Decagon
Builds and runs customer-support agents that resolve enquiries over chat, email and voice.
What it does
- Customer support
- Voice agent
Features 6
- MemoryMaintains customer context across sessions and channels, with data portability and control.
- Seamless integrationIntegrates with ticketing platforms, CRMs, knowledge bases, CCaaS providers and custom systems.
- Guardrails and guidelinesStrict controls so operations like identity verification and refunds run securely and on-brand.
- Transparent observabilityTraces how and why the agent made each decision, from model calls to referenced knowledge articles.
- Diagnostic toolsAI-powered recommendations across knowledge base, workflow design and tooling to prioritize improvements.
- Enterprise securityBuilt-in guardrails, secure access and data management controls.
How it compares
-
Cresta AI Agent
Both sell AI support agents; Cresta positions one platform across the contact center, Decagon as quick self-service agents.
Cresta is the stronger fit when the goal is to improve the entire contact-center operation
Official documentation · 9 Oct 2026 -
Sierra
Both deliver AI agents for customer experience; per Decagon, they differ on who owns and iterates the agent after launch.
Decagon and Sierra both deliver AI agents for customer experience. The difference is who owns the agent after launch.
Official documentation · 19 Sep 2026 -
Fin AI Agent
For every other team, the data points in one direction. Fin resolves more queries, costs less per resolution, deploys faster, gives your team full control, and operates within a complete platform.
Official documentation · 20 Sep 2026 -
Forethought
Both sell AI agents that resolve support conversations; Forethought pitches journey-wide agents with a no-code builder, Decagon support-only agents built in AOPs.
While Decagon is just getting started, Forethought already resolves over 1.2 billion interactions every month with AI Agents built for the whole customer journey.
Official documentation · 9 Oct 2026 -
Agentforce
Point solutions like Decagon only address specific tasks. Agentforce is a flexible, scalable solution that grows with your business, customized to meet any team, customer, or employee's needs.
Official documentation · 19 Sep 2026 -
Crescendo Concierge
A customer-support AI agent vendor naming itself against Decagon and Sierra, by name, on its own blog.
Choosing between Decagon.ai, Sierra.ai, and Crescendo.ai is not a simple decision.
Company disclosure · 2 Oct 2026 -
Retell AI Voice Agents
Retell vs Decagon - AI Phone Agent Comparison
Official documentation · 13 Oct 2026 -
Ada AI Agent
Compare Decagon, Sierra, and Ada. Each takes a different approach to deployment speed, customization depth, and pricing structure.
Company disclosure · 13 Oct 2026 -
AI Agents
Try Zendesk free and see how its native AI compares to Decagon’s bolt-on approach.
Official documentation · 13 Oct 2026 -
Chatbase
Chatbase and Decagon resolve conversations across chat, email, and voice but Chatbase also adds enterprise controls, team handover, and upfront pricing.
Company disclosure · 5 Nov 2026
Sources
- Pricing
-
Official documentation · 21 Aug 2026
Contact-sales only: a 504-URL sitemap carries no pricing page — its only two pricing-shaped URLs are a blog post and a glossary entry — checked 2026-08-21.
- Constraints
-
Derived from the security facts on this page, from the same source.
- Security
-
Platform-wide: decagon.ai/security. SSO named without SAML so sso-saml omitted. 'Zero-data retention' is enforced with Decagon's LLM providers, not a vendor no-retention mode, so ZDR and trains left unknown. trust.decagon.ai renders empty to curl (see needs_browser). Compliance list read on trust.decagon.ai in a browser 2026-10-21: 'SOC 2 Type II', 'ISO 27001:2022', 'PCI DSS 4.0.1' (company-level; no quote key, script-only portal).
- Sold within
-
The product page's only routes are "Get a demo" and "Contact Sales"; it names no plan, price or self-serve signup.
- Intended for
-
Named enterprise customers Away, Hertz, Noom, Faire; industries Financial services, Travel & hospitality, Health & wellness
Also from Decagon
-
Agent Operating Procedures Agent platform
Decagon's authoring layer for the rules an AI support agent follows, so non-engineering teams can build, iterate on and scale agents.
-
Decagon Chat AI agent
Decagon's chat channel — an AI agent that handles live customer conversations in a web or in-app chat surface.
-
Decagon Email AI agent
Decagon's email channel — agents that read and answer customer email threads rather than routing them to a queue.
-
Decagon Voice AI agent
Decagon's voice channel: an AI agent that answers customer phone calls in place of a hold queue and, through Outbound Voice, also initiates calls to customers at the right moments in their journey.
-
Experiments Application
A/B-testing suite for AI support agents: structured experiments (tone, logic, flows) against live traffic with control groups, statistical-significance testing and gradual rollout.
-
Insights & Reporting Application
Dashboards and natural-language querying ('Ask AI') over support data: CSAT/deflection performance tracking, heatmaps, customer-journey visualization and knowledge-base performance.
-
Suggestions Application
Analyzes support conversations to detect gaps in a company's help center and auto-generates draft articles, ranked by impact, with monthly updates.
-
Testing & QA Application
Integrated testing suite (internally called 'Simulations') that validates AI-agent behavior across channels before production deployment.
-
Watchtower Application
Always-on monitoring and QA for AI and human agent interactions against custom quality criteria.
-
Duet Agent platform
An AI partner built into Decagon that helps teams build and improve support agents — distilling best practices from hundreds of Decagon deployments into guidance for the builder, and auto-tuning the agent via "Duet Autopilot," which improves it with every conversation it handles.
-
Agent Workbench Application
Built-in AI chat assistant that helps business teams debug their Decagon agents by consolidating audit logs, agent reasoning and tool errors, explains why an agent behaved as it did, and guides the fix.
-
Campaign Composer Application
Control center for outbound customer campaigns run by Decagon agents: sets channels, allowed hours and retry logic, sequences follow-ups over days or weeks across SMS and voice, and books callbacks when a customer cannot talk.
-
Agent Modules Application
Catalog of customer-journey modules, such as collections and onboarding, that extend a Decagon agent beyond support with the infrastructure, analytics and campaign orchestration each journey needs, managed as multiple instances of one agent.
-
Personal Agent Gateway Application
Identifies customers' personal AI agents in live chat and voice, routes their requests through a dedicated agent channel, and lets the business control what those agents can do.
Something wrong here? Send a correction — quote this product id: decagon.