HealthcareComplex automationSeveral jobs working together: multi-stage pipelines with state, branching on rules or AI decisions, approvals or escalations, 4+ systems, AI agents that act, or reconciliation across sources. Usually rolled out in stages.

Personalized meal plans at triple the scale

For: Dietitian group practice

Typical impact

3x client capacity per dietitian

Client intake data and the practice's clinical guidelines feed an AI engine that drafts personalized weekly meal plans for dietitian approval. Approved plans deliver automatically with shopping lists, and weekly WhatsApp check-ins log weight, adherence, and questions into each client's file.

Typical results

10 min

Plan review & approval

89%

Check-in completion

0

Plans sent unreviewed

Figures reflect typical results for this kind of automation.

The challenge

Every personalized weekly plan took up to two hours to build by hand — swapping recipes around allergies, recalculating macros, formatting the document. Dietitians capped out at about 25 active clients each, follow-up between sessions was a manual WhatsApp scramble, and clients who quietly drifted were only discovered at the next weigh-in.

Before and after

Before With the automation

Time per weekly plan

−92%
120 min
10 min

Active clients per dietitian

3×
25 clients
75 clients

Weekly check-in completion

3×
30%
89%

The automation

We connected the intake forms and each dietitian's clinical guidelines to an OpenAI engine that drafts a personalized weekly plan — meals, macros, and a shopping list — respecting allergies and preferences. Drafts land in an approval queue where the dietitian edits and signs off in minutes; nothing reaches a client unreviewed. Approved plans deliver by WhatsApp, and an automated weekly check-in collects weight, adherence, and questions, logging everything to the client file and flagging anyone drifting.

How it works

  1. 01

    Intake captured

    A structured form collects the new client's goals, restrictions, allergies, and food preferences.

  2. 02

    AI drafts the plan

    OpenAI generates a personalized weekly plan following the practice's clinical guidelines and templates.

  3. 03

    Dietitian approves

    The draft lands in a review queue; the dietitian edits and signs off in minutes — nothing ships unreviewed.

  4. 04

    Plan delivered

    The approved plan reaches the client on WhatsApp, complete with a shopping list.

  5. 05

    Check-ins log progress

    Automated weekly check-ins record weight, adherence, and questions to the client file and flag anyone drifting.

Starts from

  • Client intake data
  • Dietitian guidelines

Delivers

  • Approved weekly plans
  • Weekly WhatsApp check-ins
  • Progress & adherence log

The impact

Plan production dropped from two hours to a ten-minute review, and each dietitian now carries around 75 active clients — triple the previous cap — without new hires. Weekly check-in completion jumped from 30% to 89%, drifting clients get a call within days instead of weeks, and revenue grew with headcount flat.

Questions about this automation

How does the AI draft a meal plan without breaking clinical rules?

The intake form captures goals, allergies, restrictions and food preferences, and the practice's own clinical guidelines and templates are loaded as fixed rules. OpenAI drafts meals, macros and a shopping list inside those limits. Every draft then waits in a review queue, so a dietitian checks and signs off before anything reaches a client.

What do the weekly WhatsApp check-ins collect?

Each week the client receives a short WhatsApp check-in asking for current weight, how closely they followed the plan and any open questions. Answers are written to the client file automatically. When adherence drops or weight trends the wrong way, the client is flagged so the dietitian can call before the next session.

What does a practice need to get started?

The practice needs its intake form, written clinical guidelines and plan templates, a place to keep client files, such as a CRM or Google Sheets, and a WhatsApp Business number. The guidelines become rules the AI must follow. This is a multi-step build, usually rolled out in stages, starting with drafting and approval.

Healthcare

Related automation examples

View all 60 examples

Want this in your business?

We map it to the tools you already use and show you where it saves the most time, in a free 30-minute call.