Newgen

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

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

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

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

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

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

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

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

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 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

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

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

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

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