September 2026

September 2026 Versionshinweise für Agents in Automation Cloud und Test Cloud.

September 25, 2026

Build and debug agents with Autopilot Agent (Preview)

Autopilot Agent, a coding agent built into Studio Web, is now available. For agents, it can:

• Scaffold an agent with its prompts, tools, and memory
• Debug the agent as it runs in Studio Web
• Build evaluation sets, evaluators, and test cases
• Set guardrails

Autopilot Agent runs on the same UiPath skills and command-line interface (CLI) tooling as UiPath coding agents, and connects to your project and tenant from the browser with nothing to install. Autopilot Agent is now the default Autopilot experience. Classic Autopilot remains available, and you can switch between the two experiences.

For details, refer to Autopilot for Agents (Preview).

Correction, September 25, 2026: This feature was released on September 23, 2026, but was not included in the release notes at the time.

September 22, 2026

Using Data Fabric entities as agent context is now generally available

Agents can now use Data Fabric entities directly as a structured context, letting them query and reason over live or near-real-time, structured system of record without relying on static data snapshots. This lets users query this data in natural language, while existing enterprise access rules and permissions are enforced.

For details, refer to Contexts.

Introducing advanced agents (Preview)

Agents can now be built on the advanced harness, an alternative to the standard reason-and-act loop for long-running, document-heavy work. An advanced agent keeps its intermediate work in a file workspace instead of in the prompt, delegates slices of work to sub-agents and calls its tools programmatically from a sandboxed JavaScript interpreter.

During public preview, advanced agent consumption is 50% off the standard rate.

For details, refer to Advanced agents (Preview).

16. September 2026

Build agents with Coding Agents is now generally available

Building UiPath agents with a coding agent is now generally available. You can build both low-code and coded agents entirely from a coding agent (Claude Code, Codex, Cursor, and others) and terminal.

The uipath-agents skill covers the full lifecycle for both agent types — scaffolding a project, editing prompts and input and output schemas, adding tools, running evaluation sets, and packaging and deploying to Orchestrator. The skill is available to install via uip skills install.

Weitere Informationen finden Sie auf den folgenden Seiten:

• Erstellen Sie Agents mit Codierungs-Agents
• UiPath für Codierungs-Agents

September 15, 2026

UiPath Agents in Flow is now generally available

UiPath Agents in Flow is now generally available, following its public preview in July 2026. You configure the agent's system prompt, model, input and output schema, and tools from the Flow canvas, with no standalone agent publishing step. Flow variables pass to and from inline agents natively, and multiple agents can be chained in series within a single flow.

For details, refer to Agents in Flow.

Correction, September 22, 2026: This feature was released on September 15, 2026, but was not included in the release notes at the time.

14. September 2026

Introducing conversational chat agents in Maestro Flow

Chat agents can now be built as a Maestro Flow, alongside the existing single-prompt Agent Builder path. Modeling the chat experience in Flow unlocks capabilities like intent-based routing, hand-off between specialist agents, deterministic replies, and parallel branches that run while the conversation continues. Both build paths surface to end-users as the same chattable Conversational Agent, meaning you can switch to Flow without disrupting how users reach your conversational agents.

For details, refer to Chat.

Introducing conversational voice agents in Maestro Flow

Voice agents can handle real-time phone calls — answering inbound calls and placing outbound ones. Audio streams straight to a real-time speech model, so callers can interrupt the agent mid-sentence, and tools run during the call.

You can hand off between specialist voice agents without dropping the call, feed the call transcript or a structured call summary into downstream nodes, and let the agent press digits to navigate an external phone tree. Numbers connect over a SIP trunk or your own Twilio account.

For details, refer to Voice.

9. September 2026

Richtlinien für das Agent-Design in Studio Web sind jetzt allgemein verfügbar

Die Richtlinien für das Agent-Design in der Automation Ops-Governance-Richtlinie für Studio Web sind jetzt allgemein verfügbar. Mit den Richtlinien können Sie die folgenden Anforderungen an die Agent-Konfiguration erzwingen, bevor ein Agent veröffentlicht wird:

• Mindestpunktzahl für Agents
• Maximaler Temperaturbereich
• Maximale Tokens pro Agent-Antwort
• Human-in-the-Loop-Eskalation
• Maximale Iterationen pro Agent-Ausführung

Weitere Details finden Sie unter Einstellungen für Studio Web-Richtlinien.

7. September 2026

Einführung des LLM als Richter-Leitplanke [Vorschau]

Eine neue integrierte Leitplanke, LLM als Richter, ist jetzt in der Vorschau verfügbar. LLM als Richter verwendet ein LLM, um Agent-Prompts, Antworten oder LLM-Aufrufe anhand von benutzerdefinierten Anweisungen auszuwerten, die Sie in einfacher natürlicher Sprache schreiben, und schließt die Lücke, die von anderen vorgefertigten Leitplanken übrig wird, die nur eine feste, vordefinierte Kategorie erkennen durch einen verwalteten Klassifizierungsdienst.

Jede Prüfung, die die Guardrail durchführt, stellt einen echten LLM-Aufruf dar, sodass das Richtermodell Agent Units oder Platform Units zusätzlich zur eigenen Nutzung des Agents verbraucht, die separat nachverfolgt wird. Dies gilt überall dort, wo die Leitplanke ausgeführt wird, einschließlich der Agent-Auswertungsläufe bei aktivierter Leitplanke. Weitere Informationen finden Sie unter Vorgefertigte Leitlinien und Lizenzierung.