OutSystems

The AI agent actions documentation describes tool calling directly: server actions are exposed to an agent, and the AI model autonomously decides which action or sequence of actions is appropriate by analyzing the prompts and the purpose of each exposed action, calling a single action, a sequence, or the same action repeatedly.

Agents connect to APIs, databases, ERP, CRM and legacy systems through prebuilt connectors and extensible services, wrapping and extending core systems without replacement, and Model Context Protocol support gives agents direct access to enterprise systems, external tools and services.

Forge components extend the tool surface, with the documentation giving OmniDoc2MD as a worked example of adding a component and exposing its server action as an agent action.

Sourcesuccess.outsystems.com AI agent actions documentation, outsystems.com Agent Workbench GA announcementread 2026-08-31

The agentic patterns documentation sets out named multi-agent architectures including a shared-memory pattern where agents read from and write to shared state and communicate implicitly by modifying it, and a network pattern of autonomous peer agents interacting in a graph-like structure without a central controller.

The building agentic workflows documentation combines agents with ODC workflows, where automatic activities call an agent's service action, human activities pause for approval, and validation branches route invalid results back to a prior step to rerun the agent with feedback. Agents are coordinated side by side, in sequence, in hierarchy, and with or without humans in the loop, through a visual interface. Agentic Enterprise Orchestration, launched at ONE in June 2026, is the current generation of this layer.

Sourcesuccess.outsystems.com agentic patterns and building agentic workflows documentationread 2026-08-31

The platform grounds agents in the OutSystems Enterprise Context Graph, a maintained operational knowledge layer over the customer's application estate that the vendor states grounds any coding tool or LLM in shared context, extending its contextual architecture across entities, relationships, roles and business logic.

Agent configuration begins with grounding data connecting the agent to internal databases or external APIs so responses rest on current factual information. Integrated semantic search shipped with Agentic Enterprise Orchestration at ONE in June 2026.

Document ingestion is documented through Forge components that convert Word, PDF, spreadsheet, presentation, HTML and plain text binaries to Markdown while preserving structure and extracting images.

Sourcesuccess.outsystems.com creating an agent and AI agent actions documentation, outsystems.com ONE 2026 platform announcementread 2026-08-31

The building agentic workflows documentation states that agents may require human oversight for high stakes or low confidence decisions and documents the mechanism: a Human activity element placed in the workflow pauses execution until an assigned user or role acts, the assigned person sees the agent's output on a task screen and clicks Approve or Reject, and that action raises an event closing the activity so the workflow resumes on the human's decision.

The agentic patterns documentation gives the same pattern applied to a vendor approval workflow where the agent pauses after generating a risk report. A validation branch can route a rejected result back to a prior step to rerun the agent with feedback. Separately, Agent Guardrails are enforced in the runtime and cannot be bypassed once enabled, covering prompt attack blocking, PII masking and harmful content filtering.

Sourcesuccess.outsystems.com building agentic workflows and agentic patterns documentationread 2026-08-31

The vendor operates a public Trust Center at security.outsystems.com carrying certification records and security advisories. Attestations include SOC 2 Type II, ISO 27001 and ISO 22301 certified by BSI, ISO 27017 and ISO 27018 for cloud security, and CSA STAR self-assessment, with OutSystems Developer Cloud separately holding SOC 2 attestation evaluated by Baker Tilly and SOC 1 Type 2 attestation.

Named customer-facing controls are documented: an identity service providing role-based access to screens, data and logic flows with administrator-controlled permissions, single sign-on and external authentication, and a formal logical access procedure. Agent Guardrails are enforced in the runtime rather than at the application layer, detecting and blocking prompt attacks, masking or blocking PII before data reaches a model provider, and filtering harmful content.

Sourceoutsystems.com evaluation guide security and certifications pages, security.outsystems.com Trust Center, ODC attestation announcementsread 2026-08-31

The ODC monitoring documentation documents distributed traces in which an agent is a filterable asset in its own right, with traces filterable by stage, asset, element type, trace status, total duration, date and time, and user, retained up to four weeks and queryable in two-week intervals, and spans aggregated so an agent's execution can be read both as its own trace and as a span inside a calling app's trace.

Logs carry Error, Warning and Information severities, are generated automatically or through developer-placed LogMessage actions, and link to related logs and activities for root-cause work. Agent Evaluations return quality scores with full execution traces.

Sourcesuccess.outsystems.com monitoring and troubleshooting apps documentationread 2026-08-31

OutSystems documents a memory primitive, but the developer wires the store and no controls over it are published. The state persistence section of the agentic apps documentation says the StoreMemory action in AgentFlow lets developers explicitly save previous user queries, model outputs, intermediate decisions or system states for recall in later interactions, retrieved into subsequent prompts.

The agent creation documentation adds a SessionId passed by the consumer app, with conversation state written to an ODC entity in the customer's own database, and the agentic patterns documentation describes a shared memory pattern for coordinating multiple agents. No retention period, purge path or review and deletion surface for stored memory is documented.

Sourcesuccess.outsystems.com agentic apps in ODC pageread 2026-09-29

The vendor published ODC self-hosted deployment in March 2026, under which customers run their apps, data and AI agents in their own private cloud, public cloud, or on-premises Kubernetes infrastructure while OutSystems continues to manage platform services, with single-tenant runtime provisioning from the ODC Portal and a secure pull mechanism for updates. The vendor states this addresses customers requiring absolute control over hosting environments for data residency, security or regulatory compliance mandates.

The ODC product page confirms the split of OutSystems-managed platform services against runtime applications in customer infrastructure, and documents a secure private gateway connecting ODC to on-premises databases, APIs and enterprise systems without moving data. A self-hosted provisioning repository supporting Kubernetes and OpenShift is published under the vendor's GitHub organization, and the evaluation guide documents self-managed infrastructure across multiple cloud providers and on-premises for the OutSystems 11 platform.

Sourceoutsystems.com ODC self-hosted product update, developer cloud product page and deployment evaluation guide, github.com/OutSystems/outsystems-hybrid-provisionread 2026-08-31

Agent Workbench shipped an agent marketplace at general availability in September 2025 alongside MCP support. The vendor operates Forge, a public browsable catalog of numbered, individually addressable and documented components that install into an app and whose server actions are exposed to agents, with the AI agent actions documentation using the OmniDoc2MD component as its worked ingestion example.

Agent creation is template-driven, starting from defined components for grounding data, prompt, model and tools, and a Mentor capability in beta generates a full agent configuration including instructions, tools and model settings from a plain-language description with conversational refinement. OutSystems launched its first end-to-end Agentic Industry Solution, a Banking Solution for Loan Origination, at ONE in June 2026 as the first of a family.

Sourceoutsystems.com Agent Workbench GA announcement, ONE 2026 announcement and Q2 2026 product update, outsystems.com Forgeread 2026-08-31

The ODC monitoring documentation states that when traces are filtered by an agent, the returned traces are flows triggered by an Event Handler, a Timer, or a REST Expose, naming three distinct entry routes for agents specifically.

Timers are background scheduled jobs configured with OutSystems schedule syntax and forced on demand through the Wake action; events are implemented through the platform's event-driven architecture; REST Expose makes an agent callable as an inbound HTTP endpoint.

Agents are additionally published as service actions consumed by any app in the tenant, embedded into web and mobile interfaces, and reachable externally through the Agent Experience MCP and A2A services.

Sourcesuccess.outsystems.com monitoring and troubleshooting apps, use timers and event-driven architecture documentationread 2026-08-31

Agent Workbench documents connecting a model once for reuse across agents, with support at general availability for AWS Bedrock, Azure OpenAI and Anthropic, plus Gemini, Cohere, Mistral, Databricks, AI2 and IBM watsonx, custom-built models on Vertex AI and open-source models on Hugging Face.

An expanded Amazon Bedrock partnership announced in Q2 2026 gives teams access to more than one hundred large language models through a single set of credentials, and the vendor documents swapping models as pricing or performance shifts without rewriting underlying logic. The vendor positions the platform explicitly as insulating customers from LLM lock-in.

Sourceoutsystems.com Agent Workbench GA announcement, Q2 2026 product update and ONE 2026 platform announcementread 2026-08-31

The ODC REST APIs documentation publishes APIs for the platform itself, authenticated through API clients using OpenID Connect over OAuth 2.0 client credentials, with twelve named references: User and Access Management, Portfolio v2, Build Operations, Native Mobile Build, Deployments, Dependency Management, Asset Repository, Asset Configurations, Environment Configurations, Code Quality, External Library Generation Service and Subscription. Agents are also exposed through REST Expose as inbound endpoints, and OutSystems announced Agent Experience in June 2026 as a layer of A2A and MCP services, though no addressing details for those services are published.

Sourcesuccess.outsystems.com ODC REST APIs pageread 2026-09-29

Agent Evaluations validate agent logic against a Golden Dataset of inputs, expected outputs and expected tool calls, returning quality scores and full execution traces, with an automatic judge scoring results rather than requiring manual inspection.

The vendor describes Evaluations as replacing manual one-off testing with a repeatable validation process, and frames advanced agent evaluations launched at ONE 2026 as validating the outcomes agents are responsible for the way unit tests validate code.

ODC separately documents debugging with breakpoints, step-by-step execution and runtime value inspection, and automated testing strategies for application delivery.

Sourceoutsystems.com ODC Agent Evaluations product update and ONE 2026 announcement, success.outsystems.com agentic development documentationread 2026-08-31

Agents act through server actions selected by the model, through prebuilt connectors to ERP, CRM, databases and legacy systems, and through Model Context Protocol, all of which are programmatic interfaces.

No browser control, navigation, form filling, screen interaction, visual grounding or desktop automation appears in the agentic apps documentation, the AI agent actions documentation, the agentic patterns documentation, or any product or launch page, and the vendor makes no claim in that territory.

The platform's legacy modernization path analyzes COBOL and Lotus Notes systems to rebuild their functionality as new applications, which is code transformation rather than interface operation.

Sourcesuccess.outsystems.com agentic apps and AI agent actions documentation, outsystems.com ONE 2026 announcementread 2026-08-31