Oriental Nippon Development
Back to blog
Technology

Human-in-the-Loop AI: Draft, Don't Send

Care schedules, support-session reports, sales outreach, training content: our AI systems propose and draft. A named person decides. Here's why that design wins.

Look across the AI systems we have shipped and one pattern keeps repeating: the model drafts, a person decides.

That is a design choice, not a limitation of the technology. This post explains where we use it, what it costs, and how to make the human step fast enough that people actually do it.

Where the pattern shows up

SystemWhat the AI doesWho decides
Care schedulingProposes shift assignmentsCare coordinator
Disability-support sessionsDrafts report fields from the transcriptPractitioner
Sales researchDrafts personalised outreachSales rep
Learning contentGenerates training materialNamed reviewer
Lead captureFills contact fields from cards and conversationsSales staff, before saving

In care settings, a named person stands behind every record the system drafts.

Why not fully automate?

Because an automated record nobody checked is not an improvement. It is a faster way to be wrong at scale. Automated sending scales the wrong thing, and automated approval scales the error.

In regulated settings like care and healthcare there is a simpler reason too: someone has to be accountable for each record, and that someone has to be a person.

What the human step buys you

  1. Trust. Practitioners adopt tools that respect their judgement. Tools that overrule them get quietly avoided.
  2. Data quality. Every confirmation is a labelled example of what "right" looks like.
  3. Accountability. A named person stands behind each decision.
  4. A safe way to improve. Edit rates show exactly where the model is weak, without customers finding out first.

Making review fast

The human step only works if it is quick. If reviewing takes as long as writing, people stop reviewing.

  • Structured drafts. A form to confirm, not prose to rewrite. In the support-session system, the practitioner checks fields, not paragraphs.
  • Show the evidence. The transcript excerpt, the constraint that was satisfied, the source cited.
  • One action to accept. Confirming a correct draft should be a single click.
  • Edits are cheap. Changing one field should not mean starting over.

What to measure

MetricWhat it tells you
Acceptance rateHow often the draft is confirmed unchanged
Edit rate by fieldWhich parts the model gets wrong
Time to confirmWhether review is actually fast
Rejection reasonsGaps in data, rules or prompts

The time saving is still real

In the disability-support project, paper double handling disappeared entirely: sessions are recorded, transcribed and drafted, and the practitioner confirms. The person stays in charge, and the admin burden still drops.

See it in practice in AI transcription for disability support sessions.

Sources and further reading

  1. People + AI Guidebook, Google PAIR
  2. Guidelines for human-AI interaction, Microsoft HAX Toolkit
  3. AI Risk Management Framework, NIST
  4. Collaborative intelligence: humans and AI are joining forces, Harvard Business Review

Related case study

AI Transcription and Report Drafting for Disability Support Sessions