OutSystems
Also known as: OutSystems Agent Workbench, OutSystems Mentor, OutSystems Agentic Systems Platform, OutSystems Agentic Enterprise Orchestration, OutSystems Agent Experience, OutSystems Developer Cloud, OutSystems ODC, OutSystems Enterprise Context Graph
Enterprise AI powered low code platform whose Agent Workbench lets teams build, test, orchestrate, and govern custom AI agents on top of existing systems, with model choice across many providers, an Enterprise Context Graph, a golden dataset evaluation suite, sovereign deployment control, and built in observability.
OutSystems, based in Boston with roots in Portugal, sells an AI powered low code platform, the Agentic Systems Platform, for building, orchestrating, and governing AI agents alongside applications. Founded in 2001 and now led by chief executive Woodson Martin, it is a privately held enterprise vendor whose network spans more than sixty million end users, over five hundred partners, and customers in more than seventy five countries.
The platform pairs two AI pillars. OutSystems Mentor is an AI partner across the software lifecycle, generating, delivering, and monitoring applications. Agent Workbench, now generally available, is an end to end low code environment for building and orchestrating custom AI agents, with thousands of agents in development across a community of certified builders. It brings three capability sets together. Model and data integrations let teams connect a model once and reuse it, with support for Anthropic, Azure OpenAI, Bedrock, Gemini, Mistral, Databricks, watsonx and open source models, and models can be hot swapped to optimize cost and quality without rewiring.
Lifecycle management covers building, testing, deploying and monitoring agents with low code and the context of the whole app portfolio, and multi agent orchestration runs through a visual, drag and drop interface. Agents are grounded in an Enterprise Context Graph, with guardrails, granular access controls, and built in observability that tracks agent reasoning, quality, and cost. An Evaluations feature tests agent logic against a golden dataset with an automatic judge before anything reaches production.
With ODC self hosted deployment, agents, apps and data run in the customer's own private cloud, public cloud or on premises Kubernetes while OutSystems manages platform services, so the customer controls where agents run and data resides. Agents act through server actions, connectors and MCP, and do not drive a browser. OutSystems targets agent sprawl by putting agents, apps, humans, and workflows under one governed platform, and aims it at enterprises building many custom agents on top of their existing systems.
Vendor details
Canonical URL
https://www.outsystems.com
Category
Agent builder
Subcategory
Enterprise low-code platform for building and orchestrating AI agents
Funding status
Independent and privately held, headquartered in Boston with engineering roots in Portugal, founded in 2001 and led by chief executive Woodson Martin. OutSystems is a large, enterprise proven low code vendor backed by major private investors, whose network spans more than sixty million end users, over five hundred partners, and active customers in more than seventy five countries across twenty plus industries. It launched Agent Workbench into general availability on September 30, 2025, reporting more than five thousand five hundred agents in development, and unveiled its Agentic Systems Platform powered by the Enterprise Context Graph at its 2026 ONE conference, and it is named a Leader in the G2 2026 AI Agent Builder Grid.
Company status
independent
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
OutSystems connects agents to APIs, databases, ERP, CRM, and legacy systems through prebuilt connectors and extensible services, wrapping and extending core systems without rip and replace. Agent Workbench connects a model once for reuse across agents, with broad support for Anthropic, Azure OpenAI, Bedrock, Gemini, Cohere, Mistral, Databricks, IBM watsonx, Vertex AI, and Hugging Face, and the platform works with agentic coding tools including Claude Code, Codex, and Kiro.
In practice
Different teams are spinning up fragmented AI agents with no shared governance, creating sprawl, security gaps, and stalled pilots. OutSystems Agent Workbench puts every agent, app, and workflow under one governed platform with access controls and observability.
You want custom agents deeply wired into your ERP, CRM, and legacy systems, but coding them from scratch is slow and risky. OutSystems lets teams build and orchestrate agents visually on low code, grounded in your enterprise context and connected through prebuilt integrations.
You cannot put an agent in front of users without proving it works. OutSystems Evaluations tests your agent logic against a golden dataset with an automatic judge, so you see whether a prompt or tool change improved or broke behavior before deploying.
Sources & related URLs
Related / legacy domains
Research sources
Agentic Index coverage score
12.5 / 14 capabilities · 89%
| Integrations & Tool Calling | Full |
|---|---|
|
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 |
|
| Workflow Orchestration | Full |
|
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 |
|
| Knowledge Grounding & RAG | Full |
|
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 |
|
| Human Oversight & Guardrails | Full |
|
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 |
|
| Security, Identity & Governance | Full |
|
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 |
|
| Observability & Auditability | Full |
|
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 |
|
| Memory & State Persistence | Partial |
|
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 |
|
| Deployment & Data Residency | Full |
|
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 |
|
| Prebuilt Agents, Templates & Packs | Full |
|
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 |
|
| Triggers & Channel Coverage | Full |
|
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 |
|
| Model Flexibility & Routing | Full |
|
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 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
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 |
|
| Testing, Debugging & Optimization | Full |
|
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 |
|
| Browser & Computer Use | Not documented |
|
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 |
|
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
OutSystems MCP, a remote MCP server for OutSystems Developer Cloud, is now generally available on every ODC tenant. Coding agents such as Claude Code, Codex, Cursor and AWS Kiro can use it to hand build work to Mentor, query the tenant's apps, data models and dependencies, publish and promote between stages, roll back, and read logs and traces.
Bears on: MCP / tool calling / API
View sourcePricing
Free tier to start building. Production enterprise pricing is quoted, scaled to applications, agents, users and environments.
Enterprise engagements are quoted and scaled to applications, agents, users and environments.
What is public
A free tier to start building is public, but production enterprise pricing is quoted through direct engagement rather than listed.
Billing mechanics
Customers start on a free tier and move to an enterprise engagement scaled to applications, agents, users and environments. AI model usage adds inference cost, and production rates are not published.
Cost watchouts
Enterprise pricing scales with applications, agents, users, and environments, and AI model usage adds inference cost, so production deployments grow well beyond the free tier.
Variable cost rationale
Enterprise pricing scales with applications, agents, users and environments, and agents add AI model inference cost, so the bill grows with the size of the agentic footprint. No rate, cap or included quota is published, so nothing public limits that growth. The free tier costs nothing but is meant for building, not production.
Additional watchouts
How the platform prices applications, agents, users and environments is not published, and AI model inference adds cost on top. The free tier does not reflect production scale.
Sales call required
Mixed (some tiers require a call)
Free / trial
Free tier to start building agents
Lowest paid plan
Not published
Key ambiguities
A free tier is public, but production enterprise pricing is not listed and depends on applications, agents, users, environments, and AI usage.
Related vendors
- Lindy — Lindy is an AI teammate that lives in Slack, answers from your tools…
- Activepieces — Open source, MIT licensed automation platform where every one of 700…
- Agenta — Agenta is an open source workspace where teams build AI agents by…
- AgentX — No code platform to build, evaluate, and deploy multi agent…
- AI Library — No code platform for building and running AI agents, with a…
- Aigensei — Enterprise agentic workflow platform that runs business processes…
Alternatives to OutSystems
The closest documented capability profiles to OutSystems among agent builders tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Mendix12.5 / 14Matches OutSystems across all 14 documented capabilities
- AgentX12.0 / 14A lighter documented profile than OutSystems
- Airia12.0 / 14A lighter documented profile than OutSystems
- Dify12.0 / 14A lighter documented profile than OutSystems
- LuMay12.0 / 14A lighter documented profile than OutSystems
- Moveo.AI12.0 / 14A lighter documented profile than OutSystems
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded