Blits.ai vs Cognigy (2026)

Agents act in outside systems through three routes. A catalog covers 56 enterprise systems, among them Salesforce, SAP, ServiceNow, Workday, Zendesk, Oracle, Jira, Snowflake and Databricks, and business tools for HubSpot, Freshdesk, Zoho, Notion, Odoo, Dynamics 365 and Microsoft 365 connect through per system OAuth.

Custom functions call REST or SQL sources, or run JavaScript in an isolated sandbox, with versioning and publishing. External MCP servers connect over SSE or HTTP, and their tools appear to the agent. Built in tools add web search, file generation, payment links, lead capture, handover, and call control on voice such as transfer, DTMF and callback scheduling.

Sourceblits.ai/featuresread 2026-10-13

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

A BPMN style canvas lays out each conversation as flows of dialog, action, condition and AI blocks, with subflows, functions and agents referenced from any flow and versions published separately to Test and Live.

The agent block hands a turn to an LLM agent, and the trigger workflow block starts an agentic workflow, an agent loop that calls tools on its own until the task is done. Workflows carry instructions, configuration, a validation check and an on or off switch.

Agentic tasks hold a deferred action of the do X when Y kind, with scheduled rechecks, an expiry and a dry run mode, so a step can wait days for its condition before it runs.

Sourceblits.ai/featuresread 2026-10-13

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

Fourteen channels carry work to an agent, from the web chat widget, WhatsApp, SMS and phone to Microsoft Teams, Slack, Telegram, Facebook Messenger, email, Alexa and Google Assistant, an in app webview, a digital human and a REST or WebSocket API.

Agentic workflows also start on a schedule, or when an outside system calls a per workflow token endpoint, which queues the run with the request body as its input and allows 30 runs a minute per workflow by default.

Agentic tasks recheck a condition on a schedule before acting, outbound campaigns dial a contact list inside a set calling window, and an incoming email webhook turns mail into conversations.

Sourceblits.ai/api-docsread 2026-10-13

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

Retrieval runs over a maintained document library that ingests PDF, Word, PowerPoint, Excel, CSV, JSON, Markdown, images and Outlook messages, crawls websites and their subpages on a recrawl, and keeps version history with revert.

Chunk size and overlap are configurable, storage sits on PostgreSQL pgvector or file based HNSW indexes, and search combines dense vectors with BM25 keyword matching and deduplication. Agents can also query registered PostgreSQL or SQLite databases directly.

Answers cite the document, page and source date, newer content ranks ahead when sources overlap, and retention rules expire outdated material automatically.

Sourceblits.ai/featuresread 2026-10-13

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

A conversation keeps its state across turns and page refreshes, and a client can reconnect to an existing conversation, load or delete one user's history, and push state variables such as a customer name or account number into the session.

Inside a flow, a get history block reads the transcript, and a user data provider turns verified balances, loyalty points and tiers into variables. Data removal and retention controls sit in the GDPR toolkit.

Nothing the agent learns is written to a store of its own for later conversations, so what it knows about a returning customer is the history and the variables the host system supplies.

Sourceblits.ai/api-docsread 2026-10-13

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

Agentic actions above a configurable threshold pause for a person, who approves or rejects them before they run, and a tool execution policy limits which tools an autonomous agent may call at all. Agentic tasks offer a dry run mode, and an anomaly review queue flags unusual conversations for review and can push them into a test suite.

For purchases, authorize then capture holds a payment for later capture, with amount ceilings and velocity limits. Staff can watch live conversations and take over, phone calls included, and blocked topics are enforced deterministically, independent of the model's judgment.

Sourceblits.ai/featuresread 2026-10-13

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

Single sign on works with Microsoft Entra ID and Google accounts, with multi factor authentication on admin login, and role based access control offers more than 60 permissions, custom roles per tenant, roles per bot, and separate publish rights for Test and Production. Tenants are isolated down to every record and query, API keys are hashed and validated server side, and PII and card numbers are masked at the gateway before text reaches a model.

Certifications cover ISO 27001:2022, ISO 42001 and SOC 2 Type II, and the trust center also shows GDPR compliance, with policies and controls available on request. Payments run on an isolated service built to PCI DSS v4.0.1 Level 1, with tokenization at the payment provider and encrypted credentials, while PCI DSS certification itself is still in progress.

Sourceblits.ai/featuresread 2026-10-13

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

Every agent turn can be inspected with token counts and trace detail, including each tool and SQL call with its origin, arguments and latency, and per agent statistics track token use and cost. Agentic workflow runs keep a full audit trail per run with downloadable run data, and the platform records user audit logs and tamper evident event logs. Conversation logs open in a permission gated transcript viewer, live conversations can be watched as they happen, and outbound campaigns log every call attempt.

Sourceblits.ai/featuresread 2026-10-13

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

Three deployment routes are offered, a managed service, the customer's own AWS, Azure or Google Cloud account, and an on premises install in the customer's data center, including air gapped sites.

The managed cloud has regional endpoints in the EU, the US, the UAE, Qatar and Australia, each with the same API, and data sent to a regional endpoint stays in that region.

Deployment is Kubernetes native, a self contained Docker Compose stack covers local installs, Google models can be routed to EU or UAE regions through Vertex AI, and transcription can run on GPU servers that Blits.ai operates itself.

Sourceblits.ai/deployment-optionsread 2026-10-13

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

Create with AI turns a written use case into a working bot with agents, flows, guardrails, knowledge suggestions and a go live checklist, and a solution portfolio in the admin console groups curated use cases by sector with their capabilities and channels.

More than 45 rich card types cover flights, hotels, orders, loyalty points, card benefits, balances and charts, each with its own prompt instructions. Each agent is still assembled for the customer, and there is no gallery of prebuilt agents to switch on. The public AI Use Case Library of 282 use cases is research on deployments across the market, not a set of installable agents.

Sourceblits.ai/featuresread 2026-10-13

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

An admin chooses the model for each agent from more than 15 providers, including OpenAI, Azure OpenAI, Anthropic, Google Gemini and Gemma, Meta Llama, Mistral, Microsoft Phi, Qwen, DeepSeek, GPT OSS, Hugging Face, Humain, Fanar and OpenRouter, and can move an agent to another provider without rebuilding it. Any OpenAI compatible model connects with the customer's own key.

Regional routing sends traffic to EU or UAE regions, reasoning effort is set per agent, and models above a plan's level stay visible but disabled. Embeddings come from OpenAI, Google, Nomic or OpenRouter, and intent recognition can run on Microsoft CLU, Dialogflow, Watson, Wit.ai or an LLM.

Sourceblits.ai/featuresread 2026-10-13

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

A REST API and a WebSocket API drive the platform from outside, authenticated with bot, agent or workflow JWTs sent as bearer tokens to platform.blits.ai or a regional host.

Endpoints open a conversation, send text, speech or files, check whether it is active, erase a user's data and run intent analysis on a message, and the WebSocket adds streaming speech, history loading and state variables. Separate endpoints run an agent with streamed NDJSON output, start an agentic workflow and return metered interaction counts per tenant. Each hosted MCP server has its own URL and exposes an agent's tools to outside MCP clients over Streamable HTTP with an API key.

Sourceblits.ai/api-docsread 2026-10-13

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

Test suites run automated conversations against agents, bots and workflows through the real chat pipeline, and multi turn sets play out as one continuous session with notes per turn for the grader.

Grading uses deterministic rules or an LLM judge with a configurable prompt, a selectable model and knowledge base evidence, and run reports show the pass rate, per turn verdicts, grader reasoning and run history, with regrading. Test cases import from JSON.

Monitors run scheduled health checks against rule based or LLM expectations and alert by email or webhook, and separate checks compare speech to text providers on word error rate and test MCP tool discovery.

Sourceblits.ai/featuresread 2026-10-13

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

A web browsing tool sits among the built in agent tools beside web search and Wikipedia, so an agent can open and read web pages while it works. UiPath is one of the 56 connectable systems, and the agentic product connects RPA tools, which lets an agent hand screen based work to a robot the customer already runs. There is no hosted browser or desktop session for the agent to drive itself. Real browser testing, which loads the live chat widget under simulated network and CPU conditions, is quality assurance on Blits.ai's own product.

Sourceblits.ai/featuresread 2026-10-13

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