uipath-platform

UiPath Platform — uip CLI Assistant

Comprehensive guide for UiPath Cloud / Orchestrator / Studio Web / Integration Service, end-to-end via the uip CLI. For uip solution lifecycle load uipath-solution; for PDD/SDD design & task planning load uipath-planner.

Route Diagnostic Intent Before Platform Work

Classify the requested outcome before running any command:

1. Causal outcome → hand off immediately. User wants an explanation, diagnosis, or root cause for undesirable existing behavior → invoke the Skill tool with uipath-troubleshoot (name exactly as it appears in your available-skills list) before running anything. No preliminary job/log/trace fetching — troubleshoot owns evidence collection. Prose telling the user to use troubleshoot is not a substitute for the Skill call.
2. Operational outcome → stay here. Inspect current state without a causal question, perform CRUD or lifecycle actions, validate an input before applying it, or execute an already-diagnosed platform fix.
3. Mixed request → troubleshoot first. Hand off the diagnosis; return here only for the platform mutation that applies the confirmed fix.
4. Sibling unavailable → degrade gracefully. State the handoff could not run; give the entity, scope, and time window needed to retry the investigation. Do not improvise a platform-only root cause.

Use the CLI. Don't roll your own REST.

Always reach for uip CLI commands first. The CLI covers auth, Orchestrator (folders, processes, jobs, machines, users, roles, sessions, calendars, settings, audit logs, credential stores, feeds, attachments), resources (assets, queues, queue items, storage buckets, bucket files, libraries, webhooks, triggers), Integration Service (connectors, connections, activities, IS triggers), traces, and licensing end-to-end.

Hand-rolling HTTP calls — reading ~/.uipath/.auth and POSTing to /odata/... or /orchestrator_/... — almost always misses something the CLI gets right: the X-UIPATH-OrganizationUnitId folder header, OData filter shape (Key eq '...' with escaped single quotes), pagination envelope, retry semantics, validation error shape, or Result/Code/Data output contract. Reach for raw REST only after you've searched references/uip-commands.md for your task and confirmed no uip command covers it. The CLI is the source of truth.

If you find yourself about to curl https://cloud.uipath.com/... — stop. Search the command index first. Examples of what people often miss:

• "upload a file to a storage bucket" → uip or bucket-files upload (NOT a PUT /buckets/.../signedUrl dance)
• "create an asset" → uip or assets create (NOT a POST /odata/Assets)
• "start a job for a process" → uip or jobs start <process-key> (NOT POST /odata/Jobs/UiPath.Server.Configuration.OData.StartJobs)
• "configure an Integration Service connection" → uip is connections create <connector-key> (NOT a hand-rolled OAuth flow)
• "attach a file to a Data Fabric record" → uip df files upload <entity-id> <record-id> <field-name> --file <path> (NOT records insert / records update with the file value — the platform silently strips FILE columns and returns Success, see references/data-fabric/data-fabric.md Rule 6)

When to Use This Skill

Load this skill BEFORE writing any code that talks to UiPath. Specific triggers:

• Auth & tenant: login, logout, switch tenant, named login profiles via --profile <name>, ~/.uipath/.auth, OAuth token, organization

• Orchestrator core: folders (list/get/create/edit/move/delete/runtimes), processes/releases, jobs (start/stop/logs/traces/healing-data), packages (upload/download/versions), machines, users / roles / sessions (incl. DirectoryUser/DirectoryGroup/DirectoryRobot/DirectoryExternalApplication), licenses, calendars, settings, audit logs, credential stores, feeds, attachments

• Resources (Orchestrator-scoped): assets (text/integer/bool/credential), queues + queue items, storage buckets + bucket files (upload/download/get-download-url/get-upload-url), libraries (.nupkg), webhooks (HMAC signing), triggers (time/queue/api)

• Integration Service: connectors, connections (OAuth flow), activities, IS triggers, agent-workflow reference resolution

• **Data Fabric **: UiPath's structured, typed data store. **⛔ STOP — before ANY uip df command, Read references/data-fabric/data-fabric.md.The reference carries Critical Rules (folder-scope prompt flow, irreversible-op gates, complex-field config), request-body schema, per-type operator matrix, and routes to topic files: entity-schema.md, records-query.md, filter-platform-contract.md, choice-sets.md, file-attachments.md, bulk-import.md. Surfaces:

  • Entities — schemas with typed columns, per-type constraints (lengthLimit, minValue / maxValue, decimalPrecision), choice-set / relationship / file fields, addFields / updateFields / removeFields evolution.
  • Records — insert / update / delete / list / get / query with server-side filters, sorting, pagination, group-by, and aggregates (COUNT, SUM, AVG, MIN, MAX).
    • DF filter body uses filterGroup.queryFilters[] — full shape in records-query.md.
  • Files — binary attachments stored on FILE-typed fields via files upload / download / delete (record-level writes silently strip FILE values; the dedicated verbs are mandatory).
  • Choice sets — shared enumerations consumed by CHOICE_SET_SINGLE / CHOICE_SET_MULTIPLE fields; values use immutable integer NumberIds, not labels.
  • Folder scoping — tenant-level OR folder-scoped via --folder-key <GUID> on every write, --include-folders on entities list / choice-sets list.
  • CSV bulk import — uip df records import <entity-id> --file <path.csv> --output json. Basic field types only; complex fields (CHOICE_SET, RELATIONSHIP, FILE, AUTO_NUMBER) require records insert --file <json>.

  For Query / Create / Update / Delete / GetById connector nodes inside a .flow, hand off to uipath-maestro-flow — that skill owns the in-flow node JSON, bindings_v2.json, and connection-resource layout.

• LLM Gateway — BYO product configurations: uip llm-configuration byo-connections (list / get / create / update / delete / list-product-configs). Register tenant-owned OpenAI / Azure OpenAI / AWS Bedrock / Google Vertex / Anthropic / OpenAI-compatible keys against UiPath product features (agents, agenthub, jarvis, IXP, agent builder, ECS). Two input shapes: single-mapping (for AnyModelWithOwnAdditions features) and repeated --mapping (required for AllModels / AnyModel). Server-side validation is mandatory.

• LLM Gateway — diagnose a failing BYO config: re-probe the underlying IS connection with byo-connections get <id> --force-refresh, force a fresh server-side probe with an idempotent update, audit the tenant with list --include-connection-details filtered on connectionState != Enabled, check catalog drift with list-product-configs, and cross-reference trace evidence with uip traces spans get <trace-id>. The gateway does not expose per-request invocation logs via CLI — diagnosis is current-state + trace evidence only. See references/llmgateway/byo-connections.md § Diagnostics. For tenant-wide AI Trust Layer policy that may be overriding routing, see uipath-governance.

• AI Trust Layer — BYO guardrail (BYOG) configurations: uip guardrails byo-configurations (list / list-validators / probe / create / update / delete) — manage tenant-registered external guardrail validator providers (e.g. Azure AI Content Safety, Databricks AI Guardrails), each backed by an Integration Service connection. ValidatorName is tenant-unique and is the only value agents reference (ByoValidator(<ValidatorName>) — the connection resolves server-side). Before creating, list (the name must be free) and uip is connections list (for --connection-id); create always probes the connection/validator pair server-side and aborts if the probe fails, with no skip flag, and update re-probes whenever --connection-id changes. probe and list-validators test a pairing without saving anything; update merges supplied fields and can flip --enabled/--disabled; delete requires --force; no get verb. See references/guardrails/byo-configurations.md. For authoring a guardrail against one of these configurations (low-code or coded), see uipath-agents.

• Traces: uip traces spans get <trace-id> (LLM/agentic execution observability)

• Context grounding: knowledge indexes for semantic search / RAG — uip context-grounding (list / create from a bucket or connection / ingest / retrieve to poll ingestion status / search / delete). Agents and flows consume these indexes as tools. See references/context-grounding/index-management.md.

• Platform licensing: tenant license allocations, user/group bundle assignments, consumables reporting (uip platform tenants licenses, users licenses, groups rules, licenses consumables get — the only consumables verb; summary/daily/folders are --mode values)

• CLI tooling itself: uip tools list/search/install, uip mcp serve

For uip solution lifecycle (init / pack / publish / deploy / activate / upload) and CI/CD pipelines that build and deploy UiPath solutions, load uipath-solution.

Auth token location

The default login stores credentials at ~/.uipath/.auth:

UIPATH_URL=https://cloud.uipath.com
UIPATH_ORGANIZATION_NAME=my_org
UIPATH_TENANT_NAME=my_tenant
UIPATH_ACCESS_TOKEN=eyJ...
UIPATH_ORGANIZATION_ID=...
UIPATH_TENANT_ID=...

Named profiles store credentials at ~/.uipath/profiles/<name>/.auth. Use named profiles when the user asks to keep multiple UiPath logins on the same machine:

uip login --profile dev --output json
uip login status --profile dev --output json
uip login which --profile dev --output json

Rules:

• --profile <name> is a global option. Pass it on every uip command that should use that login, for example uip --profile dev or folders list --output json.
• default means the built-in unprofiled login and maps back to ~/.uipath/.auth.
• Profile names may contain only letters, numbers, ., _, and -. Never use paths like ../prod.
• --profile and auth-command --file <folder> are mutually exclusive. Use one or the other.
• A missing named profile does not fall back to ~/.uipath/.auth or Robot credentials. Tell the user to run uip login --profile <name>.

These tokens can be reused for direct Orchestrator REST API calls when CLI commands don't cover a use case. If a named profile is active, read the path from uip login which --profile <name> --output json rather than assuming ~/.uipath/.auth.

Quick Start

Step 1 — Authenticate

Before interacting with Orchestrator, solutions, or Integration Service, the user must be logged in.

Always check first — most sessions are already authenticated:

uip login status --output json

If it reports Logged in, skip the rest of this step. There is no --check flag — status is the verification subcommand.

If the user names a profile, check that profile explicitly:

uip login status --profile dev --output json

Interactive login (browser OAuth2): uip login opens a browser window on the user's machine and blocks until they complete it. In a non-interactive or automated session, do NOT run it yourself — tell the user to run it and wait.

uip login --output json

For a named interactive login:

uip login --profile dev --output json

For a custom authority (e.g., alpha.uipath.com):

uip login --authority "https://alpha.uipath.com/identity_" --it --output json

For non-interactive (CI/CD) scenarios, use client credentials:

uip login --client-id "<ID>" --client-secret "<SECRET>" --tenant "<TENANT>" --output json

Step 2 — Select a Tenant

List available tenants and set the active one:

uip login tenant list --output json
uip login tenant set "<TENANT_NAME>" --output json

Step 3 — Explore Orchestrator

List folders to orient yourself:

uip or folders list --output json

Step 4 — Work with Orchestrator Resources

Choose the appropriate operation from the Task Navigation table below. For uip solution ops, load uipath-solution.

Task Navigation

Resolving UiPath Studio

Some operations (creating projects, validating, running workflows, packing) require UiPath Studio. When Studio is needed:

1. Check for a running instance first:

   rpa-tool list-instances --output json
   

2. If no instance is running, try the standard install location:

   rpa-tool start-studio --output json
   

3. If that fails (version too old, not found, etc.) — ASK THE USER where their Studio build is located. Do NOT search the entire filesystem. Common locations include:

   • C:\Program Files\UiPath\Studio
   • A dev build directory (e.g., dev4/Studio/Output/bin/Debug)
   • A custom install path

4. Once you have the path, pass it explicitly:

   rpa-tool start-studio --studio-dir "<STUDIO_DIR>" --output json
   

Never spend time searching for Studio automatically. If the default doesn't work, ask immediately — the user knows where their build is.

Key Concepts

UiPath Platform Hierarchy

Organization
  └── Tenant(s)
        └── Folder(s)              ← Orchestrator folders (logical containers)
              ├── Processes         ← Published automation packages
              ├── Assets            ← Key-value configuration (Text, Bool, Integer, Credential, Secret)
              ├── Queues            ← Work item queues for distributed processing
              ├── Jobs              ← Running/completed process executions
              ├── Triggers          ← Event-based or queue-based job triggers
              ├── Schedules         ← Time-based job scheduling (cron)
              ├── Storage Buckets   ← File storage for automation data
              ├── Machines          ← Robot execution environments
              └── Robots            ← Attended/Unattended execution agents

Robot Types

Folder Types

Asset Types

CLI Overview

The UiPath CLI (uip) is a unified command-line tool for interacting with the UiPath platform:

Global Options

Every uip command accepts:

Always use --output json when calling uip commands programmatically. JSON is compact and machine-readable.

To narrow list results, use the noun's own filter flag (--state Faulted, --type Text, --status New, --name, --process-name, --search). The backend filters before sending; pagination stays correct. Per-noun flags: references/uip-commands.md. Never list-everything-then-filter-mentally.

Use --output-filter (JMESPath) for output reshaping or for fields with no server-side flag — e.g., --output-filter "Data[].{id: id, name: name}", or filtering by a derived/computed value. Don't reach for it when the server already has a filter for that attribute.

Deployment Notes

• Starting jobs requires runtimes. If you get error 2818 "no runtimes configured", the target folder needs machine templates with Unattended/Development runtimes assigned.
• For uip solution pack / publish / deploy / activate flows, load uipath-solution. This skill owns the auth and Orchestrator surface those flows depend on; the solution skill owns the lifecycle commands.
• Fallback: direct REST API. When CLI tools don't support an operation, use the Orchestrator REST API with the access token from ~/.uipath/.auth. See references/orchestrator/orchestrator.md - REST API.

References

• CLI Command Reference — Every uip command with workflow links
• Orchestrator — Concepts, folders, jobs, processes, machines, users
• Resources — Assets, queues, buckets, triggers, libraries, webhooks
• Solutions — Solution lifecycle (uip solution init/pack/publish/deploy/activate)
• Planner — PDD/SDD design + multi-skill task planning (Process → Solution Design Document → task list)
• Traces — Spans — LLM execution trace observability
• Traces — Feedback — Annotate traces with sentiment and comments
• Integration Service — Connectors, connections, activities, resources
• Data Fabric — Entity schemas, records CRUD, query filters and aggregates, choice sets, file attachments, CSV bulk import, folder scoping
• LLM Gateway — BYO Connections — Register tenant-owned LLM keys against UiPath products
• Guardrails — BYOG Configurations — Manage tenant-registered bring-your-own guardrail (BYOG) configurations and diagnose their underlying Integration Service connections
• Licensing — Tenant allocations, user/group bundles, consumables reporting
• Coded Workflows — Building coded automation projects

Trouble? If something didn't work as expected, use /uipath-feedback to send a report.