parallel Subagents & UltraCode Mode

Claude Code now supports dynamic workflows that let the agent orchestrate tens to hundreds of parallel subagents in a single session, checking work before anything reaches you. Available in research preview in the CLI, Desktop, and VS Code extension for Max, Team, and Enterprise plans, plus the API (Amazon Bedrock, Vertex AI, Microsoft Foundry).
How to use
- Ask directly: "Create a workflow"
- Enable UltraCode via the effort menu (sets effort to
xhigh), letting Claude auto-decide when to spawn a workflow.
Workflows consume substantially more tokens than a typical session — start scoped.
Capabilities shown in early access
- Codebase-wide bug hunts: parallel search across a repo, then independent verification on every finding.
- Large migrations: framework swaps, API deprecations, language ports spanning thousands of files end-to-end.
- Double-checked results: independent solution attempts and adversarial agents that try to break the result before delivering it.
Real-world example: Bun rewrite
Jarred Sumner used dynamic workflows to port Bun from Zig to Rust — ~750,000 lines of Rust in 11 days, with 99.8% of existing tests passing. Workflow steps:
- Map Rust lifetimes for every struct field.
- Write every
.rsfile via hundreds of parallel agents, each with two reviewers. - Fix loop driving build/test until clean.
- Overnight workflow to eliminate unnecessary data copies, opening a PR for each fix.
How it works
Claude plans dynamically from your prompt, breaks the task into subtasks, fans work across parallel subagents, checks results independently, and iterates until answers converge — producing a single coordinated answer.
📖 Read the full source: HN AI Agents
👀 See Also

AgentPeek: Open-source dashboard for monitoring Claude Code agent teams
AgentPeek is a local dashboard that hooks into Claude Code to provide visibility into agent teams, showing orchestration hierarchies, execution traces, token costs, and file operations. Installation requires cloning the GitHub repo and running pipx install.

Leadership App with 90+ Lessons from 20+ Books Runs in Claude
A developer created a leadership app that runs inside Claude, featuring 90+ lessons extracted from 20+ books on leadership, habits, discipline, influence, team culture, and wealth mindset. The app provides daily lessons with specific actions, streak tracking, journaling, and search capabilities.

Gemma 4 26B vs Qwen 3.5 27B: Local Business Workflow Benchmark on RTX 4090
A developer tested Gemma 4 26B and Qwen 3.5 27B on an RTX 4090 workstation for 18 real business operator tasks. Gemma won 13-5, showing faster speed and better discipline for daily execution work, while Qwen excelled at broader strategic thinking.

Decision Passport: An Audit Layer for AI Agent Execution Governance
The Claude Code leak highlights a gap in AI agent governance. Decision Passport addresses this with append-only execution records, portable proof bundles, and offline verification for tamper-evident audit trails.