Creatio vs OutSystems (2026)

Named productivity integrations put agents inside Outlook, Teams and Zoom with results syncing back to the CRM, and a marketplace publishes connectors, ready-to-use apps and templates. Agents act as well as read, creating and updating records, generating quotes and triaging cases inside the customer's own system. To add a connection of its own, a customer can use no-code web service integration, which lets a business process call any third-party REST API without code, and developers can build custom RESTful configuration services.

Sourceacademy.creatio.com integrations documentation and marketplaceread 2026-09-01

Agents call tools 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, such as OmniDoc2MD, whose server action can be exposed as an agent action.

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

Creatio began as a business process management product, and the platform still carries the control flow. A visual process designer builds multi-step processes with conditional branching, and ProcessEngineService lets an external app start them. Agents are composed from a role, instructions, an explicit skill list and a set of low-level actions, and the conversational workspace runs several agent dialogues in parallel, each holding its own context and permissions. Business processes can also call third party web services mid flow through no code integration.

Sourceacademy.creatio.com 8.3 release notes, process designer and integrations documentationread 2026-09-01

Named multi agent architectures include 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.

Agents combine 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, is the current generation of this layer.

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

Business processes fire on record events and schedules and can invoke agents as steps, agents run against sales, marketing and service workflows, and the Productivity agent acts on calendar state by finding available slots across participant schedules automatically. The agent reaches people where they already work rather than only in the CRM, following users into Outlook, Teams and mobile, with a conversational workspace as the direct surface.

Sourceacademy.creatio.com 8.3 release notes and process designer documentationread 2026-09-01

Agent runs start from three entry routes, an Event Handler, a Timer or a REST Expose. Timers are background scheduled jobs configured with OutSystems schedule syntax and forced on demand through the Wake action, events run through the platform's event driven architecture, and 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

Agents work from the buyer's own content. Every data object, relationship and workflow in the customer's Creatio instance is natively accessible to agents, so they ground on the customer's CRM records, and skills such as record summarization and lead scoring read those objects directly. Separately, customers upload documents for summarization or analysis, with the content held in customer-dedicated storage and extraction performed inside the platform with no external system handling it. A Knowledge agent maintains and generates knowledge base articles from that material.

Sourceacademy.creatio.com Creatio.ai data privacy and AI agent documentationread 2026-09-01

Agents are grounded in the OutSystems Enterprise Context Graph, an operational knowledge layer over the customer's application estate that OutSystems says grounds any coding tool or LLM in shared context, spanning entities, relationships, roles and business logic.

Agent configuration begins with grounding data that connects the agent to internal databases or external APIs so responses rest on current factual information, and integrated semantic search shipped with Agentic Enterprise Orchestration at ONE.

Forge components ingest documents, converting 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 conversational workspace runs several agent dialogues in parallel, each holding its own context and permissions within the dialogue. Creatio does not say what an agent retains after a conversation ends, for how long, or whether retention is scoped per user, per team or per workspace, and it does not describe agents learning from a team's actual sales patterns.

Sourceacademy.creatio.com 8.3 release notes conversational workspace sectionread 2026-09-01

OutSystems offers a memory primitive that the developer wires to a store. 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. A SessionId passed by the consumer app writes conversation state to an ODC entity in the customer's own database, and a shared memory pattern coordinates multiple agents. OutSystems does not describe a retention period, purge path or review and deletion surface for stored memory.

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

Oversight is configurable at the agent definition itself. Each AI Agent carries limitations and restrictions, where the customer specifies what the agent must not do and what limits apply to its actions and data access, and a list of available skills and low level actions, so a skill the customer has not added cannot be used at all. Access to the AI is gated by a system operation permission, role-based access restricts both data and model access, and the platform supports multi-level approvals within business processes.

Sourceacademy.creatio.com 8.3 release notes agent components and Creatio.ai permissions documentationread 2026-09-01

Agents can be held for human oversight on high stakes or low confidence decisions. 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.

In one example, a vendor approval workflow pauses after the agent generates 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

Access follows least-privileged role-based access control with fine-grained roles restricting both data and model access, plus system operation permissions gating who may invoke the AI at all, and row and column level security. External access uses OAuth-based authorization, and audit logs run across the platform.

Creatio runs regular internal and external penetration testing under OWASP methodology and third party scanning, complies with SOC 1, SOC 2 and ISO 27001, and supports GDPR and HIPAA. A separately deployed LLM instance is hosted in the same region as the customer's site, the provider retains no customer data and does not train on it, and uploaded files are held in storage dedicated to the customer.

Sourcecreatio.com/our-technologies/security and academy.creatio.com Creatio.ai data privacy documentationread 2026-09-01

OutSystems runs a public Trust Center at security.outsystems.com with 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.

An identity service provides 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

Creatio AI Studio records every request an agent handles as a run with a full trace, showing the text sent to the model and the arguments each tool was called with, beside an immutable audit log of who changed what, when and with what result, and per agent spending budgets.

Sourceacademy.creatio.com/guides/ai-studio/creatio-ai-studio-overviewread 2026-10-01

Distributed traces treat an agent as a filterable asset in its own right, 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 are 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 LogMessage actions developers place, 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

Beyond shared multi tenant software as a service, Creatio can be installed and run on site on the customer's own infrastructure, and a dedicated cloud option is offered on the Unlimited tier. Every cloud instance runs on an audited security foundation with regional hosting, and the separately deployed LLM instance is hosted in the same region as the customer's Creatio site.

Sourceacademy.creatio.com on-site deployment documentation and Creatio.ai data privacy pageread 2026-09-01

With ODC self hosted deployment, 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.

OutSystems aims this at customers who need absolute control over hosting environments for data residency, security or regulatory compliance mandates. A secure private gateway connects ODC to on premises databases, APIs and enterprise systems without moving data.

A self hosted provisioning repository supporting Kubernetes and OpenShift is published on OutSystems' GitHub, and the OutSystems 11 platform runs on self managed infrastructure across multiple cloud providers and on premises.

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

A browsable list names the agents that ship out of the box, which depend on the apps installed.

They include a Sales AI assistant consolidating the sales skills, a Productivity agent that finds available time slots across participant schedules, a Case resolution agent that summarizes cases and suggests resolutions, a Knowledge agent that generates case articles, and an Email generation agent for branded marketing emails, alongside prebuilt agents for lead conversion scoring, account research and quote generation. A marketplace of ready-to-use apps, connectors and templates sits alongside them.

Sourceacademy.creatio.com AI agent list and 8.3 release notesread 2026-09-01

Agent Workbench shipped an agent marketplace at general availability alongside MCP support. Forge, a public browsable catalog of numbered, individually addressable and documented components, installs components into an app and exposes their server actions to agents, OmniDoc2MD among them.

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, 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 Prompt Agent Designer lets the builder choose across several LLM providers, with Anthropic Claude, OpenAI and Google Gemini named, and set temperature and other model specific parameters per agent, inside a registry of approved models. Creatio does not say whether every provider is available on every plan.

Sourceacademy.creatio.com/guides/ai-studio/creatio-ai-studio-overviewread 2026-10-01

In Agent Workbench a model is connected once and reused 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 gives teams access to more than one hundred large language models through a single set of credentials, and models can be swapped as pricing or performance shifts without rewriting underlying logic. OutSystems pitches the platform 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

Creatio exposes several external interfaces, OData 4 and OData 3 REST services exposing every Creatio object for CRUD operations with OAuth 2.0 authorization, a DataService for batch and filtered requests, ProcessEngineService for running business processes from an external app, and custom RESTful configuration web services a developer can create, all set out on a full developer documentation site. Postman collections of worked CRUD examples are published, and no-code web service integration lets a business process call any third-party REST API without code.

Sourceacademy.creatio.com integrations and API documentationread 2026-09-01

ODC publishes REST 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 has announced Agent Experience as a layer of A2A and MCP services, without publishing addresses for those services.

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

An evaluation harness lets customers test their own agents, with test cases written once and graded on content and on operational checks such as latency, cost and which tools were called, and the live Preview panel shows the full reasoning trace beside each answer while building.

Sourceacademy.creatio.com/guides/ai-studio/creatio-ai-studio-overviewread 2026-10-01

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.

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

ODC also offers 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 operate on the customer's own CRM objects through skills and low-level actions such as changing a record, validating data or reading a lookup value, and reach outside systems through OData services, custom web services and no-code web service calls, all programmatic routes. Creatio does not describe a hosted or local browser, desktop session, remote computer control, web scraping or a third party browser engine.

Sourceacademy.creatio.com 8.3 release notes agent actions and integrations documentationread 2026-09-01

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. OutSystems does not describe browser control, navigation, form filling, screen interaction, visual grounding or desktop automation, and makes no claim in that territory. The platform's legacy modernization path analyzes COBOL and Lotus Notes systems and rebuilds their functionality as new applications through code transformation.

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