xAI 为 Grok Build 推出 Workflows 功能，最多可并行调度 1,024 个 agents
Workflows in Grok Build Grok Build can now write and run workflows: orchestration scripts that fan a task out across hundreds of parallel agents, verify the results, and report back in one background run. Jul 23, 2026
- 1Grok Build 推出 Workflows 功能，自然语言描述任务即可自动规划并由数百个并行 agents 后台执行汇总
- 2单次运行预算 128 个 agents，大型任务可到 1,024 个，进度随跑随存，暂停续跑不重做已完成工作
- 3保存的 workflow 可变成带参数的斜杠命令复用，.grok/workflows/ 目录内的版本可与团队共享
- 4内置 /deep-research 将研究问题分发给并行调查者，逐条核对来源后返回带引用报告
Grok Build 把大规模并行 agent 编排做成一句话可用的产品功能，复杂批量任务从写脚本变成直接用话描述。
- 影响：PR 审查、issue 分诊、安全审计等可拆分工作可交给后台跑批，不占用开发者会话时间；128 到 1,024 的 agents 用量预算需按任务规模纳入工具成本；团队共享的 workflow 会让例行动作的执行口径趋于统一。
- 参考：可考虑选一个真实的 PR 审查或 issue 分诊任务试点，对比人工耗时与后台跑批结果；值得先盘点团队重复出现的例行动作，把可拆分的沉淀为共享 workflow。
- 依据：功能细节与 128、1,024 的 agents 配额均出自 xAI 官方发布口径，暂无独立评测验证。
Grok Build can now run workflows: describe a large task in plain language, and Grok plans it, fans it out across hundreds of parallel agents in the background, and reports back when everything is done. Your session stays free the whole time.
When to use a workflow
Workflows are built for complex, multi-faceted tasks a single conversation can't hold: reviewing every feature in a large PR, triaging the last 100 issues, auditing a codebase for one class of bug. If the work splits into many independent pieces and should end in one clear report, ask for a workflow.
How it works
Grok plans the task as a small script: the phases of work, the agents in each phase, and how their results roll up. Each agent starts with a clean, focused context, and the plan can build in checks a single pass can't, like independent skeptics verifying every finding before it reaches the final report.
Runs get a budget of 128 agents, and up to 1,024 for big jobs. Progress is saved as the run goes, so pausing and resuming never redoes finished work. Run /workflows to watch it live, phase by phase, with per-agent token counts.
Saving and reusing workflows
Grok authors the workflow from your request, smoke-checks it before launching, and improves it between runs; you never write the script yourself. When one works, keep it: workflows in .grok/workflows/ are shared with your team, and ones in ~/.grok/workflows/ follow you everywhere. Each saved workflow becomes its own slash command that takes arguments, so once you keep the PR review from the demo above, the next review is just /pr-review 5137.
/deep-research ships built in: it fans research questions out to parallel investigators, verifies every claim against its sources, and returns a cited report.
Try it today
Some examples to try:
- "use a workflow to review each feature in this PR"
- "triage the last 100 Linear issues and give me a top-10 action list"
- "audit every route handler for missing auth checks, and verify each finding"
来源：xAI：News · x.ai