uipath-agents

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

UiPath Agents

Hard Rules

硬性规则

Treat "build/create/scaffold/implement a UiPath agent" as the full One-Prompt Flow by default. Do not stop after file creation or local run unless the user explicitly says to stop there.
A normal completion point is after smoke eval and the mandatory Delivery fork question. A final build summary before that is premature unless run/eval is blocked or the user opted out.
Probe the
solution
verb once per session before the first scaffold or deploy. Run
```
uip solution init --help --output json
```
. Result
```
Success
```
→ use
```
solution init
```
and
```
solution deploy run --parent-folder-path
```
/
```
--parent-folder-key
```
(post-rename, default).
```
unknown command
```
/ non-zero exit → CLI predates the rename; substitute
```
uip solution new <Name>
```
and
```
--folder-path
```
/
```
--folder-key
```
(same arguments otherwise) wherever this skill calls those.
Greenfield coded agents — scaffold with
uip codedagent new
, never hand-author the project. Building a NEW coded agent from scratch: always create it with
```
uip codedagent new <name>
```
, then generate schemas with
```
uip codedagent init
```
— never hand-write
```
pyproject.toml
```
/
```
main.py
```
/
```
langgraph.json
```
/
```
entry-points.json
```
yourself, even for a trivial agent. Hand-authoring skips required project structure and produces invalid packages. (Existing or Studio Web local-workspace projects: do NOT run
```
uip codedagent new
```
— follow the project-state gating in coded/quickstart.md.)
Coded agents only — bindings are always derived from UiPath Python SDK calls and must never be hand-authored. To derive them, always run the sync workflow in coded/lifecycle/bindings-reference.md — scan code, regenerate
```
bindings.json
```
. Without this, resources cannot be overridden per execution environment and will always default to the hardcoded values in the SDK calls. Derive bindings whenever you add, remove, or modify any UiPath SDK resource call — for instance
```
assets
```
,
```
queues
```
,
```
processes
```
,
```
buckets
```
,
```
indexes
```
,
```
connections
```
,
```
apps
```
,
```
MCP servers
```
, or
```
InvokeProcess|CreateTask|CreateEscalation(...)
```
.

默认将“构建/创建/搭建/实现一个UiPath Agent”视为完整的单提示流程。除非用户明确要求停止，否则不要在文件创建或本地运行后终止流程。
正常完成节点为冒烟测试评估和必填的交付分支问题之后。除非运行/评估被阻止或用户选择退出，否则在此之前生成最终构建摘要为时尚早。
在首次搭建或部署前，每个会话需探测一次
solution
命令。运行
```
uip solution init --help --output json
```
。若结果为
```
Success
```
→ 使用
```
solution init
```
和
```
solution deploy run --parent-folder-path
```
/
```
--parent-folder-key
```
（重命名后默认参数）。若返回
```
unknown command
```
/ 非零退出码 → CLI版本早于重命名；在本技能调用这些命令的所有位置，替换为
```
uip solution new <Name>
```
和
```
--folder-path
```
/
```
--folder-key
```
（其他参数保持不变）。
全新代码型Agent — 使用
uip codedagent new
搭建，切勿手动编写项目。从零开始构建新的代码型Agent：始终使用
```
uip codedagent new <name>
```
创建，然后通过
```
uip codedagent init
```
生成模式 — 切勿手动编写
```
pyproject.toml
```
/
```
main.py
```
/
```
langgraph.json
```
/
```
entry-points.json
```
，即使是简单Agent也不行。手动编写会跳过必要的项目结构，生成无效包。（现有或Studio Web本地工作区项目：请勿运行
```
uip codedagent new
```
— 遵循coded/quickstart.md中的项目状态限制。）
仅适用于代码型Agent — 绑定始终从UiPath Python SDK调用派生，切勿手动编写。要派生绑定，请始终执行coded/lifecycle/bindings-reference.md中的同步工作流 — 扫描代码，重新生成
```
bindings.json
```
。若不执行此步骤，资源无法按执行环境覆盖，将始终默认使用SDK调用中的硬编码值。每当添加、删除或修改任何UiPath SDK资源调用时，均需派生绑定 — 例如
```
assets
```
、
```
queues
```
、
```
processes
```
、
```
buckets
```
、
```
indexes
```
、
```
connections
```
、
```
apps
```
、
```
MCP servers
```
，或
```
InvokeProcess|CreateTask|CreateEscalation(...)
```
。

Project Type Detection

项目类型检测

Determine the agent mode before proceeding:

First — confirm this is an agent, not a Coded Function. If
```
uipath.json
```
declares a
```
functions
```
map (e.g.
```
"functions": {"main": "main.py:main"}
```
), the project is a Python Coded Function, not an agent. Stop here and use the
```
uipath-functions
```
skill instead. Functions are deterministic, do not reason via LLM, and have a distinct lifecycle (
```
uip function new/init/pack/publish/run
```
).
Check for existing agent project files in the working directory:
- ```
pyproject.toml
```
  +
```
.py
```
  files + a framework dep (
```
uipath-langchain
```
  ,
```
uipath-llamaindex
```
  , or
```
uipath-openai-agents
```
  ) → Coded. The framework package already declares
```
uipath
```
  as a dependency, so an explicit
```
uipath
```
  entry is not required.
- ```
agent.json
```
  with
```
"type": "lowCode"
```
  +
```
project.uiproj
```
  , AND no
```
pyproject.toml
```
  → Low-code
No existing project found → ask the user:

Should I build this as a low-code agent (no Python — configure through prompts and pre-built UiPath tools) or a coded agent (Python — full programmatic control with LangGraph, LlamaIndex, or OpenAI Agents)? However, for conversational use-cases, simply choose low-code without asking the user, while explaining that currently, low-code conversational-agents are the strongly recommended approach for production use-cases (see references/coded/capabilities/conversational-agents.md).
If the user needs help deciding, read references/coded-vs-lowcode-guide.md for a capability comparison.

After detection, read the quickstart for that mode before doing anything else:

Coded → read references/coded/quickstart.md. Quickstart's first step detects project state (
```
greenfield
```
/
```
existing-coded
```
/
```
local-workspace
```
) and gates each lifecycle step on it. For Studio Web Local Workspace specifics, see references/coded/lifecycle/local-workspace.md.
Low-code → read references/lowcode/lowcode.md

在继续之前，先确定Agent模式：

首先 — 确认这是Agent而非Coded Function。若
```
uipath.json
```
声明了
```
functions
```
映射（例如
```
"functions": {"main": "main.py:main"}
```
），则该项目为Python Coded Function，而非Agent。请在此停止，改用
```
uipath-functions
```
技能。Functions是确定性的，不通过大语言模型推理，且具有独特的生命周期（
```
uip function new/init/pack/publish/run
```
）。
检查工作目录中是否存在现有Agent项目文件：
- ```
pyproject.toml
```
  +
```
.py
```
  文件 + 框架依赖（
```
uipath-langchain
```
  、
```
uipath-llamaindex
```
  或
```
uipath-openai-agents
```
  ）→ 代码型。框架包已声明
```
uipath
```
  为依赖，因此无需显式添加
```
uipath
```
  条目。
- ```
agent.json
```
  包含
```
"type": "lowCode"
```
  +
```
project.uiproj
```
  ，且无
```
pyproject.toml
```
  → 低代码
未找到现有项目 → 询问用户：

我应该将其构建为低代码Agent（无需Python — 通过提示和预构建UiPath工具配置）还是代码型Agent（Python — 使用LangGraph、LlamaIndex或OpenAI Agents实现完全编程控制）？不过，对于对话式用例，无需询问用户，直接选择低代码即可，同时说明目前低代码对话式Agent是生产用例的强烈推荐方案（详见references/coded/capabilities/conversational-agents.md）。
若用户需要帮助做决定，请阅读references/coded-vs-lowcode-guide.md进行能力对比。

检测完成后，在执行任何操作前先阅读对应模式的快速入门指南：

代码型 → 阅读references/coded/quickstart.md。快速入门的第一步会检测项目状态（
```
greenfield
```
/
```
existing-coded
```
/
```
local-workspace
```
），并据此限制每个生命周期步骤。关于Studio Web本地工作区的具体说明，请参阅references/coded/lifecycle/local-workspace.md。
低代码 → 阅读references/lowcode/lowcode.md

Task Navigation

任务导航

I need to...	Mode	Read first	Then
Help user choose coded vs low-code	Both	coded-vs-lowcode-guide.md
Authenticate	Both	authentication.md
Iterate on a coded agent inside a Studio Web Local Workspace solution	Coded	coded/quickstart.md (state detection sets `project_state = local-workspace` )	coded/lifecycle/local-workspace.md for files-owned-by-SW + anti-patterns; `coded/lifecycle/running-agents.md` , `coded/lifecycle/evaluate.md`
Create/build/deploy coded agent	Coded	coded/quickstart.md	`coded/lifecycle/` , `coded/frameworks/`
Select coded framework	Coded	coded/quickstart.md § Framework Selection
Add coded capabilities (HITL, RAG, tracing)	Coded	coded/quickstart.md	`coded/capabilities/*`
Set a coded agent's environment variables, or reference an Orchestrator asset from one ( `%ASSETS/<ASSET_NAME>%` )	Coded	coded/lifecycle/environment-variables.md	`coded/lifecycle/file-sync.md` for what `.env` does and does not carry
Call an Integration Service connector (Slack, Jira, Web Search) from a coded agent	Coded	coded/capabilities/integration-service.md + then immediately read `uipath-platform/references/integration-service/agent-workflow.md` — discovery lives there, not in `uipath-agents`	`coded/capabilities/sdk-services.md` § Connections
Run coded evaluations	Coded	coded/quickstart.md § Evaluate	`coded/lifecycle/evaluate.md`
Create or scaffold a new low-code agent project	Low-code	lowcode/lowcode.md § Quick Start	`lowcode/project-lifecycle.md` , `lowcode/agent-definition.md`
Edit `agent.json` (prompts, model, schemas, contentTokens, entry-points.json)	Low-code	lowcode/lowcode.md § Capability Registry	`lowcode/agent-definition.md`
Add a low-code tool (Orchestrator process — RPA / agent / API / agentic — or Integration Service)	Low-code	lowcode/lowcode.md § Capability Registry	`lowcode/capabilities/process/` , `lowcode/capabilities/integration-service/`
Add an MCP (Model Context Protocol) server tool to a low-code agent	Low-code	lowcode/lowcode.md § Capability Registry	`lowcode/capabilities/mcp/mcp.md`
Accept files as agent input / call the Analyze Files built-in tool	Low-code	lowcode/capabilities/built-in-tools/built-in-tools.md	`lowcode/capabilities/built-in-tools/analyze-attachments.md` , `lowcode/agent-definition.md` § File Attachments
Work with file attachments (input, output, or created mid-run)	Coded	coded/capabilities/file-attachments.md
Build a conversational (chat-style) agent	Low-code	lowcode/lowcode.md	`lowcode/project-lifecycle.md` , `lowcode/agent-definition.md`
Add a low-code context (Context Grounding RAG / attachments / DataFabric entity set)	Low-code	lowcode/lowcode.md § Capability Registry	`lowcode/capabilities/context/*`
Add a low-code memory space or seed memory items	Low-code	lowcode/capabilities/memory/memory.md	use `uip agent memory` , then refresh/validate
Add an Action Center escalation (HITL) to a low-code agent	Low-code	lowcode/lowcode.md § Capability Registry	`lowcode/capabilities/escalation/escalation.md`
Add guardrails (PII, harmful content, custom rules) to a low-code agent	Low-code	lowcode/lowcode.md § Capability Registry	`lowcode/capabilities/guardrails/guardrails.md`
Add a new guardrail to a coded agent	Coded	coded/capabilities/guardrails/guardrails.md	fetch official docs via WebFetch, ask middleware vs decorator, read agent code, write Python
Add escalation guardrail (escalate action / Action Center app)	Low-code	lowcode/capabilities/guardrails/guardrails.md § escalate — Hand Off to Action Center	Run `uip solution resources list --kind App --source remote --output json` to confirm app exists
Recommend guardrails for a low-code agent based on its context	Low-code	lowcode/capabilities/guardrails/guardrails-recommend.md	fetch catalog + list, analyze agent context, apply + validate
Recommend guardrails for a specific scope or tool	Low-code	lowcode/capabilities/guardrails/guardrails-recommend.md § Scoped or Tool-Specific Filtering	filter candidates by scope or tool name after catalog analysis
Validate whether existing guardrails are correctly configured	Low-code	lowcode/capabilities/guardrails/guardrails-recommend.md § Validate Mode	check correctness, actionability, and relevance per guardrail
Recommend guardrails for a coded agent based on its context	Coded	coded/capabilities/guardrails/guardrails-recommend.md	fetch catalog + list + SDK docs, analyze agent code, apply + verify
Recommend guardrails for a specific scope or tool (coded)	Coded	coded/capabilities/guardrails/guardrails-recommend.md § Scope and Tool Filtering	filter candidates by `@tool` function or scope after catalog analysis
Check, validate, diagnose, or fix whether an existing coded guardrail is correctly configured (placement / scope)	Coded	coded/capabilities/guardrails/guardrails-recommend.md § Validate Mode	fetch SDK docs first (authoritative for scope/placement); also fetch catalog + list for relevance/entitlement — then check correctness, actionability, and relevance — fix in place
Embed a low-code agent inline in a flow, or wire a multi-agent solution	Low-code	lowcode/lowcode.md § Capability Registry	`lowcode/capabilities/inline-in-flow/inline-in-flow.md` , `lowcode/capabilities/process/solution-agent.md`
Run low-code evaluations	Low-code	lowcode/evaluations/evaluate.md	`lowcode/evaluations/evaluators.md` , `lowcode/evaluations/evaluation-sets.md` , `lowcode/evaluations/running-evaluations.md`
Run offline evals for a published Orchestrator package	Low-code	lowcode/evaluations/orchestrator-eval-run.md	Use `uip or eval run-offline-evals` (requires package published to Orchestrator)
Validate, pack, publish, upload, or deploy a low-code agent	Low-code	lowcode/lowcode.md	`lowcode/project-lifecycle.md` , `lowcode/solution-resources.md`
Debug / run a low-code agent end-to-end and inspect its output	Low-code	lowcode/debug.md	`lowcode/project-lifecycle.md` § `uip agent debug`
Embed coded agent in a flow (solution-level)	Coded	coded/embedding-in-flows.md
Use coded agent in a flow	Coded	coded/flow-integration.md
Use coded agent as tool for another agent in flow	Coded	coded/flow-integration.md § Pattern 3
Summarize / research / synthesize over PDF or TXT (DeepRAG, coded)	Coded	context-grounding-patterns.md	coded/capabilities/deeprag/planning.md
Summarize / research / synthesize over PDF or TXT (DeepRAG, low-code)	Low-code	context-grounding-patterns.md	lowcode/capabilities/built-in-tools/deeprag/planning.md
Process CSV rows with LLM per row (BatchTransform, coded)	Coded	context-grounding-patterns.md	coded/capabilities/batch-transform/planning.md
Process CSV rows with LLM per row (BatchTransform, low-code)	Low-code	context-grounding-patterns.md	lowcode/capabilities/built-in-tools/batch-transform/planning.md
Manage context-grounding indexes from the CLI (list / create / ingest / search)	Platform	`uipath-platform/references/context-grounding/index-management.md`	`uip context-grounding` — cross-cutting CLI, owned by `uipath-platform`

我需要...	模式	先阅读	然后
帮助用户选择代码型还是低代码	两者	coded-vs-lowcode-guide.md
身份验证	两者	authentication.md
在Studio Web本地工作区解决方案中迭代代码型Agent	代码型	coded/quickstart.md（状态检测设置 `project_state = local-workspace` ）	coded/lifecycle/local-workspace.md了解Studio Web托管文件及反模式； `coded/lifecycle/running-agents.md` 、 `coded/lifecycle/evaluate.md`
创建/构建/部署代码型Agent	代码型	coded/quickstart.md	`coded/lifecycle/` 、 `coded/frameworks/`
选择代码型框架	代码型	coded/quickstart.md § 框架选择
添加代码型功能（HITL、RAG、追踪）	代码型	coded/quickstart.md	`coded/capabilities/*`
设置代码型Agent的环境变量，或从其中引用Orchestrator资产（ `%ASSETS/<ASSET_NAME>%` ）	代码型	coded/lifecycle/environment-variables.md	`coded/lifecycle/file-sync.md` 了解 `.env` 的作用范围
从代码型Agent调用集成服务连接器（Slack、Jira、Web搜索）	代码型	coded/capabilities/integration-service.md + 立即阅读 `uipath-platform/references/integration-service/agent-workflow.md` — 发现功能位于此处，而非 `uipath-agents`	`coded/capabilities/sdk-services.md` § 连接
运行代码型评估	代码型	coded/quickstart.md § 评估	`coded/lifecycle/evaluate.md`
创建或搭建新的低代码Agent项目	低代码	lowcode/lowcode.md § 快速入门	`lowcode/project-lifecycle.md` 、 `lowcode/agent-definition.md`
编辑 `agent.json` （提示词、模型、模式、contentTokens、entry-points.json）	低代码	lowcode/lowcode.md § 功能注册表	`lowcode/agent-definition.md`
添加低代码工具（Orchestrator流程 — RPA / Agent / API / Agentic — 或集成服务）	低代码	lowcode/lowcode.md § 功能注册表	`lowcode/capabilities/process/` 、 `lowcode/capabilities/integration-service/`
为低代码Agent添加MCP（Model Context Protocol）服务器工具	低代码	lowcode/lowcode.md § 功能注册表	`lowcode/capabilities/mcp/mcp.md`
接受文件作为Agent输入 / 调用内置的文件分析工具	低代码	lowcode/capabilities/built-in-tools/built-in-tools.md	`lowcode/capabilities/built-in-tools/analyze-attachments.md` 、 `lowcode/agent-definition.md` § 文件附件
处理文件附件（输入、输出或运行中创建）	代码型	coded/capabilities/file-attachments.md
构建对话式（聊天风格）Agent	低代码	lowcode/lowcode.md	`lowcode/project-lifecycle.md` 、 `lowcode/agent-definition.md`
添加低代码上下文（上下文接地RAG / 附件 / DataFabric实体集）	低代码	lowcode/lowcode.md § 功能注册表	`lowcode/capabilities/context/*`
添加低代码内存空间或植入内存项	低代码	lowcode/capabilities/memory/memory.md	使用 `uip agent memory` ，然后刷新/验证
为低代码Agent添加Action Center升级（HITL）	低代码	lowcode/lowcode.md § 功能注册表	`lowcode/capabilities/escalation/escalation.md`
为低代码Agent添加防护规则（PII、有害内容、自定义规则）	低代码	lowcode/lowcode.md § 功能注册表	`lowcode/capabilities/guardrails/guardrails.md`
为代码型Agent添加新的防护规则	代码型	coded/capabilities/guardrails/guardrails.md	通过WebFetch获取官方文档，询问中间件还是装饰器，读取Agent代码，编写Python代码
添加升级防护规则（升级操作 / Action Center应用）	低代码	lowcode/capabilities/guardrails/guardrails.md § escalate — 移交至Action Center	运行 `uip solution resources list --kind App --source remote --output json` 确认应用存在
根据上下文为低代码Agent推荐防护规则	低代码	lowcode/capabilities/guardrails/guardrails-recommend.md	获取目录列表，分析Agent上下文，应用并验证
为特定范围或工具推荐防护规则	低代码	lowcode/capabilities/guardrails/guardrails-recommend.md § 范围或工具特定过滤	目录分析后按范围或工具名称筛选候选规则
验证现有防护规则配置是否正确	低代码	lowcode/capabilities/guardrails/guardrails-recommend.md § 验证模式	检查每条防护规则的正确性、可操作性和相关性
根据上下文为代码型Agent推荐防护规则	代码型	coded/capabilities/guardrails/guardrails-recommend.md	获取目录列表 + SDK文档，分析Agent代码，应用并验证
为特定范围或工具（代码型）推荐防护规则	代码型	coded/capabilities/guardrails/guardrails-recommend.md § 范围和工具过滤	目录分析后按 `@tool` 函数或范围筛选候选规则
检查、验证、诊断或修复现有代码型防护规则配置是否正确（位置 / 范围）	代码型	coded/capabilities/guardrails/guardrails-recommend.md § 验证模式	先获取SDK文档（范围/位置的权威来源）；同时获取目录列表以确认相关性/权限 — 然后检查正确性、可操作性和相关性 — 就地修复
在流程中嵌入低代码Agent，或搭建多Agent解决方案	低代码	lowcode/lowcode.md § 功能注册表	`lowcode/capabilities/inline-in-flow/inline-in-flow.md` 、 `lowcode/capabilities/process/solution-agent.md`
运行低代码评估	低代码	lowcode/evaluations/evaluate.md	`lowcode/evaluations/evaluators.md` 、 `lowcode/evaluations/evaluation-sets.md` 、 `lowcode/evaluations/running-evaluations.md`
为已发布的Orchestrator包运行离线评估	低代码	lowcode/evaluations/orchestrator-eval-run.md	使用 `uip or eval run-offline-evals` （要求包已发布至Orchestrator）
验证、打包、发布、上传或部署低代码Agent	低代码	lowcode/lowcode.md	`lowcode/project-lifecycle.md` 、 `lowcode/solution-resources.md`
调试 / 端到端运行低代码Agent并检查其输出	低代码	lowcode/debug.md	`lowcode/project-lifecycle.md` § `uip agent debug`
在流程中嵌入代码型Agent（解决方案级）	代码型	coded/embedding-in-flows.md
在流程中使用代码型Agent	代码型	coded/flow-integration.md
在流程中将代码型Agent用作其他Agent的工具	代码型	coded/flow-integration.md § 模式3
对PDF或TXT进行摘要 / 研究 / 合成（DeepRAG，代码型）	代码型	context-grounding-patterns.md	coded/capabilities/deeprag/planning.md
对PDF或TXT进行摘要 / 研究 / 合成（DeepRAG，低代码）	低代码	context-grounding-patterns.md	lowcode/capabilities/built-in-tools/deeprag/planning.md
使用LLM逐行处理CSV行（BatchTransform，代码型）	代码型	context-grounding-patterns.md	coded/capabilities/batch-transform/planning.md
使用LLM逐行处理CSV行（BatchTransform，低代码）	低代码	context-grounding-patterns.md	lowcode/capabilities/built-in-tools/batch-transform/planning.md
通过CLI管理上下文接地索引（列出 / 创建 / 摄入 / 搜索）	平台	`uipath-platform/references/context-grounding/index-management.md`	`uip context-grounding` — 跨领域CLI，归 `uipath-platform` 所有

Resources

资源

UiPath Python SDK: https://uipath.github.io/uipath-python/
UiPath Evaluations: https://uipath.github.io/uipath-python/eval/

UiPath Python SDK: https://uipath.github.io/uipath-python/
UiPath Evaluations: https://uipath.github.io/uipath-python/eval/