Complete AI Training
Sign inGet my AI kit

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

AI agent for dietitians

Lab Result Nutrition Trend Agent

Each client's plan reflects the latest labs and results are followed until they improve.

Lab Result Nutrition Trend Agent: what goes in, what the agent does and what you get

What it does

A client's labs change between visits, and the nutrition plan is not always updated to match. When new results arrive, the agent reads them, compares them with prior values and the client's targets, and finds meaningful changes, such as a rising A1C, falling iron or higher potassium. It links each change to the current nutrition plan and drafts adjustments for the dietitian to consider, with a note to the physician where needed. After the plan changes, it waits for the next result and checks whether the value moved as expected. If not, it proposes another step. The dietitian approves every change and note. Edge case: a critical value goes to the dietitian at once with a prompt to contact the physician.

How it works

Follow the arrows from top to bottom. The orange dashed arrow is the loop: when a check fails, the agent goes back and tries again.

Start and resultWhat it doesA check on its own workWaits for your OKGoes back and retries
ApprovedYes, continueNo 1 STARTS WHEN New lab results arrive 2 USES A TOOL Read the new results and prior values 3 DOES Compare each value with targets and trends 4 DOES Flag meaningful changes and critical values 5 DOES Link changes to parts of the current plan 6 DOES Draft plan adjustments and a physician note 7 YOU APPROVE Dietitian approves changes and notes 8 USES A TOOL Save the plan update and send the note 9 USES A TOOL Read the next result when it arrives 10 CHECKS THE RESULT Did the value move toward the target? If not: Review adherence and the plan, propose anotheradjustment or ask the physician to review. Back to step3. 11 RESULT Updated plan and trend
Read the steps as a list
  1. New lab results arrive
  2. Read the new results and prior values
  3. Compare each value with targets and trends
  4. Flag meaningful changes and critical values
  5. Link changes to parts of the current plan
  6. Draft plan adjustments and a physician note
  7. Dietitian approves changes and notesThe agent waits here for your OK.
  8. Save the plan update and send the note
  9. Read the next result when it arrives
  10. Did the value move toward the target?If not: Review adherence and the plan, propose another adjustment or ask the physician to review. Back to step 3.
  11. Updated plan and trend

How it decides

It flags changes by size and direction against targets and links them to plan elements.

  • Critical values go to the dietitian at once
  • A change of more than 10% from baseline is flagged
  • Reassess after the next result
  • No adjustment outside the dietitian's scope

Make it yours

Every agent is a starting point. You choose these settings for your own situation.

  • Target ranges per condition
  • Change threshold
  • Who is notified
  • Recheck timing
  • Note format

What keeps you in control

It always asks you first

  • Dietitian approves plan changes
  • Dietitian approves notes to physicians

Hard limits

  • Never advise on medicines
  • Never change a plan without approval
  • Never ignore a critical value

It stops when

  • Done: values are at target or the plan is reviewed with the physician
  • Stop: the client changes provider

Set it up

We guide you through the set-up, step by step

Members get the full set-up guide for this agent. No technical skills needed: you copy, paste and upload.

10 minto set it up in your AI
5 AIsChatGPT, Claude, Copilot, Gemini, Grok
  • One set of instructions to paste into your AI, with the clicks for ChatGPT, Claude, Microsoft 365 Copilot, Gemini and Grok
  • The agent then walks you through connecting your own data, one source at a time
  • A downloadable copy with the flow chart, the rules and the full guide
Get access to this agent

An example run

What happensA client's A1C rises from 6.8 to 7.6. The agent links it to a plan with 60 g of carbohydrates at breakfast and a new steroid medicine. It proposes lowering breakfast carbohydrates and a note to the physician about the medicine. The dietitian approves. The next result is 7.3, improved but not at target, so the agent proposes an additional snack adjustment.

More agents for dietitians