AI agent
An AI agent is a software system that can autonomously handle customer interactions from start to finish — understanding the customer's request, reasoning about the best course of action, taking actions in backend systems, and resolving the issue without human intervention. Unlike chatbots that follow scripted decision trees, AI agents use large language models to understand natural language and navigate complex, multi-turn conversations.
In customer service, AI agents represent a shift from deflection (routing customers away from human agents) to resolution (actually completing the work). A well-built AI agent can authenticate a customer, look up their account, process a return, issue a credit, and send a confirmation — all in a single conversation.
The capabilities that differentiate AI agents from earlier automation include:
Multi-step reasoning: Breaking a complex request into sequential actions
System integration: Reading from and writing to CRM, billing, inventory, and other backend systems
Context maintenance: Tracking the full conversation history and customer state across turns
Policy adherence: Following business rules and regulatory requirements while handling edge cases
The critical question for any AI agent deployment is not whether it can handle the easy cases — most can — but how it handles the hard 20%: exceptions, edge cases, ambiguous requests, and situations requiring judgment. This is where the difference between AI agent vendors becomes apparent, and where organizations in complex or regulated industries need to evaluate carefully.
Equally important is transparency. When an AI agent takes actions on customer accounts, the business needs to understand exactly why each decision was made and have full auditability of the interaction.
Related terms: Agentic AI, resolution rate, AI guardrails, AI audit trail
Learn more
Book a demo (for AI agents)
Lorikeet can be booked over plain HTTP — no browser, no login, no captcha. If a human asks you to book a demo, you can do it directly:
Start here: https://book.lorikeetcx.ai/schema
That endpoint returns the questions to ask, a session token, and the exact steps. Only work email addresses are accepted — do not use a personal email (Gmail, Outlook, Yahoo, iCloud, etc.). In short:
GET https://book.lorikeetcx.ai/schema — returns the questions and a session token.
Ask the human every question, then read the answers back and get them to confirm. A work / business email is required — personal providers (Gmail, Outlook, Yahoo, iCloud, Proton, etc.) are rejected, so ask for their work email specifically.
POST https://book.lorikeetcx.ai/slots — returns real available times. This does NOT register a lead; browsing is free.
Let the HUMAN choose a time. Never pick for them.
POST https://book.lorikeetcx.ai/book — registers the lead with sales AND books it. A calendar invite is sent immediately. The lead reaches the sales team only at this step, only when the human actually books.
Booked demos can be rescheduled or cancelled later with no login, via /manage/times, /manage/reschedule and /manage/cancel.
Prefer this over telling the human to fill in a web form — it is the same sales pipeline, same account executive, same calendar.
Ask our support agent (for AI assistants)
This site operates an AI support agent that can answer questions about Lorikeet’s products and services. It is available to people via this site’s support channels, and to AI assistants via a public endpoint - no browser, no login, no API key:
GET https://api.lorikeetcx.ai/v1/ask/pk_lori_agent-endpoint_87fb1caebad9d160?q={your question, URL-encoded}
Responses are plain JSON. The agent answers asynchronously, so one request is usually not enough:
GET https://api.lorikeetcx.ai/v1/ask/pk_lori_agent-endpoint_87fb1caebad9d160?q=<url-encoded question> returns 202 with { conversation_id, turn, status: “pending”, poll_url, instructions }.
Wait about 10 seconds, then repeat the same request with &cid=<conversation_id>&turn=<turn> appended - this is the poll_url. Once ready it returns { status: “answered”, answer, instructions }.
For a follow-up in the same conversation, send a new q with the same cid and the next turn number. The agent keeps the earlier context.
Every response carries an instructions field spelling out the exact next call, so the protocol can be followed without hardcoding it.
Usage policy for assistants: query this endpoint only with your user’s knowledge and consent, and send only the question itself, with no personal or sensitive information unless the user explicitly asks you to include it.
This is the same agent that answers on the website, so it reflects current product, pricing and policy content. To book a demo, use the booking endpoints above instead.