Kore.ai
Also known as: Kore.ai Artemis, Kore.ai XO Platform, Kore.ai Agent Platform
Enterprise agent platform whose agents are authored in a typed blueprint language, compiled and run by a single governed runtime across 27 channels, with pluggable model providers, RAG enterprise search, approval gates and tracing of every reasoning step.
Kore.ai is an enterprise agent platform built for customer experience and also used for wider business work, sold at custom enterprise prices. Agents are written in Agent Blueprint Language, a typed language that compiles to an intermediate form and runs on one governed runtime. Their definitions sit in Git as YAML and move to production through the same CI/CD pipeline as application code.
Its marketplace offers prebuilt agents for customer service, banking, retail, HR, IT, sales, and legal and finance, which install with one click and can be edited afterwards. A tools layer connects outside systems such as Salesforce, SAP, Microsoft, VMware and Zendesk over HTTP, MCP, AWS Lambda, OpenAPI and webhooks.
Agents deploy across 27 channels covering web, voice, messaging, email and enterprise APIs, so one agent handles both voice and chat. Workflows can pause at approval gates until a person signs off, Agent Evals holds back a release that fails its test suites, and tracing records every reasoning step and tool call.
Vendor details
Canonical URL
https://kore.ai
Category
Customer support agent
Subcategory
CX agent platform
Company status
independent
Use cases & customers
Primary use cases
Target customers
Deployment options
In practice
Building a CX agent from scratch is months your team doesn't have. Kore.ai's marketplace offers prebuilt agents such as Escalation Predictor and Contextual Email Responder that install with one click, so you start from a working pattern instead of a blank canvas.
Your agent needs to plug into the systems behind your support, not just chat. Kore.ai's tools layer connects Salesforce, SAP, Zendesk and other systems over HTTP, MCP, OpenAPI and webhooks, so the agent reaches the data and tools it needs.
Customers call and chat, and you don't want two separate bots. Kore.ai deploys one agent across 27 channels, voice, web and messaging among them, with consistent behavior and no rebuilding for each channel.
Agentic Index coverage score
13.0 / 14 capabilities · 93%
| Integrations & Tool Calling | Full |
|---|---|
|
The tools and integrations layer connects outside systems over HTTP, MCP, AWS Lambda, SDK invocations, the A2A protocol, sandboxed tools, OpenAPI definitions and webhooks, with circuit breakers and retry logic. Data sources such as Salesforce, SAP, Microsoft, VMware and Zendesk are reached through tool definitions, so none of them is built into agent logic. SourceKore.ai Agent Platform documentation; docs.kore.ai/agent-platformread 2026-09-05 |
|
| Workflow Orchestration | Full |
|
Four orchestration patterns are invoked through ABL constructs and enforced by the runtime. They include parallel fan out with barrier synchronization, asynchronous delegation that survives pod restarts, and turns carrying several intents that map to several agents. Supervisor routing arbitrates handoff and delegation, a pipeline classifier skips the reasoning loop for intents it recognizes with high confidence, and the Google A2A protocol carries communication to agents hosted on other runtimes. The runtime's two engines execute agentic reasoning and deterministic flows in parallel from one definition. SourceKore.ai Agent Platform documentation; docs.kore.ai/agent-platformread 2026-09-05 |
|
| Knowledge Grounding & RAG | Full |
|
Search AI is the platform's knowledge retrieval layer, providing RAG, vector search, knowledge graph traversal and reranking to surface context to agents as they reason. The customer configures it and the platform maintains it, and the retrieval pipeline comes with guidance on model selection, chunking and context window sizing. SourceKore.ai Agent Platform and Search AI documentation; docs.kore.ai/agent-platformread 2026-09-05 |
|
| Human Oversight & Guardrails | Full |
|
The Workflow Engine runs workflows lasting minutes to days, with built in steps where a person reviews the work and approval gates that hold it until someone signs off. Guardrails are a core ABL construct enforced outside the model, the runtime carries guardrails in several tiers with circuit breakers and rate limits, and supervisor routing checks those guardrails, so the runtime overrides an agent's chosen route when policy requires. Arch AI hands its work products to a person to review and never applies them silently. SourceKore.ai Agent Platform documentation; docs.kore.ai/agent-platformread 2026-09-05 |
|
| Security, Identity & Governance | Full |
|
Security and governance include SSO, role based access control, guardrails, audit logging, encryption, key management, multitenancy with full tenant isolation, PII detection, identity verification and compliance reporting, on an enterprise foundation carrying PCI, SOC 2, GDPR and FedRAMP certification, with handling for the right to erasure and data minimization controls. SourceKore.ai Agent Platform documentation; docs.kore.ai/agent-platformread 2026-09-05 |
|
| Observability & Auditability | Full |
|
Observability follows the agent's reasoning, capturing every reasoning step, tool call, routing decision and guardrail evaluation as structured trace data across chains of delegated agents. Deep Observability records over 200 trace events per session and provides runtime inspection, alerting and debugging of each session across interactions between agents. SourceKore.ai Agent Platform documentation; docs.kore.ai/agent-platformread 2026-09-05 |
|
| Memory & State Persistence | Full |
|
Memory is a formal construct in Agent Blueprint Language alongside goals, tools and guardrails, executed against a shared memory layer that coordinates state across both cognitive engines. Session Meta Memory is managed by the system. Custom Memory Stores are persistent and structured with JSON Schema, and each takes a scope: one user across all of that user's sessions, a single session that clears when it ends, or the whole application. A retention policy sets each store to last a session, a day, a week or a month, and tools read, write and delete store content at run time. Shared stores pass structured context between agents. Sourcedocs.kore.ai agent platform memory stores guideread 2026-10-25 |
|
| Deployment & Data Residency | Full |
|
Kore.ai runs as cloud SaaS or self hosted for organizations with data residency or compliance requirements, with the same platform capabilities either way. The infrastructure layer plugs into Microsoft Azure, Google Cloud, AWS, on premises installations and private VPC deployments, so the customer chooses where the platform runs. SourceKore.ai Agent Platform documentation; docs.kore.ai/agent-platformread 2026-09-05 |
|
| Prebuilt Agents, Templates & Packs | Full |
|
The AI agent marketplace offers named prebuilt agents across banking (ATM Locator, Dispute and Fraud Handler), retail (Product Search, Order Management), HR (Absence Management, Screening Agent), IT (Incident Management, Access Management), sales (RFP Response Automation, Lead Analyzer), legal and finance (Contract Amendment Assistant) and customer service (Escalation Predictor, Contextual Email Responder), installed with one click. Marketplace agents import with their predefined tools and workflows, and any component can be edited afterwards. SourceKore.ai AI agent marketplace and Create an Agent from Marketplace documentation; docs.kore.ai/agent-platform/agents/create-from-marketplaceread 2026-09-30 |
|
| Triggers & Channel Coverage | Full |
|
Agents deploy across 27 channels covering web, voice, messaging, email and enterprise APIs, among them Microsoft Teams, ServiceNow, Slack, Webex and Zoom, with consistent behavior and no rebuilding for each channel. SourceKore.ai Agent Platform documentation; docs.kore.ai/agent-platformread 2026-09-05 |
|
| Model Flexibility & Routing | Full |
|
Every layer of the ecosystem is pluggable, so the customer swaps providers without rewriting agents. Supported models include OpenAI, Anthropic, NVIDIA, Cohere and LLaMA 2 among others, and open source and custom fine tuned models work through the same interface. A models library lets an admin add a new model or a custom integration, models hosted by a third party or by the enterprise itself can be brought in, each feature can be assigned its own model, and an analytics dashboard reports token distribution, latency and cost per model connection. SourceKore.ai Agent Platform and Generative AI model documentation; docs.kore.ai/agent-platformread 2026-09-05 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
Agent Blueprint Language is a typed language driven by schemas, compiled from DSL to intermediate representation to runtime, with definitions stored in Git as diffable YAML, reviewed in pull requests and promoted by the same CI/CD practices as application code. The tools layer exposes HTTP, MCP, SDK invocations, OpenAPI, webhooks and the A2A protocol for communication with agents on other runtimes, including agents hosted outside the platform. SourceKore.ai Agent Platform documentation; docs.kore.ai/agent-platformread 2026-09-05 |
|
| Testing, Debugging & Optimization | Full |
|
Agent Evals is an automated evaluation framework for the customer's own agents, with test suites, regression tracking and quality gates that run as part of the deployment pipeline, and the results decide whether an agent is promoted. The environment pipeline routes every agent through a staging tier where automated suites and regression checks run before a pilot tier validates behavior on limited real traffic. Validation at compile time catches broken references before deployment. SourceKore.ai Agent Platform documentation; docs.kore.ai/agent-platformread 2026-09-05 |
|
| Browser & Computer Use | Not documented |
|
Agents reach outside systems only through the tools layer (HTTP, MCP, Lambda, SDK, A2A, OpenAPI and webhooks) and reach users through 27 programmatic channels. They do not drive a browser, a virtual desktop or software that lacks a programmatic interface. SourceKore.ai Agent Platform documentation; docs.kore.ai/agent-platformread 2026-09-05 |
|
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
Version 1.8.3 of the Kore.ai agent platform lets a voice agent send the caller a WhatsApp message with tappable options, such as appointment slots, while the call is still live. The message goes through the project's WhatsApp connection on Meta Cloud or Infobip. The caller's tap or typed reply comes back into the call as input, on both pipeline and realtime voice.
Bears on: Integrations
View sourceVersion 1.8.0 of Kore.ai's agent platform adds three approval modes to Autoloop: Autopilot applies changes automatically, Copilot applies them only after a person approves, and Advisor only suggests changes. The mode can be set when a loop starts or changed during a run.
Bears on: Agent capability
View sourceA Human Task node for process workflows arrived in version 1.7.0 of Kore.ai's agent platform. It pauses the workflow, notifies assignees, collects structured input through reusable forms and resumes on the chosen outcome, with deadlines, reminders and escalation.
Bears on: Workflow orchestration
View sourcePricing
No public price. Essential, Advanced and Enterprise plans are sold through sales.
Hybrid. Automation AI and Search AI bill per 15 minute session, and Contact Center AI and Agent AI bill per agent seat.
Included quota
Essential, Advanced and Enterprise plans are named without prices. Enterprise includes up to 1 GB of Search AI data ingestion by default.
What is public
The plan names (Essential, Advanced and Enterprise) and the billing units are public, with Automation AI and Search AI in 15 minute sessions, Contact Center AI and Agent AI per agent seat, and free credits on new accounts. Prices are not. There is no pricing page, and buyers reach a price by talking to an expert.
Billing mechanics
Automation AI and Search AI bill per 15 minute session, so a 31 minute conversation is three sessions. Contact Center AI and Agent AI bill per agent seat. Prices are quoted by sales.
Cost watchouts
Sessions bill in 15 minute units, inactivity included. Contact Center AI and Agent AI need seats, and voice and integrations add cost.
Variable cost rationale
Two things are metered. Automation AI and Search AI bill per 15 minute session, counted including idle time, so a 31 minute conversation is three sessions and the bill grows with conversation volume and length. Contact Center AI and Agent AI bill per agent seat, and voice speech to text and text to speech (STT/TTS) add cost on top. No session rate, seat price or minimum is public. New accounts get free credits in an unstated amount.
Additional watchouts
Prices come only from a quote. Session billing counts every 15 minutes including idle time, so long or voice conversations cost more.
Sales call required
Mixed (some tiers require a call)
Free / trial
Free credits for new accounts, amount not public
Lowest paid plan
Not published
Commercial notes
Enterprise agent platform sold through sales, with no self serve per conversation rate.
Key ambiguities
No plan price is public, so the session rate and the seat price come only from a quote.
Support SLA / resale
Standard support is by email and knowledge base. Enterprise support is offered, along with the XO GPT model and Kore.ai Academy training.
Missing data
Plan prices, the free credit amount and any minimum.
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 Kore.ai
The closest documented capability profiles to Kore.ai 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.
- ElevenAgents12.5 / 14A lighter documented profile than Kore.ai
- Khoros12.5 / 14A lighter documented profile than Kore.ai
- Bland AI12.0 / 14A lighter documented profile than Kore.ai
- Cognigy12.0 / 14A lighter documented profile than Kore.ai
- Infobip12.0 / 14A lighter documented profile than Kore.ai
- Kapture CX12.0 / 14A lighter documented profile than Kore.ai
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded