Cognigy
Also known as: NiCE Cognigy, Cognigy.AI, Cognigy AI
Enterprise conversational and agentic AI platform now owned by NiCE, building voice and chat agents in more than 100 languages, with your own LLM, NLU, STT and TTS, on premises Kubernetes deployment, assertion based Playbook testing, and certifications including ISO 27001, ISO 42001, SOC 2 Type II and PCI DSS 4.0.
Cognigy is an enterprise conversational and agentic AI platform founded in 2016 in Dusseldorf by cofounder and CEO Philipp Heltewig. After a $100 million Series C it was acquired by NiCE for $955 million under an agreement announced in July 2025. It now trades as NiCE Cognigy, and its agentic layer serves as the reasoning core of NiCE's CXone Mpower platform. More than 1,250 brands use it, including Toyota, Mercedes-Benz, Lufthansa, Nestle and ERGO Insurance.
Cognigy.AI is a low code platform for building voice, chat and digital agents in more than a hundred languages, covering intelligent IVR, self service, agent assist and autonomous agentic execution. Agents are built as Flows of Nodes in one visual builder for chat and voice, and builders drop to CognigyScript, Code Nodes and Transformers where the builder stops. Agents can also reach out first, acting on signals such as CRM updates and billing events. Lufthansa runs sixteen AI agents on Cognigy, handling sixteen million conversations a year with peaks around 375,000 interactions a day.
The platform is technology agnostic. Customers bring their own account and choose their own language model, natural language understanding engine, speech to text and text to speech, and Cognigy maintains the supported provider set as a shipped feature. It runs on premises on Kubernetes as well as on shared and dedicated SaaS, with operator settings that reach Helm values, ingress controllers and SBC certificates.
For testing, Simulator runs thousands of synthetic customer conversations against set success criteria, on demand or on a schedule, and Playbooks hold up to fifty steps with assertions checked against defined values. Snapshots package a complete agent, including flows, logic, configuration, NLU models and extensions, for promotion between development, QA and production endpoints.
Knowledge AI provides retrieval over uploaded PDFs, Cognigy Text and web pages, or over external systems reached through Knowledge Connectors. It is licensed and metered in Knowledge Chunks and backed by a Weaviate vector store. Agent Copilot supports human agents in the contact center with next action and knowledge widgets that carry source links, and Handover Providers move conversations to people with context intact.
On security, Cognigy holds ISO 27001, ISO 27701 and ISO 42001, SOC 2 Type II and PCI DSS 4.0, along with TISAX and BSI C5 attestations. Access runs on role based access control, with end to end encryption and audit logs capturing every configuration change and user action.
Enterprises buy through direct sales at quoted prices. Teams can hire ready agents from Cognigy's Job Market and give them preconfigured Jobs, or build their own flows from Nodes. The on premises route asks for an operator able to run the underlying Kubernetes cluster.
Vendor details
Canonical URL
https://www.cognigy.com
Category
Customer support agent
Company status
acquired
Use cases & customers
Target customers
Deployment options
Integrations
Cognigy is technology agnostic and integrates with any CCaaS, CRM or business system, including Genesys, Avaya, NiCE CXone, Amazon Connect, SAP and Salesforce. Handover Providers are configured per contact center platform, including a NiCE CXone provider that hands over without a platform level integration, and Agent Copilot is embeddable directly in the Salesforce Agent Console. Beyond connectors, Connections hold credentials, Extensions package custom Nodes, and Code Nodes with the Node Execution API reach legacy systems and internal tools that have no connector. Developers reach the platform itself through the Cognigy.AI API, the Playbooks API with an OpenAPI specification, the Knowledge Connector API and the Node Execution API.
In practice
Your data cannot leave your own infrastructure. Cognigy supports on premises deployment for strict data residency, provided you have a team able to operate the underlying Kubernetes cluster.
You refuse to be locked to one model vendor. The platform is technology agnostic and lets you mix and match your own LLM, NLU, speech to text and text to speech providers, and swap them later.
You are running sixteen million conversations a year across voice and chat in dozens of languages. Lufthansa runs sixteen AI agents on Cognigy at that volume, with peaks around 375,000 interactions in a single day.
Sources & related URLs
Agentic Index coverage score
12.0 / 14 capabilities · 86%
| Integrations & Tool Calling | Full |
|---|---|
|
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. Agents also reach outside tools through the Model Context Protocol, and more than 100 prebuilt tools connect CRM, ticketing, payment and other systems. Sourcedocs.cognigy.com Handover Providers and release notes 2026.9, cognigy.com AI Ops and orchestration page 2026-09-06, cognigy.com Cognigy.AI platform page and AI Agent Studioread 2026-10-13 |
|
| Workflow Orchestration | Full |
|
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 |
|
| Knowledge Grounding & RAG | Full |
|
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 |
|
| Human Oversight & Guardrails | Partial |
|
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. Agent output goes out without a review step. 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 |
|
| Security, Identity & Governance | Full |
|
Cognigy holds ISO 27001, ISO 27701 and ISO 42001, the last of which certifies an AI management system specifically. It 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 |
|
| Observability & Auditability | Full |
|
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 |
|
| Memory & State Persistence | Partial |
|
Agents carry short and long term memory. They remember customer preferences, past interactions and what is said in the live conversation, agents working together share contextual memory, and a builder adds contextual memory to an agent persona in a few clicks. Context also carries across channels, so a handover keeps history intact, and the Interaction Panel shows a developer what sits in the agent's memory during a session. How long that memory lasts, and how an operator views or clears it for one customer, is not public. Sourcedocs.cognigy.com Interaction Panel and Developer Reference 2026-09-06, cognigy.com Cognigy.AI platform pageread 2026-10-13 |
|
| Deployment & Data Residency | Full |
|
Cognigy runs as a self hosted product as well as a service. On premises installations get a YAML based data redaction configuration, introduced in the 2026.9 release to replace environment variables, with rollout percentage control and per organization exclusions in values.yaml. Operators also set an ingress controller feature flag for Traefik middleware resources, certificate secret names in the SBC SIP DaemonSet and StatefulSet, the upgrade of the Weaviate store behind Knowledge AI and a concurrency limit for Playbook execution. 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 in its own hands. 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 |
|
| Prebuilt Agents, Templates & Packs | Full |
|
Teams can hire ready to deploy agents from Cognigy's Job Market, or give an existing agent a preconfigured Job. A Job is a role, such as billing inquiries or flight rebooking, with the tools the agent may use to carry it out. More than 100 prebuilt tools cover business integrations and multimodal xApps, and the Marketplace offers ready to use channel connectors, integrations and xApps, free to download. Builders also get reusable parts. The Node library covers conversation, logic, LLM prompting, entity extraction and handover, Extensions package custom Nodes, Packages move resources such as Knowledge AI resources and Playbooks between installations, and Snapshots capture a complete agent as a portable archive. Sourcecognigy.com Cognigy.AI platform page and Marketplace 2026-10-13, docs.cognigy.com Extensions, Packages, Node Reference and Snapshotsread 2026-09-06 |
|
| Triggers & Channel Coverage | Full |
|
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 open to the operator. 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. Agents can also open the conversation. AI Agents for Proactive Engagement watch live signals such as network alerts, CRM updates and billing events, plan when and on which channel to reach a customer, and make contact by SMS, voice, email or in app, adapting the plan when the customer does not reply. Sourcedocs.cognigy.com Endpoints, Voice Gateway and release notes, cognigy.com platform page 2026-09-06, cognigy.com AI Agents for Proactive Engagementread 2026-10-13 |
|
| Model Flexibility & Routing | Full |
|
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. A builder can set which model runs each Agent Job, drawing on OpenAI, Anthropic, Google and AWS among others. 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 overview 2026-09-06, cognigy.com Cognigy.AI platform pageread 2026-10-13 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
Developers get the Cognigy.AI REST API, which reaches every feature of the platform, and a full developer CLI that fits into CI/CD pipelines and source control. The Playbooks API has its own OpenAPI specification for creating and scheduling test runs remotely, beside the Node Execution API and the Knowledge Connector API. 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, with an IDE built into the Flow Editor. 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. There is no MCP server for the platform itself. Sourcedocs.cognigy.com Developer Reference, Playbooks, Knowledge Connector API and Node Execution API 2026-09-06, cognigy.com AI Agent Studioread 2026-10-13 |
|
| Testing, Debugging & Optimization | Full |
|
Simulator runs thousands of synthetic customer conversations against an agent before and after launch. Each scenario pairs a persona, a mission and success criteria, scenarios can be generated from existing agents and real transcripts, and runs start on demand, on a schedule or inside automated regression testing. It mocks third party API responses across success, degradation and error states, scores each run against configurable criteria, and tracks success rate over time to catch regressions. Playbooks add scripted tests of up to 50 Steps, each sending input to the agent and checking the response and the Flow with Assertions that can also be inverted, run as background Tasks or through the Playbooks API, with up to ten at once and the limit configurable on premises through MAX_CONCURRENT_PLAYBOOK_EXECUTIONS in values.yaml. 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 guidance 2026-09-06, cognigy.com AI Agent Evaluationread 2026-10-13 |
|
| Browser & Computer Use | Not documented |
|
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 |
|
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
Release 2026.21.0 of Cognigy removes the Trusted Extensions feature and the legacy Extension runtime. All Extensions now run in the new Extension runtime, which was called Cognigy Serverless during its rollout in Q2 and Q3 of 2026.
Bears on: Integrations
View sourceCognigy 2026.20 added an experimental A2A Server Endpoint that exposes a Cognigy.AI flow to outside agents over the Agent2Agent protocol, with an agent card, skills, streaming, multi turn conversations and long running tasks. A new A2A Agent Node works the other way, letting a Cognigy AI agent call a remote A2A agent as a tool.
Bears on: Workflow orchestration
View sourcePricing
No price is public. Cognigy is enterprise only and quote based.
A platform license plus usage, with telephony for voice and implementation services billed alongside.
What is public
No prices are public, while capability, scale and compliance detail runs deep.
Billing mechanics
Quote based enterprise licensing combining platform license with usage, telephony costs for voice, and implementation services. No public rate card exists and pricing is negotiated per deployment.
Cost watchouts
Telephony and implementation services sit outside the license, and the blank canvas design means substantial internal or partner engineering effort to design, build, test and maintain agents.
Variable cost rationale
Usage is metered by conversation or session on top of the platform license, and voice adds telephony, so spend grows with interaction volume and voice minutes carry their own cost. Implementation services are a separate line. No rate card, cap or usage unit definition is public. Pricing is negotiated per deployment, so any limit on the bill sits in the contract.
Additional watchouts
The platform is a toolset, not a packaged solution, so a team builds, integrates and tests its own agents, and the implementation effort is real. Licensing, usage, telephony and services are separate costs that add up together. On premises control carries a Kubernetes operations burden.
Sales call required
Yes, required for paid access
Free / trial
None public, and evaluation runs through enterprise sales
Lowest paid plan
Not published
Commercial notes
NiCE bought Cognigy for $955 million and positions its agentic layer as the reasoning core of CXone Mpower. NiCE's AI ARR grew 66 percent year over year in the first quarter of 2026.
Key ambiguities
There is no public rate card, and how NiCE will package Cognigy within CXone Mpower is not yet clear.
Missing data
Any rate, the license structure, usage unit definitions, telephony rates and packaging under CXone Mpower since the acquisition.
Related vendors
- Decagon — AI agent platform purpose-built for customer support, with deep…
- 5.Y — 5
- Ada — Agentic customer experience platform whose AI agents autonomously…
- Aisera — Enterprise agentic AI platform that orchestrates specialized agents…
- ASAPP — Generative AI for enterprise contact centers that plugs into…
- Assembled — AI customer support orchestration platform that unifies autonomous…
Alternatives to Cognigy
The closest documented capability profiles to Cognigy among customer support agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Crisp11.5 / 14A lighter documented profile than Cognigy
- ElevenAgents12.5 / 14Fuller documented coverage on Human Oversight & Guardrails
- Khoros12.5 / 14Fuller documented coverage on Human Oversight & Guardrails
- Verint11.5 / 14A lighter documented profile than Cognigy
- WotNot11.5 / 14A lighter documented profile than Cognigy
- Ada11.0 / 14A lighter documented profile than Cognigy
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded