Bizagi vs Newgen (2026)

Agents act through AI Actions. A builder links connectors already set up in the project, SAP BTP connectors or MCP servers reached over server sent events, picks which of their actions the agent may use and writes the goal into the prompt, and the agent decides when to call each one, with up to 100 actions in total. MCP servers authenticate with an API key sent as Basic, Bearer or a custom header. Agents can gather more data, act in outside systems and start processes in Bizagi or third party systems this way.

Sourcehelp.bizagi.com/platform/en/ai_actions.htmread 2026-10-13

Marvin works inside business systems and performs tasks there, not only answers, and agents in Agentic Workspaces trigger actions when they spot a business event. Around them, prebuilt connectors reach SAP, Salesforce, Microsoft 365, Temenos, Mambu, TCS BaNCS, Guidewire, Duck Creek, InsureMO and EHR systems, certified connectors sit on partner marketplaces, and a data connector layer pulls in data lakes, warehouses and marts. LumYn connects to CRM, core banking and data lakes for its analysis.

Sourcenewgensoft.com/platform/integration-ecosystemread 2026-10-13

Agents run inside BPMN processes built in Bizagi Studio, as an action on an AI task that fires when a case enters or leaves it, from a button on a form, from entity forms or inside data pipelines, and Master and Persona entities can now run an agent as an Entity Action with its own input and output mappings. Several agents can run in one process, side by side or one after another, and their outputs map to typed fields in the data model, so later steps, business rules and people use them like any other case data.

Sourcehelp.bizagi.com/platform/en/ai_agents.htmread 2026-10-13

The agent framework's reasoning hub, built on LangGraph, breaks a complex task into logical steps and coordinates several specialist agents to reach the goal, and agents can work alone or together. NewgenONE Process Orchestration coordinates agents, people and enterprise systems across end to end workflows in a single engine, tracks SLAs and resolves exceptions as they happen. Agentic Workspaces run multi agent workflows beside the people who own each decision, and agents adjust tasks, priorities and decision paths as conditions change.

Sourcenewgensoft.com/platform/agentic-ai/agentic-workspacesread 2026-10-13

An agent on an AI task runs whenever a case reaches that task, with no one asking. Cases themselves start from a timer start event on a schedule, from a message or signal thrown by another process, from events Bizagi consumes off Kafka topics, or from a person in the work portal, and AI Jobs in the Management Console schedule and monitor AI work on their own. Agents can in turn trigger events that start processes in Bizagi or in other systems, and processes can publish events back to Kafka.

Sourcehelp.bizagi.com/platform/en/start_events.htmread 2026-10-13

Agents keep watch on systems, detect business events or anomalies and trigger the right action on their own, without anyone starting them. Marvin classifies and routes incoming email as it arrives, matching it against past ingestion history, so content reaches the right workflow with no manual step. Service request agents also run behind round the clock self service portals and other channels.

Sourcenewgensoft.com/platform/agentic-ai/agentic-workspacesread 2026-10-13

Enterprise Knowledge holds catalogs that are processed, indexed and served through retrieval augmented generation while agents run, kept in a vector database that serves retrieval and never trains a model.

File Knowledge builds a catalog from content extracted from documents and serves AI Agents, AI Workers and the Ask Ada assistant, and Bizagi Data Knowledge builds one from records stored in Bizagi entities for AI Agents. Catalogs sit in categories in Studio's AI Hub and are reindexed after a deployment or update.

Agents can also find conceptually similar past cases without exact keyword matches, and the knowledge can extend or replace an agent's default instructions with a company's guidelines and procedures.

Sourcehelp.bizagi.com/platform/en/enterprise-knowledge.htmread 2026-10-13

Agents ground their work in the company's own content. An advanced retrieval engine built on a vector database and enterprise knowledge graphs finds relevant information across data sources, drawing on documents held in NewgenONE's content repository and data brought in through its connectors. Marvin answers from company documents and searches the whole repository in plain language, filtered by date, type and version, and a knowledge repository approved by subject matter experts feeds service request agents.

Sourcelanding.newgensoft.com/hubfs/_2020%20website%20files/pes%20website/brochure/agentic%20ai.pdfread 2026-10-13

Each agent call works from inputs mapped from the case and the knowledge catalogs attached to it, and writes its outputs back to case fields, so the case carries the state while it runs. Inputs can run to 500,000 characters, so whole documents and long case histories can be passed in on each call. An agent keeps no memory of its own that it reads from one case to the next.

Sourcehelp.bizagi.com/platform/en/ai_agents_faqs.htmread 2026-10-13

Agents work on the case or request in front of them, with its documents and data held by the process and content platform for as long as the case runs. Nothing an agent learns in one case carries into a later, separate case, and there is no setting to view or clear what an agent retains. A semantic enterprise memory built on the content platform is announced as coming and is not yet part of the product.

Sourcenewgensoft.com/platform/agentic-ai/agentic-workspacesread 2026-10-13

AI Workers take on tasks people would normally do in one of three modes. In supervised processing the worker does as much of the task as it can and hands it to a person to review or finish, conditional processing follows rules the customer sets to decide when it works alone, and autonomous processing falls back to a person whenever it cannot finish. Each decision comes with its reasoning for a person to check, and agent outputs land in form fields that people review before a case moves on.

Sourcebizagi.com/en/platform/ai-workersread 2026-10-13

Agentic Workspaces put real time approvals into multi agent workflows, so a person signs off where a decision needs one, and agents act only within the boundaries they are granted. Agentic Shield filters hallucinated, inaccurate or off brand output, scans incoming and outgoing data and redacts personal and confidential information, with guardrails configured per use case. Business rules from NewgenONE BRE bound what each agent decides.

Sourcenewgensoft.com/platform/agentic-ai/agentic-workspacesread 2026-10-13

Bizagi holds ISO/IEC 27001:2022, its cloud for US government is FedRAMP Moderate, and independent reviews found the cloud meets HIPAA and HITECH requirements. Users sign in through SAML, OAuth or LDAP with two factor authentication, role based segregation of duties and delegated administration govern who can do what, and roles can be kept in step with Microsoft Entra ID. Data is encrypted in transit and at rest, each customer's applications and data are isolated, and an annual transparency report covers government requests for customer data.

Sourcebizagi.com/en/platform/complianceread 2026-10-13

Users sign in through single sign on with SAML, OAuth 2.0, OpenID Connect, LDAP or Microsoft Active Directory, with two factor and multi factor options. Role based access gives analysts, developers, data engineers and DevOps managers different rights, object level controls govern each tool, and admins can create custom administrative roles. Newgen's cloud meets SOC 1 and SOC 2 Type 2, PCI DSS Level 1, HIPAA, ISO/IEC 27017 and 27018 and ISAE 3000, and Marvin's actions run under the same role based permissions as the rest of the platform.

Sourcenewgensoft.com/platform/governance-securityread 2026-10-13

Tracing in the Management Console records AI agent invocations, the requests and responses of the connectors an agent calls, tagged with the case number, and the responses AI Workers produce, at error, warning or information level, and AI Workers show the rationale behind each decision.

Traces are kept for 90 days and are meant for troubleshooting, with the platform's audit and accountability controls kept apart from them. An AI consumption report traces usage to processes, tasks, entities and applications and shows the models and tokens behind each execution, and an AI Metrics dashboard tracks agent use over time by process and by agent.

Sourcehelp.bizagi.com/platform/en/tools-tracing.htmread 2026-10-13

Every action an AI agent takes is logged and traceable, and users can follow its decision path and the rationale behind it to check it against policy. Marvin's email ingestion has a dashboard of logs, routing rules and how confident each classification was. Platform audit logs capture object level activity with timestamp, user, module, role and operation.

Sourcenewgensoft.com/platform/agentic-ai/agentic-workspacesread 2026-10-13

Each customer gets a dedicated cloud setup with isolated storage and its own URL, provisioned in the Azure geography it picks at onboarding, US, EU, Asia or US Government, and every service and resource stays inside that geography. Bizagi chooses the exact Azure region within it. Production data is replicated to a paired region and backed up nightly, with a 5 minute recovery point and a 3 hour recovery time.

Sourcehelp.bizagi.com/platform/en/available-regions-for-bizagi-c.htmread 2026-10-13

NewgenONE runs on public cloud on AWS or Azure, in multi tenant or dedicated deployments, and the Enterprise plan adds hybrid and on premises deployment, with private cloud also offered for the agent framework. Marvin runs entirely inside the customer's NewgenONE environment, so content does not leave it and personal data never reaches a public model. Committed uptime is 99.5% on Professional and 99.95% on Enterprise, with service credits when it is missed.

Sourcenewgensoft.com/platform/pricingread 2026-10-13

AI agent templates deploy straight from Bizagi Studio, with 13 for banking and investments, 7 for customer service and 10 for manufacturing and retail, grouped into predefined Solutions a builder can search by Solution, title or description. They cover jobs such as generating and comparing earnings reports, categorizing customer incidents, obfuscating personal data, composing incident responses, writing knowledge base articles, translating policies, comparing vendors and summarizing RFx responses. Bizagi Copilot helps refine a template's prompt in plain language.

Sourcebizagi.com/en/platform/ai-agent-templatesread 2026-10-13

Ready made agents include Marvin for routine tasks and content work, LumYn, which reads more than 250 behavioral signals with over 30 ML models to find revenue opportunities, Harper, which audits sales calls and coaches reps, and NewgenONE AURA AI.

Vertical agents cover credit decisioning, underwriting assistance, early claim probability, policy retention, claim adjudication, early warning signals, loan collections and KYC, with agentic solutions for trade finance documents, regulatory management and service requests.

Agent Studio offers prebuilt templates, and Newgen Market on the developer portal adds application templates and connectors to start from.

Sourcenewgensoft.com/platform/agentic-airead 2026-10-13

Agents run on Azure OpenAI through Bizagi's private GPT service. For each agent a builder picks a model from those OpenAI currently offers, which change with OpenAI's updates and deprecations, choosing between direct response models and reasoning models with a set reasoning level, and tunes temperature, top p, frequency penalty and presence penalty. Files as inputs need GPT 4o or a newer model. Every choice stays within OpenAI's models, with no option to bring another maker's model or a customer's own deployment.

Sourcehelp.bizagi.com/platform/en/ai_agents_from_scratch.htmread 2026-10-13

Agents run on domain specific fine tuned large and small language models with a reasoning engine, and Newgen offers an LLM Mesh to work out which model suits an organization. Marvin draws on large language models from OpenAI, Meta's Llama 3 and Microsoft Azure underneath, but a buyer has no setting to pick a provider or bring a model of its own. Customers can build their own machine learning models in Data Science Studio for risk and decision models.

Sourcenewgensoft.dev/knowledgebase/ai-genai-assisted-developmentread 2026-10-13

The Bizagi API is a RESTful service on OData 4.0 with OAuth 2 bearer tokens, so outside applications can start cases for a process, search cases and work with process data. A JSON file in Swagger 2.0 and OpenAPI 3.0 format describes every OData endpoint for middleware, a full service index lists them, and examples include C# code. Since the Summer 2026 release a REST API also exports and imports deployments, so a team can automate releases from its own pipeline, and API traces can be switched on for debugging.

Sourcehelp.bizagi.com/platform/en/api_odata.htmread 2026-10-13

Newgen's developer portal documents the platform's APIs, which NewgenONE generates automatically for processes, rules, custom business functions, service flows, document processing, AI models, content and templates, published to OpenAPI and Swagger specifications. Developers sign in with a session token and can call over gRPC as well as REST, UI, workflows, rules, bots and reports can be exposed as APIs to other systems, and each plan carries a monthly allowance of API calls, 50,000 on the trial. Data Science Studio deploys models behind APIs.

Sourcenewgensoft.dev/knowledgebase/integration-ecosystem-overviewread 2026-10-13

Builders try an agent in a Test Prompt window, which runs one input file at a time, shows which actions the agent called, and can differ from what happens at run time. AI Workers in supervised mode learn from each user after the 50th interaction on a task, building a personal policy from that user's behavior and feedback, and a team can switch that reinforcement learning on or off per task. Bizagi has retired its Autotesting tool, and there is no saved test set, quality gate or measure of how the learning changes results before an agent goes live.

Sourcereleasenotes.bizagi.com/en/release-notes/releases/fall-2025read 2026-10-13

Data Science Studio monitors model performance and runs a built in champion and challenger comparison, so a new model can be tried against the one in production, and continuous monitoring watches agents in use. Low code DevOps pipelines add automated, AI driven testing, validation and version control before each application release. These checks cover the machine learning models and the application build, and there is no test suite or quality gate that checks an agent's answers before release.

Sourcenewgensoft.com/platform/agentic-airead 2026-10-13

Screen level work runs through RPA bots from partners such as Automation Anywhere, which handle manual tasks while Bizagi manages the flow of data between people and robots. The bots and their runtime come from the RPA vendor, and Bizagi's own agents do not drive a browser or desktop themselves.

Sourcebizagi.com/en/solutions/robotic-process-automation/automation-anywhere-and-bizagiread 2026-10-13

NewgenONE RPA bots take over repetitive, rule based tasks, either alone at the task level or embedded in larger processes beside agents and people, with exceptions routed to a person. A bot studio records, debugs and runs automation scripts across web and Windows applications, with browser automation for web screens and desktop automation that reaches AS400 terminals, and the process designer brings bots and people into one flow.

Sourcenewgensoft.com/platform/process-automation/robotic-process-automationread 2026-10-13