Human-in-the-loop (HITL)
Human-in-the-loop (HITL) is a system design approach where human oversight is built into an AI workflow — humans review, approve, or override AI decisions at defined points rather than the AI operating fully autonomously. In customer service, HITL ensures that high-stakes or ambiguous situations receive human judgment before actions are taken.
HITL operates on a spectrum:
Full HITL: A human reviews and approves every AI-generated response before it's sent (agent assist model)
Selective HITL: The AI handles routine cases autonomously but flags uncertain or high-risk cases for human review
Oversight HITL: The AI operates autonomously but humans periodically review a sample of interactions for quality assurance
Escalation HITL: The AI handles the conversation until it encounters a situation requiring human judgment, then transfers seamlessly
For most customer service deployments, selective HITL is the practical sweet spot. The AI resolves the straightforward cases (password resets, order tracking, account updates) without human involvement, while complex cases (billing disputes, compliance-sensitive requests, upset customers) are routed to human agents with full context.
The key design decision is where to draw the line. Too much human involvement negates the efficiency benefits of AI; too little creates risk. The best implementations define clear criteria for when HITL triggers: monetary thresholds, compliance categories, customer sentiment scores, or AI confidence levels.
HITL is also the mechanism that enables AI systems to improve over time. When humans review and correct AI decisions, that feedback can be used to refine the AI's behavior — creating a virtuous cycle where the AI gradually handles more cases correctly, reducing the need for human intervention.
Related terms: AI guardrails, escalation rate, automated quality assurance
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.