Decagon

What it does

Done-for-you service

PartlyYou run the software and your own CX team owns the AOPs, but Decagon also staffs every engagement with a forward-deployed team, so it is not purely self-service.Most enterprises go live in weeks rather than months. A forward-deployed team are included with every engagement to accelerate your team’s path to…decagon.ai/vs/sierra ↗

How much it does unattended

Runs autonomously

YesThe agent handles inbound customer requests end-to-end across channels without a human, though changes the agent proposes to itself are staged for human approval first.Handle inbound requests end-to-end across web live chat, SMS, WhatsApp, and more.decagon.ai/product/chat ↗

Multi-agent

PartlySeveral specialised models act on one conversation — a supervisor checking responses and a bad-actor screen — but Decagon never describes customers composing or orchestrating multiple agents themselves.during conversations, a supervisor model checks responses in real time and a bad-actor model screens manipulation attemptsdecagon.ai/vs/sierra ↗

Agent permissions

YesThe agent executes real operations such as refunds and identity verification, and how far it may go before escalating is set by AOP guardrails and guidelines.Ensure critical operations like identity verification and refunds are executed securely, reliably, and on-brand with strict controls.decagon.ai/product/overview ↗

Which models it runs on

Claude

PartlyAnthropic is named as one of Decagon's AI providers and is listed as an LLM subprocessor, but the buyer never selects Claude — routing is Decagon's.Decagon enforces zero-day retention with all AI providers like OpenAI and Anthropic, ensuring no conversation data is stored or used for training.decagon.ai/security ↗

GPT

PartlyOpenAI is named as an AI provider and appears as an LLM subprocessor on the trust centre, yet no page offers the customer a choice of GPT.Decagon enforces zero-day retention with all AI providers like OpenAI and Anthropic, ensuring no conversation data is stored or used for training.decagon.ai/security ↗

Model choice

NoModel selection belongs to Decagon, not the buyer: the engine is proprietary and most traffic runs on models Decagon trained itself, with no published model picker.Today, over 80% of all model traffic at Decagon runs on models we trained ourselves.decagon.ai/blog/introducing-decagon-labs ↗

Not established: Open models

Where you use it

In your pipeline

PartlyAgent versions can be tested from CI/CD pipelines and versioned in Git, but nothing describes Decagon acting on a pull request itself.Integrate with CI/CD practices to test every agent version and ensure every change meets the quality bar without regressions.decagon.ai/product/testing-qa ↗

In a browser

YesThe platform is a hosted web console: building, monitoring, QA dashboards and analytics all run in-product behind a sign-in.Track trends across flags and categories to spot systemic issues, monitor progress, and prove impact from a single source of truth shared across…decagon.ai/product/watchtower ↗

Not established: On the command line

Whose machine it runs on

Self-hosted

PartlyDecagon claims headless deployment inside your own infrastructure, but publishes no on-premise or self-hosted edition and runs its platform on its own cloud subprocessors.tools are written in Python with MCP support, and the platform deploys headlessly inside your existing infrastructuredecagon.ai/vs/sierra ↗

Open source

NoNo repository, licence or source availability appears anywhere on the site; the vendor markets the engine underneath as proprietary.Every Decagon agent is built on a proprietary engine that understands your business and becomes more intelligent with every interaction.decagon.ai/product/overview ↗

What it costs to run

How it meters

YesBilling meters customer contact, not seats: a fixed rate per incoming conversation, or a higher rate per resolution with escalations free.Per-conversation pricing: A fixed rate for every incoming conversation, with flexible pricing for higher volumes.decagon.ai/blog/pricing-ai-agents ↗

Free tier

NoEvery entry path on the site is a sales demo: there is no signup, no trial and no free plan, and each engagement ships with a forward-deployed team.Most enterprises go live in weeks rather than months. A forward-deployed team are included with every engagement to accelerate your team’s path to…decagon.ai/vs/sierra ↗

API access

PartlyAgent logic and tools are Git-backed and written in Python and the platform deploys headlessly, but the API reference sits behind a login so the public surface cannot be checked.Decagon is built to feel native to an engineering team: agent logic and tools are Git-backed with versioned workspaces for staging and productiondecagon.ai/vs/sierra ↗

MCP server

PartlyMCP is supported as the way Decagon's agent reaches your systems; no page says Decagon exposes an MCP server another agent could query.Connect to any data system or application via an open standard for real-time data and actions.decagon.ai/product/integrations ↗

Not established: Bring your own key

Buying it for a team

A company can buy it

YesThis is sold to enterprises only — named logos are large organisations and the buying motion runs through a demo and a signed engagement.Our platform enables leading enterprises like Avis Budget Group, Chime, Oura Health, 1-800-FLOWERS.COM, and Hunter Douglas to deploy AI agentsdecagon.ai/about ↗

Seat model

NoPricing is metered on conversations or resolutions rather than per seat, and no seat floor, ceiling or per-user rate is published anywhere.Sierra prices per outcome (per resolution), while Decagon lets you choose per-conversation or per-resolution pricing.decagon.ai/vs/sierra ↗

Admin controls

YesAdmins constrain the agent two ways: role-based platform permissions, and AOP guardrails that gate refunds, escalations and brand voice.Platform access is defined and enforced by role, ensuring every user automatically gets the right permissions for their job.decagon.ai/security ↗

Audit log

PartlyTamper-protected audit logs exist and capture logins and unusual activity, but Decagon states access is limited to its own senior engineering leadership rather than the customer's admins.Comprehensive, tamper-protected logs capture key events, from logins to unusual activity, accessible only to senior engineering leadership.decagon.ai/security ↗

Single sign-on

YesSSO is offered against enterprise identity providers, with Okta and Microsoft Entra named; the underlying SAML or OIDC protocol is not stated.Decagon integrates with identity providers like Okta and Microsoft Entra, enabling secure access across systems without additional passwords.decagon.ai/security ↗

Not established: Pooled budget

What happens to your code

Opt out of training

YesStronger than an opt-out: zero-day retention is enforced with every AI provider by default, so conversation data is not stored or trained on.Decagon enforces zero-day retention with all AI providers like OpenAI and Anthropic, ensuring no conversation data is stored or used for training.decagon.ai/security ↗

Data residency

PartlyDefault processing is US-hosted on Google Cloud; EU-only residency inside EEA infrastructure is available on request.Decagon offers EU-only data residency, in which Customer Personal Data is processed and stored within EEA-located infrastructure.decagon.ai/legal/dpa-security-annex ↗

Getting out

PartlyDecagon asserts full data portability and no SDK lock-in, and its trust centre lists deletion on departure, but no export API or retention terms are published.Complement your systems of record with full data portability, while retaining granular control over what context is stored and how it’s used.decagon.ai/proactive-agents ↗

Certifications

YesA full enterprise set is claimed and the trust centre carries the underlying reports, including a SOC 2 Type II report and an ISO 27001 certificate.SOC 2 Type II, HIPAA, GDPR, PCI, and ISO 27001decagon.ai/vs/sierra ↗