Ada vs Lorikeet (2026)

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 found by connecting any server by URL. Named integrations include Salesforce, Zendesk, ServiceNow, Genesys, Amazon Connect, Twilio Flex, Freshworks and Aircall, with handoff integrations into those contact center stacks.

Sourceada.cx/platformread 2026-09-29

Connectors cover ticketing and messaging (Zendesk, Zendesk Messaging, Front, Help Scout, Slack), CRM (Salesforce, including running workflows inside it) and revenue tooling. Tools are set up as APIs or webhooks, so the agent reads data and takes actions in any internal system, scoped least-privilege with short-lived single-operation tokens and HMAC-signed inbound webhooks.

Sourcelorikeetcx.ai/integrationsread 2026-09-05

Playbooks let the agent follow multi-step SOPs using real-time data, breaking complex journeys into focused steps. The agent answers off-script questions from approved knowledge, returns to the right step, and moves 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

The agent runs multi-step work by following the customer's own standard operating procedures without improvising, whether a three-step form or a forty-step refund flow. Workflow steps include workflow matching, ticket triage, gather, get status, choice and route based on problem, with tool calls such as retrieving recent transactions shown inline. Lorikeet describes specialized agents working together in real time across channels to deliver end-to-end resolutions, and the login surface is a workflows console.

Sourcelorikeetcx.airead 2026-09-05

Work starts when a company's customers arrive on voice, email, chat, messenger, WhatsApp, SMS, Instagram, in-app and custom channels. Ada also offers Proactive Outreach for messaging, and conversation start events trigger Playbooks.

Sourceada.cx/platformread 2026-09-29

Five channels run on one engine, phone, SMS, chat, email and WhatsApp, with an SDK as a further delivery surface, and specialized agents work together in real time across chat, email, voice and SMS to deliver end-to-end resolutions. Voice runs at sub-second latency on the same engine, so a customer who starts in chat does not repeat themselves on a call, and every channel inherits the same guardrails and logging.

Sourcelorikeetcx.airead 2026-09-05

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

The agent is grounded in the customer's own documented procedures, not retrieval alone. Lorikeet follows the customer's SOPs, taps into its systems and handles its highest-stakes workflows, and says its architecture goes beyond retrieval-augmented generation by following the procedures themselves, so the agent neither just retrieves nor invents process. Help centers, reference materials and internal tools supply the surrounding material, and the customer writes and owns the procedures.

Sourcelorikeetcx.airead 2026-09-05

The platform keeps customer identity, context and conversation continuity across channels, returns to the correct Playbook step when earlier information is corrected, and carries context into a human handoff. Conversation identifiers and persistence are supported. The agent does not write its own memory across conversations with a scope, lifetime and a way to review or delete it.

Sourceada.cxread 2026-09-29

Customer memory keeps context across every touchpoint, so a customer who starts in chat does not repeat themselves on a call, because the channels run on one engine and persistence spans channels. No scope, lifetime, retention window or deletion control for that memory is described.

Sourcelorikeetcx.airead 2026-09-05

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, and act in the customer's systems under the customer's controls. Conversations hand off to human agents with context. There is no step where a person approves an agent action before it runs.

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

Runtime guardrails detect sensitive topics and escalate to the customer's team before the agent proceeds, and outbound checks block the agent from disclosing withheld fields or acting outside policy, independently of the model. Tools are scoped least-privilege, dangerous actions need per-user elevation, and the integration is red-teamed against prompt injection and scope escalation before go-live. People write the procedures the agent follows, and handoffs arrive with the investigation complete.

Sourcelorikeetcx.ai/product/trustread 2026-09-05

The trust center at security.ada.cx publishes SOC 2 Type 2 and SOC 3 reports with named observation periods, plus HIPAA. Ada also holds AIUC 1 certification, with independent penetration testing at the infrastructure and AI model layers, and has zero data retention with LLM providers. Customers get 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 named in the privacy policy are Ada's own internal controls.

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

Lorikeet holds SOC 2 Type II, ISO 27001:2022, HIPAA and GDPR, all independently verified and published on a public Vanta trust center at trust.lorikeetcx.ai with reports downloadable under NDA and refreshed annually, and it signs BAAs for healthcare customers. Controls include automatic PII redaction, minimum-necessary PHI handling, TLS 1.3 in transit and AES-256 at rest, no public internet access to production, row-level-security tenant isolation, SSO with hardware-key MFA, and third-party penetration testing.

Sourcelorikeetcx.ai/product/trustread 2026-09-05

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). Rows for each tool show API response times, each step has a details pane, and each conversation gets an Automated Resolution assessment. 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

Every customer interaction, model choice and action is tracked and fully explainable, not a black box. Every tool call, elevation request and reasoning step is logged with timestamps and can be replayed for a regulator examination, and Coach scores the quality of every conversation, human or AI.

Sourcelorikeetcx.ai/product/trustread 2026-09-05

The platform is hosted on AWS in regions including the United States, Canada, Ireland and Germany, and the enterprise agreement sets 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

Production runs on Google Cloud Platform in a private VPC with no public internet access and row-level-security tenant isolation, with US primary hosting and data storage residency available in Australia or the EU. Lorikeet's marketing articles name the US, Australia and the UK, while its trust page lists Australia and the EU.

Sourcelorikeetcx.ai/product/trustread 2026-09-05

Vertical Playbooks ship as a dedicated product on their own subdomain, playbooks.ada.cx, as packaged multi-step SOPs that customers adopt into their agent. The named verticals are ecommerce, financial services, gaming, health insurance, property and casualty insurance, SaaS and travel, though which of them ship today is not confirmed.

Sourceplaybooks.ada.cxread 2026-09-29

Each customer's configuration is written from its own standard operating procedures, by design. Lorikeet's test is that if you can explain to a human agent how to resolve a ticket, the agent can handle it, so time to value depends on the customer's procedure documentation. There is no template library, prebuilt agent catalog or marketplace, and the specialized agents in the Team of Agents architecture work together internally and are not assets a customer browses and adopts. Lorikeet also runs a separate site at lorikeet.tools, branded Toolshed, whose contents are not described.

Sourcelorikeetcx.airead 2026-09-05

Ada orchestrates multiple LLMs behind its Reasoning Engine to understand, act and resolve, so several models are in play. Ada handles selection and routing itself, and customers cannot choose a model.

Sourceada.cxread 2026-09-29

OpenAI, Anthropic and Baseten are among the core subprocessors, so several model providers are in play, all under zero-data-retention agreements with no fine-tuning on customer data, and Lorikeet routes between providers by task. The routing is Lorikeet's own and model choice is tracked, not made by the customer, with no customer-facing selection or bring-your-own-model control.

Sourcelorikeetcx.ai/product/trustread 2026-09-05

Developers get a public reference at docs.ada.cx for the Conversations API, which embeds the agent in custom channels, and for the Variables, Tools, Data Export and Audit Log APIs with webhooks. SDKs sit alongside, as does Ada's own MCP server, with getting-started guides for Claude, ChatGPT, Codex, Gemini CLI and Google ADK, an authentication guide and a tools list covering test cases, test runs, coaching and knowledge search.

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

A developer documentation site at docs.lorikeetcx.ai covers a quickstart and API reference, and integrations use scoped Bearer-credential access and HMAC-signed inbound webhooks that the customer's systems call. Lorikeet also publishes public HTTP endpoints that outside AI assistants can call to query its support agent and book demos. The documentation sits behind a customer access code, so the platform API and its scope are open only to customers, and no SDK is advertised.

Sourcedocs.lorikeetcx.ai/guides/quickstartread 2026-09-05

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. They serve 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

Testing covers both sides of go-live. Before launch, a pre-go-live simulation suite lets a security or compliance team validate agent behavior before unsupervised resolution begins. After launch, Coach reviews every ticket, not a sample, whether handled by people, AI or both, shows why performance is trending up or down, proposes fixes and, with approval, implements them, with automated quality assurance, thematic analysis, segmentation and export. Coach is sold to Lorikeet customers and standalone, is metered per ticket and is generally available.

Sourcelorikeetcx.airead 2026-09-05

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, not a way to operate a browser or desktop. Browser control and computer use are not described.

Sourceada.cx/platformread 2026-09-29

Work happens programmatically inside the customer's systems through controlled integrations, tapping into Zendesk, Stripe and internal APIs, with tool calls such as retrieving recent transactions shown as named workflow steps. No browser control, hosted session or computer use is described. Lorikeet's public HTTP endpoints let outside AI assistants call Lorikeet and do not operate any interface.

Sourcelorikeetcx.airead 2026-09-05