AI audit trail
An AI audit trail is a complete, human-readable log of every decision an AI system makes during a customer interaction — what information it accessed, what reasoning it applied, what actions it took, and why. In regulated industries like financial services, healthcare, and insurance, audit trails are not optional: they're a compliance requirement.
Traditional customer service channels produce audit trails naturally. A human agent's actions are logged in the ticketing system, their notes explain their reasoning, and their conversation is recorded. When AI handles conversations autonomously, that same level of traceability needs to exist — arguably more so, because AI decisions happen faster and at higher volume.
A robust AI audit trail should include:
Decision reasoning: Not just what the AI did, but why — which policies it applied, how it interpreted the customer's request, what alternatives it considered
Data accessed: Which customer records, knowledge articles, and system data informed the decision
Actions taken: Every backend action (refund issued, account updated, ticket escalated) with timestamps
Confidence signals: Where the AI was certain vs. where it was uncertain and how it handled ambiguity
This matters beyond compliance. Audit trails are how CX teams debug issues, improve AI performance, and build trust with internal stakeholders. Without them, AI is a black box — the team knows what happened but not why, making it impossible to improve systematically.
Organizations evaluating AI for customer service should treat audit trail depth as a primary evaluation criterion, not a checkbox.
Related terms: AI compliance, AI guardrails, AI observability, quality assurance in customer service
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.