# Crescendo — AI-native CX platform: agents resolving support across voice, chat, email and SMS, with a staffed team behind them.

> Source: The Agents Index — https://theagentsindex.com/crescendo (structured, researched, re-verified)
> Facts last verified: 2026-09-12

Crescendo is an AI-native customer experience platform whose agents resolve support conversations across voice, chat, email, SMS and WhatsApp. It ships with a staffed CX team that deploys, tunes and runs the system alongside the software.

| Fact | Value |
| --- | --- |
| Website | https://www.crescendo.ai/ |
| Price | from $1.25/resolution pay-as-you-go |
| Free tier | No |

No $0 plan and no self-serve trial is published. The free items are onboarding ('100% Free Onboarding') and Total Outcome Guarantee credits for dissatisfied AI-resolved interactions; the only route to the product is a booked demo.

## What it does

**Writes code** · Partly — Only inside its own integration workspace: Crescendo Connect turns a plain-English capability request into generated integration code and a published tool, not into application code in your repository.

> It reads the API documentation, plans the integration, generates the code, tests happy-path and failure-path scenarios
> — https://www.crescendo.ai/blog/crescendo-connect-agentic-integration · 'How Crescendo Connect works' section, paragraph describing the build loop

**Debugs and fixes** · Partly — Debugging is scoped to the integrations it builds: failures in a tool run are inspected, the logic updated and rerun in the same workspace, rather than diagnosing bugs in customer software.

> Inspect failures, update logic, and rerun in the same workspace.
> — https://www.crescendo.ai/blog/crescendo-connect-agentic-integration · Stage table, 'Debug' row

**Writes tests** · Partly — It generates and runs happy-path and failure-path scenarios against each integration before the assistant may call it; these are vendor-run integration checks, not a test suite you own or edit.

> Run happy-path and failure-path scenarios before the assistant uses it.
> — https://www.crescendo.ai/blog/crescendo-connect-agentic-integration · Stage table, 'Test' row

**Ships it** · Partly — It ships what it builds only into its own runtime: a tested integration is published as a governed tool the assistant can call in live chat and voice, with no deployment to customer infrastructure.

> Expose the tested capability as a governed tool for chat and voice.
> — https://www.crescendo.ai/blog/crescendo-connect-agentic-integration · Stage table, 'Publish' row

**Done-for-you service** · Yes — This is software plus people: Crescendo deploys its own team to calibrate the platform, and its PartnerHero affiliates in seven countries supply human support agents and QA.

> We deploy a team that keeps the platform calibrated to your business and owns the outcome.
> — https://www.crescendo.ai/ · 'FAST changes everything' section, 'Applied expertise' card

## How much it does unattended

**Runs autonomously** · Yes — The Concierge agent is described as closing issues end to end — status lookups, account updates, order changes — and handing off with full context only when it cannot resolve.

> Agentic infrastructure means that Concierge understands customer intent, takes action, and closes issues without a human in the loop.
> — https://www.crescendo.ai/agents/concierge · 'Concierge is Crescendo's front-door AI resolution agent' section, 'Agentic handling' card

**Multi-agent** · Yes — Seven named agents divide the operation — Concierge, Quality, Agent Assist, Applied Insights, Optimization, Integration and Knowledge — and feed each other in a documented improvement loop.

> A team of autonomous CX agents that work 24/7 so your team can focus on the high-judgment work.
> — https://www.crescendo.ai/ · 'Meet your Crescendo AI team' section, intro paragraph

**Agent permissions** · Yes — A named Safe Action Framework splits autonomous actions from ones needing human approval, and published integration tools carry typed inputs, permissions and review before the agent may call them.

> Tenant-isolated, audit-logged, and governed by a Safe Action Framework that determines what AI can do autonomously and what requires human approval.
> — https://www.crescendo.ai/ · 'The right CX solution builds trust' section

## Which models it runs on

**Claude** · No — Anthropic appears nowhere on the site, and the binding sub-processor list that authorises every third party touching customer data names OpenAI, Google Gemini/Vertex, Groq, Azure and Amazon Nova Sonic only.

> Third-party providers Crescendo uses to process personal data; the Use column clarifies whether each supports the Platform, Admin, or Both.
> — https://www.crescendo.ai/subprocessors · 'Crescendo Authorized Sub-processors' table introduction

**GPT** · Yes — OpenAI is a listed sub-processor and Crescendo announced GPT-5 across CX Assistant, Voice of Customer and CX Insights, available to all customers rather than gated to a tier.

> GPT-5 is available in all Crescendo environments.
> — https://www.crescendo.ai/news/crescendo-adds-gpt-5 · 'Available Now' section

**Model choice** · No — The vendor picks: requests are fanned out across several LLM providers in parallel and the fastest valid response wins, with no published control for a buyer to pin a model.

> Crescendo’s multi-provider architecture routes every AI request across multiple large language model (LLM) providers in parallel, and automatically selects the fastest valid response in real time.
> — https://www.crescendo.ai/news/multi-provider-architecture · Third paragraph of the press release body

_Not established: Open models_

## Where you use it

**In a browser** · Yes — Everything runs in the browser: an embedded chat widget on the customer's site and app, plus a hosted dashboard where conversations, routing and analytics live.

> Manage all support conversations in one streamlined dashboard.
> — https://www.crescendo.ai/solutions/features · 'Features and Capabilities' list, 'Helpdesk Software' entry

## Whose machine it runs on

**Self-hosted** · No — Delivered as software-as-a-service only; the platform runs on Google Cloud Platform with US sub-processors, and no on-premise, VPC or bring-your-own-infrastructure option is offered on any tier.

> Crescendo’s software-as-a-service platform provided to Customer as part of the Service(s), which is distinct from End User Support Service and any Non-Crescendo Services.
> — https://www.crescendo.ai/policies/platform-terms · Schedule A: Definitions, definition of “Platform”

**Open source** · No — Proprietary throughout: no repository, licence or source release is published anywhere on the site, and the platform terms forbid reverse engineering or adapting the service.

> reverse engineer, modify, adapt, or hack the Service, or otherwise attempt to gain unauthorized access to the Service or its related systems or networks
> — https://www.crescendo.ai/policies/platform-terms · Section 1.1.2 Usage Restrictions, clause (e)

## What it costs to run

**How it meters** · Partly — Billing is per resolution — $1.25 for AI-handled, $2.25 for the AI-plus-human model — but the fixed monthly fee charged alongside it is never quantified, so only half the unit is public.

> It charges a flat rate of $1.25 per resolution and a fixed monthly fee.
> — https://www.crescendo.ai/blog/how-much-do-chatbots-cost · 'Crescendo AI: Performance-Based Chatbot Pricing Example' section, 'All-in-One Pricing Policy'

**Free tier** · No — No $0 plan, self-serve signup or trial is published; the single route in is a booked demo, and the only free items are onboarding and the guarantee credits.

> Book a personalized demo with us. We’ll show you how our technology, and our agents, can elevate and evolve your customer experience.
> — https://www.crescendo.ai/contact · 'Schedule a demo' section, the only conversion path published on the site

**API access** · Partly — Developers can drive the embedded assistant from their own page through widget functions that pass context, but no public REST API or developer documentation for the platform is published.

> Web developers can now invoke functions to send contextual information or set pre-filled fields in the CX Assistant widget.
> — https://www.crescendo.ai/blog/crescendo-technology-platform-release-notes-june-2025 · 'CX Assistant Context Collection' section

**MCP server** · Partly — MCP runs the other way round: Crescendo's assistants act as clients against third-party MCP servers such as Shopify's, and no Crescendo MCP server is published for outside agents to query.

> Crescendo adds additional support for Model Context Protocol (MCP) providing new capabilities that allow Assistants to interface more effectively to existing systems
> — https://www.crescendo.ai/blog/crescendo-ai-suite-2025 · 'Integrations in minutes not days' section, 'What's new'

**Bring your own key** · No — Inference is Crescendo's to arrange: the contract defines LLM providers as entities it retains, and the only customer lever is objecting to a named sub-processor within thirty days.

> any entity retained or used by Crescendo to provide certain AI features, including but not limited to chatbot functionality
> — https://www.crescendo.ai/policies/platform-terms · Schedule A: Definitions, definition of “Third-Party LLM Provider(s)”

## Buying it for a team

**A company can buy it** · Yes — Sold to organisations only, under a master agreement and executed Service Orders, with the platform licensed for the customer's internal business operations and its end users.

> make the Platform available to Customer for use by Authorized Users solely for the internal business operations of Customer and End-Users via Customer’s website and mobile application
> — https://www.crescendo.ai/policies/platform-terms · Section 1.1 Provision of the Platform, clause (a)

**Seat model** · No — Not a per-seat product: Crescendo prices the resolution and says so explicitly against seat-selling rivals, so no seat floor, ceiling or per-agent rate is published.

> While others sell seats, licenses, or hype, we tie our success to business outcomes.
> — https://www.crescendo.ai/news/multi-provider-architecture · 'About Crescendo' boilerplate at the foot of the press release

**Pooled budget** · Partly — Buyers hold one contracted conversation volume rather than per-seat balances, and low-CSAT conversations are excluded from it; no allocation or sub-budget controls are described.

> under our Quality Guarantee, any conversation scoring 2 or lower on Predictive CSAT doesn't count toward your contracted volume at all.
> — https://www.crescendo.ai/crescendo-vs-fin · FAQ, 'How is Crescendo packaged?', final paragraph

**Admin controls** · Yes — Admins constrain both people and agent: role-based permissions govern who sees what, and the Safe Action Framework decides which actions the AI may take unattended.

> Control who can see and do what with flexible access roles.
> — https://www.crescendo.ai/solutions/features · Security section, 'Custom Permissions' entry

**Audit log** · Yes — Access logging and real-time activity tracking are listed platform features, and the homepage describes every tenant as audit-logged; retention windows are configurable.

> Track who accessed what and when, for added visibility and security.
> — https://www.crescendo.ai/solutions/features · Security section, 'Access Log' entry

_Not established: Single sign-on_

## What happens to your code

**Opt out of training** · Partly — The DPA bars use of customer personal data beyond delivering the service, but there is no published model-training opt-out, and de-identified derivatives of your data become Crescendo's property.

> Crescendo will not: (i) retain, use, or disclose Customer Personal Data for any purpose other than for the specific purpose of performing the Services specified in the Agreement for Customer
> — https://www.crescendo.ai/policies/data-processing-agreement · Section 5.4, Crescendo Obligations

**Data residency** · Partly — No region choice is offered: every listed sub-processor sits in the United States and the DPA reserves global transfer, with EU and UK transfers covered by Standard Contractual Clauses.

> Crescendo may transfer and Process Customer Personal Data on a global basis as necessary to provide the Service(s).
> — https://www.crescendo.ai/policies/data-processing-agreement · Section 13.1, Data Transfers

**Getting out** · Yes — Reports and insights export to CSV, Excel, image or PDF in-product, and on termination the customer instructs deletion or return of all personal data; no credits exist to expire.

> Following the termination or expiration of the Agreement, Customer shall provide written instructions to Crescendo to delete or return all Customer Personal Data and Crescendo shall comply
> — https://www.crescendo.ai/policies/data-processing-agreement · Section 8.1, Deletion or Retrieval of Personal Data

**Certifications** · Yes — SOC 2 Type II, ISO 27001 and HIPAA attestation with GDPR- and CCPA-aligned controls; certificates and the DPA are requestable from the trust portal, and a BAA is available.

> SOC 2 Type II and HIPAA attested, with GDPR- and CCPA-aligned controls, ISO 27001 certification, and automated PII and PHI redaction during export
> — https://www.crescendo.ai/news/multi-provider-architecture · 'Enterprise-grade trust' bullet in the press release

## Provenance

Every fact above comes from the vendor. Nothing here is independently corroborated yet.

## Coverage elsewhere

Pages about this product that the vendor does not control. The label states how independent each one is.

| Source | Kind | Read |
| --- | --- | --- |
| cmswire.com | Independent source | 2026-08-23 |
| ringly.io | A competitor's comparison | 2026-08-23 |

## What changed

- 2026-09-12 — Capabilities · Commercial terms · Free tier · Price
- 2026-09-02 — Capabilities · Commercial terms · Free tier
- 2026-08-31 — Capabilities · Commercial terms · Free tier
- 2026-08-23 — One-liner · Summary

## Correcting this record

Anything marked "Not established" is a question we have not answered — it is not a No. If you represent Crescendo, or anything here is wrong or out of date, you can supply it with a source: the operations this site accepts from an agent are listed at https://theagentsindex.com/.well-known/agents.json — that catalogue needs no key to read, and each entry states its own auth.

Supplying evidence is free. Nothing that can be bought here changes what a field says, whether a gap is closed, or how this record is scored.