UiPath
Also known as: UiPath Platform, Maestro, Autopilot, Agent Builder, PATH
Agentic automation platform that orchestrates UiPath, coded and external agents alongside robots and people, with escalations to humans, agent memory, scored evaluations, step-level traces and self-healing UI automation.
UiPath grew from robotic process automation into a platform for orchestrating AI agents alongside robots and people. Agents of every origin run on it, from UiPath's own system agents such as Autopilot and Healing Agent to low code agents built in Studio Web, coded agents built with UiPath SDKs in a developer's own IDE, and external agents invoked inside UiPath processes. All of them are managed, scheduled and monitored through Orchestrator and combined with Maestro for business process orchestration.
An agent acts only through tools it has been granted, draws on permissioned indexes for context, and can escalate to a person through Action Center for validation, approval or manual help, with escalations routed to a user, a group's least-loaded member or round robin. Agent memory, in preview, keeps past cases and resolved escalations in memory spaces that can be inspected, edited and deleted, so a comparable case is handled the next time without asking again. Orchestrator starts agents on schedules and when new items arrive in a queue.
Agents are tested with evaluation sets that score output and trajectory from 0 to 100, every run leaves a step-by-step trace for debugging and audit, and the builder chooses and refines the model per agent. UiPath's robots drive real application screens, and Healing Agent recovers automations when an interface changes. The platform runs as Automation Cloud or on the customer's premises as Automation Suite, and UiPath publishes SOC 2 Type 2, ISO 27001, HITRUST, C5 and IRAP attestations. Agent templates, preconfigured with prompts, tools and starter evaluation sets, are available in Automation Cloud and UiPath Marketplace.
At its FUSION conference in September 2026, UiPath made its coding agents generally available, so its own coding agents and tools such as Claude Code, Cursor and Codex work natively with UiPath folders, jobs, queues and connections. It added Delegate, a productivity agent that saves routines from a user's actions and runs them on demand, on a schedule or from triggers, an MCP Connector for calling tools on any compatible MCP server, and governance controls including a Model Hub, a runtime checker for agent behavior, an LLM as judge guardrail, compliance packs and identity and access policies. Automation Suite now runs on Linux with the full agentic stack.
Vendor details
Canonical URL
https://www.uipath.com
Category
Enterprise operations agent
Subcategory
Enterprise agentic automation and orchestration
Funding status
Public company listed on the New York Stock Exchange under the ticker PATH.
Company status
independent
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
Agents act through explicitly granted tools, including UiPath activities and connections created in Integration Service, draw on permissioned indexes as context, and escalate to people through Action Center. Coded agents are built with UiPath SDKs and deployed to Orchestrator, and agents of any origin, including external ones, run inside UiPath processes alongside robots, apps and human tasks.
In practice
A bank models a loan process in Maestro with BPMN, orchestrating an Agent Builder agent, UiPath robots, and human approvals across multiple systems end to end.
When a target application's UI changes, the Healing Agent adapts the automation automatically so the process keeps running without a maintenance ticket.
A developer uses Autopilot in Studio to turn a plain language description into a working automation, then validates it with self healing agentic tests across SAP and Salesforce.
Sources & related URLs
Research sources
Agentic Index coverage score
13.5 / 14 capabilities · 96%
| Integrations & Tool Calling | Full |
|---|---|
|
Tools connect an agent's reasoning to real actions, giving it access to data in business applications and the ability to execute functions, and an agent can only act through tools it has been explicitly granted, described in the system prompt with when to use them. Integration Service adds an MCP Connector that lets workflows call tools from any compatible MCP server as a native activity, Database Hub to read and write systems such as SQL Server, Oracle and Databricks without custom code, and Relay to reach on premises systems from cloud automations. Sourcedocs.uipath.com/agents (agent tools) and uipath.com/newsroom/uipath-platform-updates-fusionread 2026-10-24 |
|
| Workflow Orchestration | Full |
|
UiPath orchestrates agents of every origin, UiPath system agents, low-code agents, coded agents and external agents, inside one platform, where agents work alongside activities, other agents, apps, human tasks and Maestro for business process orchestration, and are managed, scheduled and monitored through Orchestrator. Sourcedocs.uipath.com/agents/automation-cloud/latest/user-guide/agent-capabilities-in-the-uipath-platform.mdread 2026-09-18 |
|
| Knowledge Grounding & RAG | Full |
|
An index added as agent context gives the agent access to a permissioned knowledge base of the customer's own content, and the builder configures the search strategy and scope that decide what the agent retrieves. Sourcedocs.uipath.com/agents/automation-cloud/latest/user-guide/agent-contexts.mdread 2026-09-18 |
|
| Human Oversight & Guardrails | Full |
|
Escalations, powered by Action apps in Action Center, let a developer have the agent validate business details with a person before running a tool, request approval, or ask for manual assistance on a business exception. Each escalation carries a prompt that tells the agent when to raise it, and is routed to a specific user, to the least-loaded member of a group, to all group members, or round robin. Runtime Checker validates agent behavior against defined policies while the agent is running, not only when it was built, and an LLM as judge guardrail evaluates outputs against custom criteria. Sourcedocs.uipath.com/agents (agent escalations) and uipath.com/newsroom/uipath-platform-updates-fusionread 2026-10-24 |
|
| Security, Identity & Governance | Full |
|
UiPath's trust portal publishes a SOC 2 Type 2 report, an ISO 27001 certificate, a HITRUST certificate, C5, IRAP, HIPAA and Spain's ENS certificate of conformity. The customer-facing controls on the agent layer are Automation Ops policies applied through the AI Trust Layer at tenant level, which control whether users can access and use agents across the organization. Sourcetrust.uipath.comread 2026-09-18 |
|
| Observability & Auditability | Full |
|
Every agent run leaves a trace, a detailed record of the steps taken, data processed, decisions made and results generated, with timestamps, errors, inputs and outputs, so a failed tool call can be inspected at the exact step with its inputs, outputs and error. UiPath positions traces for debugging, performance analysis of latency, errors and throughput, and compliance and auditing as a verifiable record of what the agent did, when and how. Sourcedocs.uipath.com/agents/automation-cloud/latest/user-guide/agent-traces.mdread 2026-09-18 |
|
| Memory & State Persistence | Partial |
|
Agent memory, in preview, keeps memory spaces that several agents can share. Episodic memory holds the inputs, outputs and outcomes of past cases with the feedback attached to them, and items enter it when a person promotes feedback from an agent run. Escalation memory stores how a person resolved an escalation in Action Center. Before each run a recall step embeds the current inputs, finds similar items and adds them to the agent's context as examples, and before raising an escalation the agent checks for a matching resolution. Memory items can be inspected, edited and deleted from the Memory spaces tab. Nothing is written to memory by the agent on its own, and no retention period or expiry is stated. Sourcedocs.uipath.com agents user guide, agent memoryread 2026-10-25 |
|
| Deployment & Data Residency | Full |
|
UiPath comes in two delivery models, Automation Cloud, its cloud service, and Automation Suite, which runs the platform on the customer's own premises, each with its own documentation set. Automation Suite now runs on Linux with the full agentic AI stack, so agents, robots and people work inside infrastructure the enterprise already operates. Sourcedocs.uipath.com/llms.txt and uipath.com/newsroom/uipath-platform-updates-fusionread 2026-10-24 |
|
| Prebuilt Agents, Templates & Packs | Full |
|
UiPath ships agent templates, available on the Agents page in Automation Cloud and in UiPath Marketplace, each preconfigured for a specific task with a system prompt, activity tools with descriptions and starter evaluation sets, needing only minimum configuration to run and open to modification. Sourcedocs.uipath.com/agents/automation-cloud/latest/user-guide/using-agent-templates.mdread 2026-09-18 |
|
| Triggers & Channel Coverage | Full |
|
Agents deploy as processes in Orchestrator, which schedules and launches jobs through time triggers at regular intervals and queue triggers that start the automation whenever new items are added to a queue, so agents run without anyone asking. Sourcedocs.uipath.com/orchestrator/automation-cloud/latest/user-guide/about-triggers.mdread 2026-09-18 |
|
| Model Flexibility & Routing | Full |
|
The builder chooses the model for each agent at design time and refines that choice once evaluations show how different models perform on accuracy, stability, speed and cost, and a custom model can be configured for Context Grounding through the admin guide's LLM configuration. Sourcedocs.uipath.com/agents/automation-cloud/latest/user-guide/choosing-the-best-model-for-your-agent.mdread 2026-09-18 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
With a UiPath SDK, developers build coded agents in their own IDE, package them and deploy them to Orchestrator as standard packages, where they run as processes under the same governance as other automations, and they can connect the project to Studio Web for debugging, evaluation and publishing. Sourcedocs.uipath.com/agents/automation-cloud/latest/user-guide/about-coded-agents.mdread 2026-09-18 |
|
| Testing, Debugging & Optimization | Full |
|
Evaluations check agents against defined cases before and during release. An evaluation pairs an input with an evaluator that checks the agent's output or trajectory against the expected result, evaluation sets group evaluations, and each run produces a score from 0 to 100 with traces of the evaluation runs to diagnose failures and re-run. Evaluations can be created from correct past runs, and evaluation results guide model choice. Sourcedocs.uipath.com/agents/automation-cloud/latest/user-guide/agent-evaluations.mdread 2026-09-18 |
|
| Browser & Computer Use | Full |
|
Robots operate real application interfaces in attended and unattended automation, and Healing Agent autonomously detects and recovers from UI automation failures caused by changing interfaces, network throughput and evolving UI frameworks, using just-in-time analysis of the automation to choose a recovery strategy. Sourcedocs.uipath.com/agents/automation-cloud/latest/user-guide-ha/what-is-healing-agent.mdread 2026-09-18 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Product updates
Autopilot Chat returns to Orchestrator and now works directly on the customer's tenant instead of only answering questions. It can manage processes, jobs, queues, assets, triggers, machines and folders, look into failed jobs and access issues, and help plan, build and deploy automations. Admins pick an approval mode, from asking before every operation to running with no approval prompts, and can connect MCP servers and switch tools and skills on or off.
Bears on: Human approval / guardrails
View sourceBuilding Maestro BPMN processes with a coding agent is now in public preview in UiPath for Coding Agents. A coding agent authors a Maestro BPMN process from the user's description, then helps validate, publish, run and diagnose it, and the skill installs with uip skills install.
Bears on: Agent capability
View sourceAdministrators can now bring their own safety vendor into UiPath's AI Trust Layer, in preview, so agent guardrails run under the customer's own vendor agreement and region. Azure AI Language, Azure Content Safety and Noma are supported, checks can be enforced across the organization, and each evaluation is recorded in the agent trace.
Bears on: Security / enterprise
View sourcePricing
Basic starts at $25 per month, and Standard and Enterprise are quoted by sales. The Community plan is free, and Autopilot is included in the platform license.
Consumption and role based licensing, across robots, agents and platform units.
What is public
The licensing structure (Automation Cloud versus Automation Suite, consumption and role based, Autopilot included, free tier to start) is public. The only published dollar figure is Basic, from $25 per month. Standard and Enterprise are quoted by sales.
Billing mechanics
Platform subscription with consumption and role based licensing across Automation Cloud (SaaS) and Automation Suite (self hosted). Autopilot is bundled into the platform license, while agents, robots and document processing are metered.
Cost watchouts
Enterprise costs scale with unattended and attended robots, agent consumption, document processing volume (IXP) and AI unit usage. Self hosted Automation Suite shifts infrastructure cost to the customer.
Variable cost rationale
Robots, agents, AI units and document processing are licensed by consumption, alongside role based licenses, so cost grows with automation volume. Large enterprise programs span thousands of robots, and at that scale the workload, not the user count, sets the bill. Outside the Basic plan, no unit price, allowance or cap is published. Unit prices and allowances are set in each negotiated quote. Autopilot is included in the platform license, and self hosting on Automation Suite moves infrastructure cost to the customer rather than removing it.
Additional watchouts
Enterprise automation programs accrue cost across robots, agents and AI units, so a full deployment costs the sum of those lines, not a single license.
Sales call required
Yes, required for paid access
Free / trial
Community plan free forever, and a 60 day free trial of Standard
Lowest paid plan
Basic, starting at $25 per month, with up to 2 robots
Key ambiguities
UiPath is a public company with complex enterprise licensing. List prices for robots, agents and platform units are not centrally published, and quotes are customized.
Support SLA / resale
Community gets forum support. Basic includes UiPath Bronze Support and 99.9% uptime.
Missing data
List prices for robots, agents, AI units and document processing, and the tier boundaries.
Related vendors
- 11th Estate — Agentic platform whose AI engine scans markets, matches an…
- Abacum — FP&A platform for growing companies whose AI Modeler builds, edits…
- Adopt AI — AI native accounting and bookkeeping firm whose agents run…
- Aera Technology — Decision intelligence platform where an always on agent executes…
- Akro AI — On premise operational intelligence that automates document heavy…
- alfred_ — AI executive assistant that triages the inbox overnight and scores…
Alternatives to UiPath
The closest documented capability profiles to UiPath among enterprise operations agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Appian13.5 / 14Matches UiPath across all 14 documented capabilities
- Pega13.5 / 14Matches UiPath across all 14 documented capabilities
- ServiceNow13.5 / 14Matches UiPath across all 14 documented capabilitiesUiPath vs ServiceNow →
- Microsoft14.0 / 14Fuller documented coverage on Memory & State Persistence
- Tungsten Automation13.0 / 14A lighter documented profile than UiPath
- Writer13.0 / 14A lighter documented profile than UiPath
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded