Cognigy vs Infobip (2026)

Cognigy is technology agnostic by design and integrates with any CCaaS, CRM or business system, including Genesys, Avaya, NiCE CXone, Amazon Connect, SAP and Salesforce, taking authenticated action across the contact center estate.

Handover Providers are configured per platform, with a NiCE CXone non integrated provider added in the 2026.9 release for handover without a platform level integration, a Salesforce MIAW provider maintained, and Agent Copilot embeddable directly in the Salesforce Agent Console. Beyond handover, Connections hold credentials, Extensions package custom Nodes, and Code Nodes and the Node Execution API reach complex legacy systems and internal tools that have no connector. The actions are transactional, and rebooking, cancellation, order status, invoice requests, payment and refunds are outcomes the agents execute.

Sourcedocs.cognigy.com Handover Providers and release notes 2026.9, cognigy.com AI Ops and orchestration pageread 2026-09-06

In the Tools section a customer adds three kinds of tool to each agent, a Component, an MCP server or an Exchange application, which let the agent call APIs, execute backend logic, retrieve external data and trigger automated workflows. Components encapsulate reusable logic and can orchestrate multiple API calls or backend processes for complex integrations.

MCP servers are configured with a name, endpoint URL, HTTP headers for authentication tokens, and an Allowed functions field naming which actions the server may take when called, so each connection is authenticated and scoped. Exchange applications are selected from a published integrations catalog. Underneath sits the messaging estate the agent acts through, more than fifteen natively integrated channels each with its own API, plus the modular CPaaS X stack.

Sourceinfobip.com/docs/ai-agents/ai-agents/configure-ai-agentread 2026-09-05

Agents are built as Flows of Nodes in a unified visual builder covering chat and voice together. Say and Question Nodes handle turns, LLM Prompt and LLM Entity Extract make model calls, Go To jumps within a Flow, Code Nodes and Transformers carry logic the builder does not express, Search Extract Output handles retrieval, and Handover to Human Agent is a terminal path.

Agentic AI reasons across channels and orchestrates actions to move from conversation to resolution, executing transactions such as rebooking, cancellation, order status, invoice requests, payment and refunds. Flows compose into Snapshots that carry all resources, logic, content, configuration, NLU models and Extensions as one deployable unit, so each orchestration ships as a release artifact.

Sourcedocs.cognigy.com Node Reference and Snapshots, cognigy.com AI Ops and orchestration pageread 2026-09-06

An AI agent can be set up as an orchestrator that coordinates other agents. The customer adds subagents from a list, and the orchestrator delegates tasks to specialized agents, combines their responses and controls conversation routing, with the agents table showing how many subagents each orchestrator has connected. Each agent's Description field is what other agents read to decide when to call it.

Beneath that, Automation Studio builds journey flows and chatbots that route on rules, triggers and Customer Profiles data, and the Agent connector element drops an AI agent into a chatbot so deterministic flows and autonomous agents combine in one path. Agents themselves execute multi-step tasks, calling tools in sequence to reach a goal.

Sourceinfobip.com/docs/ai-agents/ai-agents/configure-ai-agentread 2026-09-05

Voice, chat and digital channels are served with intelligent IVR and self service in more than a hundred languages, delivered through Endpoints that separate the agent from the channel. Webchat v3 is the web surface, and the in house Voice Gateway has its own self service portal and SIP infrastructure, with SBC configuration and TLS handling exposed in the release notes.

Endpoints are kept out of Snapshots so channel configuration and agent logic version independently. In production the platform handles tens of thousands of concurrent sessions and peaks around 375,000 interactions a day, across several independent inbound queues including telephony. Work arrives by channel, and Cognigy describes no scheduled or event driven triggers.

Sourcedocs.cognigy.com Endpoints, Voice Gateway and release notes, cognigy.com platform pageread 2026-09-06

Agents work across WhatsApp, SMS, RCS, MMS, email, voice, live chat, video, in-app messaging, mobile push, Viber, Messenger, Instagram, Telegram, Apple Messages for Business, Kakao, Line and Zalo, each with its own API page, all flowing through the same system.

Work starts in three ways, inbound when a customer reaches out on any supported channel, event-driven when Automation Studio journey flows are triggered by customer behavior or profile changes, and scheduled when journeys start on dates.

Voice is built in, with a Transfer call to AI agent element placing an agent inside an IVR flow, and Broadcast handles outbound at volume.

Sourceinfobip.com/docs/automation-studioread 2026-09-05

Knowledge AI is a retrieval product with its own license, quota model and vector store. Customers upload knowledge as PDF, Cognigy Text or web pages, or connect external systems through Knowledge Connectors, to create Knowledge Sources, and agents use RAG over those documents to give accurate, context aware responses.

Retrieval is wired into the Flow through the Search Extract Output Node for agents and the Copilot Knowledge Tile for human agents, which returns source links naming the files an answer came from.

The corpus is licensed in Knowledge Chunk quotas allocated across organizations through the Management UI or the Cognigy.AI API, and on premises installations use Weaviate as the vector database, with operators told to upgrade it to v1.22.5.

Sourcedocs.cognigy.com Knowledge AI overview and activation, release notes 4.68read 2026-09-06

Knowledge agents are specialized agents for retrieving information from documents, URLs and files, built for FAQ-style interactions, and they sit alongside a Knowledge Base shared component available across AgentOS. Quality center has a dedicated Knowledge agents section that validates responses against expected answers and tracks quality over time, against a persistent body of content the customer curates. General-purpose AI agents reach the same material through tools and components. The Customer Profiles data platform is a separate database of customer profiles and events.

Sourceinfobip.com/docs/ai-agents/knowledge-agents/overviewread 2026-09-05

Conversation context carries across channels, so a handover keeps history intact, and the Interaction Panel lets a developer inspect what sits in the agent's memory during a session. Cognigy does not say what an agent keeps about a contact between separate conversations, whether state is scoped per user, per session or per organization, how long it lasts, or how an operator inspects or deletes it for one person. Knowledge Sources hold knowledge, not memory. The developer reference is large, and a state model behind the memory inspection may be described there.

Sourcedocs.cognigy.com Interaction Panel and Developer Referenceread 2026-09-06

Customer Profiles is AgentOS's customer data platform, holding person and company profiles, attributes, segments and behavioral events, with interaction history available to AI agents so they can personalize responses and make context-aware decisions across sessions.

Agents also carry session state within a conversation, and past sessions can be viewed through Session history.

Customer Profiles is a store the customer loads and queries, not state the agent forms and retains, and Infobip has no agent memory product, no scope, lifetime or deletion control for retained agent state, and no memory entry in the AgentOS product set.

Sourceinfobip.com/docs/customer-profilesread 2026-09-05

Handover Providers are configured per contact center platform, a dedicated Handover Flow controls the interaction with the human agent and the transfer, and a Handover to Human Agent Node sits in the Flow. Agent Copilot workspaces then suggest next actions and surface knowledge with source links to the person now holding the conversation.

Escalation is a designed path that keeps context intact, and role based access control enforcing separation of duties limits who can change agent behavior. There is no review and approve step over agent output, such as a pre send queue, draft review mode, confidence threshold or per action sign off. The agent answers and acts on its own until a Handover Node or a configured condition moves the conversation to a person.

Sourcedocs.cognigy.com Agent Copilot getting started, Handover Providers and Handover Featuresread 2026-09-06

Guardrails are a field in the agent's Advanced settings with their own configuration page, where the customer selects content filters that detect and block harmful content in agent conversations, controlling what the agent can and cannot discuss. Release control sits with the customer too, since a configured agent stays a draft until a named version is created and explicitly activated for production, with earlier versions available to roll back to.

Each MCP server carries an Allowed functions list naming what it may do when called. When automation reaches its limit the conversation transfers to Inbox with the complete history, so the customer does not have to start over with the human agent, who works with an Inbox copilot. Infobip does not describe an approval step before an individual agent action goes out.

Sourceinfobip.com/docs/ai-agents/ai-agents/configure-guardrailsread 2026-09-05

Cognigy's public trust center lists ISO 27001, ISO 27701 and ISO 42001, the last of which certifies an AI management system specifically. Cognigy also holds SOC 2 Type II and PCI DSS 4.0, the latter with independent QSA attestation, along with the TISAX and BSI C5 attestations, GDPR and HIPAA alignment, and work under way mapping SOC 2 controls to HITRUST CSF.

Access is governed by granular role based access control enforcing separation of duties, with the Management UI distinguishing admin rights for organization level tasks such as allocating Knowledge Chunk quotas, alongside end to end encryption in transit and at rest and detailed audit logs.

Sourcetrust.cognigy.com, docs.cognigy.com Administration and Knowledge AI activationread 2026-09-06

Infobip is audited regularly against ISO/IEC 27001, 27017, 27018 and 22301 and the ISAE 3000 standard, assessed annually, with certificates available for download at infobip.com/certificates and a full or summary copy of current reports provided on written request. It also holds a HIPAA attestation under SSAE 18, and its sub-processor list, data transfer agreement, data retention notice and privacy notice are all public at named URLs.

Single sign on works through any SAML 2.0 identity provider with SP-initiated flow, with identity-provider groups mapped to custom roles and re-synchronized on every login, and role-based access control with predefined and custom roles governs per-feature permissions. Admins can set two-factor authentication to be remembered or required at each login, and password validity and maximum login attempt policies, IP safelisting and separate API access permissions complete the controls. Infobip's identity, authentication and fraud prevention products are things it sells to its customers, not controls over the customer's own tenant.

Sourceinfobip.com/docs/essentials/manage-my-account/account-settingsread 2026-09-05

Detailed audit logs capture every configuration change and user action, recording who altered the agent and when, and cover platform administration as well as conversations. The Interaction Panel executes a Flow node by node in Debug Mode against a chosen Flow, Locale and Snapshot, shows the agent's memory during a session, and can follow a live session by user identifier, so a specific run can be reconstructed step by step. Insights transcripts, from which a Playbook can be generated, and analytics and reporting across the conversational estate sit alongside.

Sourcedocs.cognigy.com Interaction Panel and Insights, cognigy.com AI Ops and orchestration pageread 2026-09-06

Insights and Analytics, one of the five AgentOS products, monitors AI agent performance, tool usage and session tracking through dedicated dashboards, with every interaction across all five products feeding it and the output covering performance metrics, root causes and AI-driven recommendations. Tool usage and session tracking record what an individual agent did, not only an aggregate.

From inside an agent, Go to Session history opens previous sessions with their analytics, and View as code renders the running configuration. Changes are tracked separately, since agents autosave up to ten draft versions, named versions are created and activated deliberately, and version history records what was live when. Infobip does not describe an immutable audit log with actor and timestamp for configuration changes.

Sourceinfobip.com/docs/insights-and-analyticsread 2026-09-05

Cognigy runs as a self hosted product as well as a service.

Release notes for on premises installations cover a YAML based data redaction configuration introduced in the 2026.9 release to replace environment variables, with rollout percentage control and per organization exclusions via values.yaml, an ingress controller feature flag governing Traefik middleware resources, parameterized certificate secret names in the sbc-sip DaemonSet and StatefulSet, a Weaviate version upgrade instruction for on premises installations running Knowledge AI, and a concurrency limit for Playbook execution set through values.yaml.

Licensing distinguishes shared SaaS, dedicated SaaS and on premises routes, with Knowledge AI quotas administered differently for each, so a customer can run Cognigy inside its own infrastructure with Kubernetes level configuration exposed to the operator. The on premises route needs an operator able to run the underlying Kubernetes cluster.

Sourcedocs.cognigy.com release notes 2026.9, 4.68 and 4.72, Knowledge AI activationread 2026-09-06

AI agents are available only in five data centers, Europe (EU1), Sweden (SE1), Germany (FR4), India (MUNM) and United States (NY2), so an account sits in a named region across three continents and the customer can tell which.

Infobip publishes its full legal tier openly, a sub-processor list, a data transfer agreement, a data retention notice and a privacy notice, each at its own public URL, plus an infrastructure overview and network connectivity options.

Infobip offers no self service or other way for the customer to choose or move their region, placement appears to be set at account provisioning, and there is no on premise, private cloud or single tenant deployment.

Sourceinfobip.com/docs/ai-agents/ai-agents/overviewread 2026-09-05

Customers get reusable parts to assemble into their own agents.

The Node library covers conversation, logic, LLM prompting, entity extraction and handover, Extensions package custom Nodes, Packages export and import resources, including Knowledge AI resources and Playbooks, between installations, Snapshots capture a complete agent as a portable archive, and prebuilt handover providers and connectors cover the contact center estate.

These move work between projects and environments. There is no template gallery, agent library, industry starter pack or marketplace of prebuilt agents, so the route to a live agent is building a Flow from Nodes, configuring Endpoints and handover, and testing it with Playbooks.

Sourcedocs.cognigy.com Extensions, Packages, Node Reference and Snapshotsread 2026-09-06

Agent instructions can be filled from predefined templates, Appointment booking agent, Order status assistant and Sales representative, and Automation Studio has its own predefined and custom templates to speed up journey and chatbot creation.

Agents move as units, since an existing agent can be duplicated, exported to a .export file and imported into another workspace. Components are reusable logic blocks selected from a list and shared across agents. AgentOS itself ships as five named products a customer switches on. The template set is small, and there is no browsable marketplace of ready made agents.

Sourceinfobip.com/docs/ai-agents/ai-agents/configure-ai-agentread 2026-09-05

The customer sets up an account with one of the supported LLM providers, configures the provider in Settings and selects the model from the supported list, and individual Nodes state which model capabilities they need. The provider set is maintained as a shipped feature, and the 2026.9 release added Google GenAI as a provider with the Gemini 3 family, including gemini-3.1-pro-preview, gemini-3-flash-preview and gemini-3.1-flash-lite-preview.

Customers are subject to the terms of the generative AI providers they use, and Cognigy disclaims responsibility for those services, since the customer holds the provider relationship. The same choice extends beyond the language model to natural language understanding, speech to text and text to speech, so the customer assembles the stack, brings the account, selects the model and can swap it later.

Sourcedocs.cognigy.com Generative AI and LLMs section, 2026.9 release notes, Knowledge AI overviewread 2026-09-06

Under Advanced settings when configuring an AI agent, the Model field lets the customer select the LLM that best matches its requirements for reasoning capability, latency and cost, so each agent can run on a different model. It sits alongside Guardrails and structured output in the same settings panel, and the Instructions field acts as the system prompt for the underlying language model. Third party agents reaching Infobip through MCP are a matter of interoperability, not model choice.

Sourceinfobip.com/docs/ai-agents/ai-agents/configure-ai-agentread 2026-09-05

The Developer Reference covers the Cognigy.AI API, the Playbooks API with its own OpenAPI specification for creating and scheduling test runs remotely, the Node Execution API function reference and the Knowledge Connector API function reference.

Extensions build custom Nodes, Packages move resources between installations, and Code Nodes, Transformers and CognigyScript let builders drop to code where the low code builder stops. Administration APIs reach the Management UI, and Knowledge Chunk quotas can be set through the API as well as the interface.

An outside caller can drive Cognigy to run a test, execute a node, feed a knowledge connector or administer an organization. Cognigy describes no MCP server for the platform.

Sourcedocs.cognigy.com Developer Reference, Playbooks, Knowledge Connector API and Node Execution APIread 2026-09-06

Infobip publishes an API reference, SDKs, release notes, an integrations catalog and a public roadmap, all reachable without a login, plus Postman collections, a GitHub organization and a developer Discord. Every channel is exposed as its own REST API, and the modular CPaaS X stack is sold specifically for platforms building on top.

On the agent side, MCP servers let an Infobip agent call outside systems with scoped allowed functions, and an agent's configuration can be viewed as code, exported to a portable file and imported elsewhere, with structured output constrained by a customer-defined JSON schema. Components let a developer encapsulate backend logic the agent then calls, and Exchange applications add partner integrations.

Sourceinfobip.com/docs/apiread 2026-09-05

Playbooks are Cognigy's test tool. A Playbook holds up to 50 Steps, each carrying input text and data sent to the agent and Assertions that check the response and aspects of the Flow against a defined value, and assertions can be inverted to check that a value is absent. Runs execute as background Tasks with results in a Runs tab filterable by status and creator.

Up to ten Playbooks run at once, with the limit configurable on premises through MAX_CONCURRENT_PLAYBOOK_EXECUTIONS in values.yaml, and a Playbooks API allows remote creation and scheduled runs against the OpenAPI specification. Playbooks can be generated from a live conversation or an Insights transcript and exported as a Package, and Cognigy calls them automated QA testing for regression.

The Interaction Panel adds manual runs against a chosen Flow, Locale and Snapshot with node by node debugging, and Snapshots package a complete agent for promotion between development, QA and production endpoints.

Sourcedocs.cognigy.com Test section, Playbooks and Interaction Panel, Cognigy support center Playbooks guidanceread 2026-09-06

AgentOS ships Quality center, a set of tools to monitor, evaluate and improve agent response quality, where the customer creates test groups, defines test cases, runs tests and reviews results to confirm agents behave as expected.

For Knowledge agents it validates responses against expected answers and tracks quality over time, producing a scored comparison. Separately, the build flow has a step before publishing, Test an AI agent, that validates agent responses and behavior, and agent versioning lets a team activate a specific version and roll back a bad one. The tests run against the customer's own agent.

Sourceinfobip.com/docs/ai-agents/quality-center/overviewread 2026-09-05

Agents reach outside systems through Handover Providers, Connections, Extensions, Code Nodes and the Node Execution API, all credentialed programmatic paths, and act on backend systems through APIs and connectors. Cognigy's own surfaces are Endpoints, a Webchat widget, a Voice Gateway and the Agent Copilot workspace embedded in a contact center console, which are channels the agent speaks through or Cognigy's own interfaces. The agents do not control a browser, desktop or remote computer.

Sourcecognigy.com AI Ops and orchestration page, docs.cognigy.com Node Reference and Extensionsread 2026-09-06

An Infobip agent reaches other systems through three tool types, all programmatic, Components running backend logic, MCP servers called at an endpoint URL with scoped allowed functions, and Exchange applications from the integrations catalog, and its output side is the messaging estate of more than fifteen channels, each with its own API. AgentOS offers no browser control, hosted session, virtual desktop or interface automation, and nothing in the agent configuration offers a browser, a screen or a pointer.

Sourceinfobip.com/docs/ai-agents/ai-agents/configure-ai-agentread 2026-09-05