Ada

Ada Computer gives the agent API tools that read and write in the customer's systems, code tools for logic such as refunds and eligibility, and MCP tools discovered by connecting any server by URL, with named integrations including Salesforce, Zendesk, ServiceNow, Genesys, Amazon Connect, Twilio Flex, Freshworks and Aircall, and documented handoff integrations into those contact center stacks.

Sourceada.cx/platformread 2026-09-29

Playbooks let the agent follow multi-step SOPs using real-time data, breaking complex journeys into focused steps, answering off-script questions from approved knowledge and returning to the right step, and transitioning to another workflow or a handoff with context; Processes add block-based flows, and the Conversation View traces each Playbook step.

Sourceada.cx/platformread 2026-09-29

A unified intelligence layer grounds the agent in shared customer context, business logic and policies including knowledge bases and SOPs, managed in one place across channels; the Reasoning Engine retrieves knowledge in its original language and answers in 60 languages, and each conversation trace shows which Knowledge articles were used.

Sourceada.cx/platformread 2026-09-29

Oversight is authored constraint plus escalation: API tools are restricted by default to the Processes and Playbooks that call them, can be limited to certain users by rules on collected variables, act in the customer's systems under the customer's controls, and conversations hand off to human agents with context. No step where a person approves an agent action before it runs is documented.

Sourcedocs.ada.cx/docs/automation/tools/api-tools/api-tool-controlread 2026-09-29

Ada publishes both attestations and customer-facing controls.

The trust center at security.ada.cx publishes SOC 2 Type 2 and SOC 3 reports with named observation periods plus HIPAA, and the trust page adds AIUC 1 certification with independent penetration testing at the infrastructure and AI model layers and zero data retention with LLM providers.

For customers, the docs document SSO for team access and an Audit log of every configuration change with actor, entity and interface, exportable through an Audit Log API and webhook; the RBAC and MFA in the privacy policy describe Ada's own controls.

Sourceada.cx trust center, platform/trust and docs; security.ada.cxread 2026-09-29

The Conversation View gives a complete trace of the steps the AI Agent took in each conversation and the resources it used (Coaching, Knowledge, Actions, Playbooks), with per tool rows showing API response times, a details pane per step and an Automated Resolution assessment per conversation; the Audit log separately records every configuration change with actor, entity and interface, exposed through an Audit Log API and webhook.

Sourcedocs.ada.cx/docs/optimization/conversationsread 2026-09-29

The platform preserves customer identity, context and conversation continuity across channels, returns to the correct Playbook step when earlier information is corrected, and carries context into human handoff, and the docs cover conversation identifiers and persistence. No agent-written cross-conversation memory with scope, lifetime and a review or delete path is documented.

Sourceada.cxread 2026-09-29

The privacy policy states the platform is hosted on AWS in regions including the United States, Canada, Ireland and Germany, and the trust page states the enterprise agreement specifies data residency options, retention schedules and deletion rights; no self host, VPC or on premises deployment is offered.

Sourceada.cx privacy policy and platform/trustread 2026-08-30

Vertical Playbooks ship as a dedicated product surface on their own subdomain (playbooks.ada.cx, linked from the platform page), packaged multi-step SOPs customers adopt into their agent. Verticals named for the Playbooks are ecommerce, financial services, gaming, health insurance, property and casualty insurance, SaaS and travel; the current pages do not confirm which of them ship today.

Sourceplaybooks.ada.cxread 2026-09-29

Work starts when the buyer's own customers arrive on voice, email, chat, messenger, WhatsApp, SMS, Instagram, in-app and custom channels, and the docs add Proactive Outreach for messaging and conversation start events that trigger Playbooks.

Sourceada.cx/platformread 2026-09-29

Ada orchestrates multiple LLMs behind its Reasoning Engine to understand, act and resolve, so several models are in play, but selection and routing are Ada's own and no customer facing model choice is exposed.

Sourceada.cxread 2026-09-29

A public developer reference at docs.ada.cx covers the Conversations API (embed the agent in custom channels), Variables, Tools, Data Export and Audit Log APIs with webhooks, alongside SDKs and Ada's own MCP server with documented getting-started guides for Claude, ChatGPT, Codex, Gemini CLI and Google ADK, an authentication page and a tools list (test cases, test runs, coaching and knowledge search).

Sourcedocs.ada.cx/llms.txtread 2026-09-29

Simulations run a library of up to 1,000 test cases as multi-turn conversations in bulk (up to 3,000 a day) and evaluate the agent's simulated responses against expected outcomes the customer defines, for regression testing, compliance audits and deployment readiness, alongside Interactive Testing and Coaching; test cases and runs are also exposed as tools on Ada's MCP server.

Sourcedocs.ada.cx/docs/optimization/testing/simulationsread 2026-09-29

The agent acts in backend systems through Ada Computer, which despite its name is a tool layer of API tools, code tools and MCP tools rather than operation of a browser or desktop; no browser control or computer use capability is documented.

Sourceada.cx/platformread 2026-09-29