# DAIR.AI 创始人 Elvis Saravia 分享动态工作流实践

- 来源：elvis (@omarsar0)
- 发布时间：2026-06-04 23:14
- AIHOT 分数：48
- AIHOT 链接：https://aihot.virxact.com/items/cmpzn8uzt055aslkpfuom8sjp
- 原文链接：https://x.com/omarsar0/status/2062553527730540611

## AI 摘要

Elvis Saravia 逆向工程了动态工作流（Dynamic Workflows）并集成到自研智能体编排器中，同时构建 HTML 监控仪表盘跟踪任务、指标和报告。该工作流可在 Claude Code、Codex、Pi 等编码智能体及自研 @dair_ai agent 上运行。成功用例包括分支深度研究、并行深度研究、会话挖掘、Bug 定位、分类、事实核查、LLM 委员会、AI 模拟、数据合成和评测生成等。他认为动态工作流与 agent 技能一样，是实现复杂长期任务的关键原语，不仅限于编码，还可扩展至商业、科学等领域。

## 正文

I am hooked on Dynamic Workflows！

The idea of generating harnesses on the fly is so compelling that I reverse-engineered it for my agent orchestrator.

And then I built a monitoring dashboard （as an HTML artifact） to track tasks， metrics， and reports.

I can now use and monitor dynamic workflows in my agent orchestrator with coding agents like Claude Code， Codex， Pi， and even my own custom-built @dair_ai agent.

This is clearly the future of working with agents to accomplish complex， long-running tasks.

Some use cases I'm having success with：

- Branching deep research tasks （with verification）
- Parallel deep research tasks
- Session mining of all my agent sessions
- Bug hunting
- Triaging
- Fact-checking
- LLM councils
- AI simulations
- Data synthesis
- Evals generation
… and many others

Dynamic workflows， like agent skills， feel like an important primitive to not only get the most out of agents but also incorporate dynamic behaviors and important components like cooperation and verification.

There is so much exploration ground here. The exciting part is that this is not limited to coding tasks； it extends to business use cases and many other technical domains like science and research.