Ada

Summary

Ada is an enterprise customer-service platform whose AI agents resolve inquiries across voice, chat, email, SMS and social from one Reasoning Engine. Playbooks, coaching and simulations let a CX team build, test and govern that agent from a web dashboard.

Best for: Enterprises that want a long-running, well-capitalized AI support agent vendor with a public V2 REST API and an MCP server, rather than a sales-only integration surface.
Not for: Teams that want transparent public pricing, a self-serve trial to test before buying, or that have been burned before by a wide gap between polished admin tooling and the actual end-customer chat experience.

Captured 2026-09-08 · theagentsindex.com

Price: Ada's pricing is simple and transparent. With our conversation-based pricing model, you pay for every conversation your AI agent has with end usersno public pricing
Free tier: NoNo standing $0 plan and no self-serve trial: /pricing redirects to the demo booking form, the login page only mails links to instances you already have, and use requires a signed Order Form.

Visit Ada Compare Find alternatives

What it does

Writes code: PartlyNot a coding agent, but Ada's own MCP Server lets a connected assistant author the Python behind a Code tool from a plain-language description; the draft stages on a change set until a human promotes it.Connect an AI assistant to Ada's MCP Server and describe the tool; the assistant writes the name, description, inputs, outputs, and code.docs.ada.cx/docs/automation/tools/code-…
Debugs and fixes: NoAda diagnoses its own agent's conversations, not software failures; its only code surface is a small data-shaping Python tool.A code tool runs a small piece of Python to clean up, transform, or compute data before your AI Agent uses it.docs.ada.cx/docs/automation/tools/code-…
Writes tests: NoTest cases here are multi-turn conversation scenarios scored pass/fail against the AI agent's replies, not software tests.Create test cases from production conversations, trigger test runs, and review pass/fail results and evaluation rationale, all without leaving your…docs.ada.cx/mcp/introduction/overview
Reviews code: NoThe only review surface is the agent's own configuration; nothing reads a diff or a pull request.Audit your setup. "Summarize our configuration" returns every playbook, API tool, coaching entry, and custom instruction in one view.docs.ada.cx/mcp/introduction/overview
Whole-codebase work: NoThere is no repository concept: code exists only as single sandboxed snippets in a restricted Python subset.Language: Python only, a restricted subset, not full Python. A few standard-library modules can be imported; no classes.docs.ada.cx/docs/automation/tools/code-…
Ships it: PartlyOnly for Ada's own sandboxed Code tools: promoting a change set puts the Python live in production conversations and a promote can be reverted, but a human approves and nothing deploys to your infrastructure.When the results look right, promote the change set to make the tool live. A promote can be reverted if you need to roll back.docs.ada.cx/docs/automation/tools/code-…
Done-for-you service: PartlyYou run the software, but Ada sells consultants who embed with your team plus a certified partner network, so the build can be shared rather than fully outsourced.Ada's strategic and technical experts embed with your team to establish and scale your ACX function and continuously improve your AI customer service…ada.cx/experts

How much it does unattended

Runs autonomously: YesAda's central claim is end-to-end resolution without a human: it authenticates, executes the workflow and confirms the outcome, escalating to a live agent only on the rules you set.AI agents that act autonomously, understand complex customer problems, take action on the customer's behalf, and resolve issues end to end.ada.cx/platform
Multi-agent: NoOne agent per instance on a single reasoning layer; additional Ada Agents are separate instances added as separate connections, and escalation goes to a human.Unified Reasoning Engine™: A single unified intelligence layer that delivers consistent experiences across channels.ada.cx/platform
Agent permissions: YesEvery connected tool starts off and is enabled one at a time, write tools can be gated behind a Playbook, and availability rules limit what content the agent may reach mid-conversation.No tool runs until you turn it on. Enabling a tool is the deliberate step that lets the Agent use it.docs.ada.cx/docs/automation/tools/mcp-t…

Which models it runs on

Claude: YesAnthropic is named as a model provider for all services, and Ada's docs also cover managing the agent from Claude Desktop and Claude Code; the specific Claude model is not published.Ada maintains a curated portfolio of models from leading vendors such as OpenAI, Anthropic, and Cohere.ada.cx/platform/trust
GPT: YesOpenAI is named among Ada's model vendors and appears twice on the subprocessor list, directly and via Microsoft Azure's OpenAI, for all services rather than one channel.Ada maintains a curated portfolio of models from leading vendors such as OpenAI, Anthropic, and Cohere.ada.cx/platform/trust
Open models: PartlyAda internally hosts open-source LLMs for contextual understanding only; reply generation runs on the commercial providers and the customer selects neither.internally hosts other open source LLMs for additional contextual understandingsecurity.ada.cx
Model choice: NoAda chooses and rotates the models itself behind one Reasoning Engine, benchmarking candidates before selection; no documented control lets a buyer pin or swap the model.New LLMs are benchmarked across accuracy, safety, latency, and cost before selection.ada.cx/platform/trust

Where you use it

In your editor: PartlyThere is no in-editor product, but Cursor and VS Code can reach Ada's MCP server, so an AI manager can query and edit the agent from an IDE client.configure through Cursor's MCP settings. Both OAuth and API key work.docs.ada.cx/mcp/introduction/getting-st…
On the command line: PartlyAda ships no CLI of its own; terminal use means pointing an MCP-capable CLI such as Gemini CLI or Claude Code at your instance's MCP endpoint.supports MCP server connections through its settings configuration. Both OAuth and API key authentication are supported.docs.ada.cx/mcp/introduction/getting-st…
In your pipeline: PartlyThe Platform API can be driven from a CI pipeline to push tools and MCP clients run in non-interactive environments, but there is no pull-request or build-check surface.For developers pushing code that is already written and reviewed, for example from a repository or CI pipeline.docs.ada.cx/docs/automation/tools/code-…
In a browser: YesThe dashboard is the primary surface: Performance Center, Playbooks, Tools, Team and Audit log all live there, and the deployed agent itself runs in a web chat widget.The Performance Center gives your team full visibility and control to build, launch, analyze, and optimize your AI agent.ada.cx/platform

Whose machine it runs on

Self-hosted: NoAda is sold as a service and runs on Ada's own AWS and Azure hosting; the only infrastructure choice a buyer gets is enrolling in the Europe data storage option.Ada Support's software platform, made available as a service, through which it provides its conversational Bots and related software offeringsada.cx/legal/customer-terms-of-use
Open source: NoThe platform and its models are Ada's proprietary property under the customer terms; only the client-side messaging SDKs are distributed publicly through GitHub, npm and Maven.Ada Support owns all right, title, and interest, including Intellectual Property Rights, in and to: (i) the Services, including any Ada Models…ada.cx/legal/customer-terms-of-use

What it costs to run

How it meters: YesBilling is per end-user Conversation, contractually a 24-hour window of unlimited messages in one channel, with a resolution-based model offered as an alternative; no rate is published.With our conversation-based pricing model, you pay for every conversation your AI agent has with end users, making costs easy to predict, simple to…ada.cx/platform
Free tier: NoThere is no self-serve signup or standing free plan: /pricing redirects to the demo booking form, and the login page only mails links to instances you already have.Book a free consultation with our AI customer service experts to discover how you can deliver efficient, high-quality support on every channel.ada.cx/demo
API access: YesA documented REST platform API with rotatable keys, an OpenAPI spec, webhooks and a playground covers knowledge, conversations, tools, playbooks, audit log and data export.Ada's suite of APIs opens up multiple integration paths to connect Ada with external systems, extending the capabilities of your AI agent.docs.ada.cx/reference/introduction/over…
MCP server: YesAda runs its own MCP server per instance with OAuth or API-key auth, so another agent can read metrics and conversations and stage configuration changes.Manage Ada from your AI assistant (Claude, ChatGPT, Gemini, etc.) with the same capabilities available in the Ada dashboard.docs.ada.cx/mcp/introduction/overview
Bring your own key: NoInference runs on Ada's own provider agreements; no bring-your-own-key or own-cloud path exists. You do supply credentials for your own systems when connecting API and MCP tools.All large language model (LLM) providers operate under Zero Data Retention (ZDR) agreements, ensuring customer data is never stored or reused by…ada.cx/platform/trust

Buying it for a team

A company can buy it: YesBuying is organisation-level by design: a signed Order Form sets the fees, the users and the volumes, with affiliate and marketplace purchase routes on top.Customer will pay the fees as described in the applicable Order Formada.cx/legal/customer-terms-of-use
Seat model: NoThe commercial unit is the end-user Conversation, not the dashboard seat; the count of Authorized Customer Users sits in the Order Form with no published per-seat price, floor or ceiling.Conversation: means unlimited messages between a Bot and an End User in a single Channel, other than for a Voice Conversation or Email Conversation…ada.cx/legal/customer-terms-of-use
Pooled budget: YesA customer buys one account-level allowance of Conversations shared across users and channels; exceeding the Order Form limit is invoiced at rates Ada does not publish.If Customer purchases a set number of Conversations and exceeds the Conversation limit in the Order Formada.cx/legal/customer-terms-of-use
Admin controls: YesAdmins constrain the agent with variable-based availability rules on knowledge and Playbooks, per-tool enablement, redactions on tool output, and four dashboard roles.An availability rule controls which content the AI Agent can access during a conversation, based on the values of variables.docs.ada.cx/reference/introduction/avai…
Audit log: YesConfiguration changes are logged with actor, entity, activity and interface, including changes made over the API or MCP, filterable and exportable to CSV up to 10,000 rows.The Audit log records configuration changes made to your AI Agent, giving administrators a chronological, searchable history of who changed what,…docs.ada.cx/docs/other/audit-log
Single sign-on: YesSAML 2.0 against any compliant IdP through Ada's Okta service provider; no OIDC is documented, IdP-initiated login is unsupported, and setup needs an Ada representative.Connect any SAML 2.0 compliant identity provider to Ada.docs.ada.cx/docs/other/team-access/sso

What happens to your code

Opt out of training: YesNothing to opt out of: zero-data-retention agreements with every LLM provider are the default, and the terms bar training without explicit agreement, though Ada keeps de-identified aggregate data.All large language model (LLM) providers operate under Zero Data Retention (ZDR) agreements, ensuring customer data is never stored or reused by…ada.cx/platform/trust
Data residency: PartlyHosting is listed for the USA, Canada and Europe, but European storage is an opt-in enrolment, several subprocessors are USA-only, and the residency terms themselves are contractual.Only Ada customers who have enrolled in Ada's Europe data storage option will have their data stored in the European data centres of the…ada.cx/legal/subprocessors
Getting out: PartlyA Data Export API pulls conversations and a Snapshot API exports the agent configuration, but at termination the terms promise only 'certain' data and nothing is published about unused prepaid Conversations.enable Customer to request and export certain Customer Data, and after such reasonable period of time, Ada Support will destroy or permanently delete…ada.cx/legal/customer-terms-of-use
Certifications: YesSOC 2 Type II, HIPAA and GDPR are claimed outright, with PCI DSS and AIUC-1 certification on the same page; the Trust Center holding the reports is behind a bot check.Ada holds SOC 2 Type II and HIPAA certifications and operates in compliance with GDPR.ada.cx/platform/trust

35 sourced claims on this page. Checked 2026-09-09. How we check.

Alternatives

Where we would send a reader instead, in that listing's own words.

Decagon
Enterprise AI support agents for chat, voice and email, built from natural-language Agent Operating Procedures.
Sierra
Conversational AI platform for building enterprise customer-service agents across voice, chat, email and ChatGPT.
Cresta
Contact-centre AI platform for voice and digital AI agents, real-time human agent assist, and conversation analytics.
Crescendo
AI-native CX platform whose agents resolve customer contacts across voice, chat, email and messaging.
Fin
Customer service AI agent priced per resolved outcome, deployable on any helpdesk.
Zendesk AI agents
Customer-service AI agents for messaging, email and voice, billed per automated resolution.

Filed under

APIAutonomousClaudeEnterpriseGPT

Sources and updates

The pages we read26

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

Coverage elsewhere4

Updates5

2026-09-09Capabilities · Commercial terms · Free tier · Price
2026-09-02Capabilities · Commercial terms · Free tier
2026-08-31Capabilities · Commercial terms · Free tier
2026-08-22Alternatives · One-liner · Summary
2026-08-19One-liner · Summary