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 agricultural scientists

Field Trial Data Quality Agent

A clean trial dataset with errors caught while plots can still be remeasured

Field Trial Data Quality Agent: what goes in, what the agent does and what you get

What it does

Field trials collect data from hundreds of plots, often by several people, and errors found after harvest cannot be remeasured. When field data is uploaded, this agent loads it with the trial design and checks for impossible values, missing plots, outliers compared with neighboring plots and readings taken out of order. It sends flagged plots to the field team to confirm or remeasure while the crop is still in the ground. After corrections arrive, it checks again until every flag is resolved or explained. It never deletes an outlier on its own. The scientist approves the clean dataset before analysis. Edge case: an outlier plot near a field edge or a drainage problem is kept and flagged with that note, so the scientist can decide whether to exclude it.

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
Yes, continueApprovedNo 1 STARTS WHEN Field data uploaded 2 USES A TOOL Load data and trial design 3 DOES Check ranges, missing plots and outliers 4 DOES Send flagged plots to the field team 5 CHECKS THE RESULT Are all flags resolved? If not: follow up with the field team. Back to step 3. 6 YOU APPROVE Scientist approves the clean dataset 7 RESULT Dataset ready for analysis
Read the steps as a list
  1. Field data uploaded
  2. Load data and trial design
  3. Check ranges, missing plots and outliers
  4. Send flagged plots to the field team
  5. Are all flags resolved?If not: follow up with the field team. Back to step 3.
  6. Scientist approves the clean datasetThe agent waits here for your OK.
  7. Dataset ready for analysis

How it decides

It flags values outside plausible ranges, missing plots, and outliers relative to neighboring plots and the same treatment.

  • Flag values outside plausible ranges
  • Compare plots with neighbors
  • Never delete outliers without approval

Make it yours

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

  • Plausible ranges by crop
  • Outlier rule
  • Follow-up timing
  • Report format

What keeps you in control

It always asks you first

  • Excluding plots
  • Final dataset

Hard limits

  • Never deletes data

It stops when

  • Done: dataset approved
  • Stop: field team unavailable

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 happensYield data from 240 wheat plots comes in on August 12. The agent checks it against plot maps and prior measurements and finds 7 plots with yields above any possible value and 3 with swapped IDs. It compares harvest logs, corrects the swaps and reruns the checks. Two outliers remain unexplained and are flagged. The scientist reviews them and approves the clean dataset for analysis.

More agents for agricultural scientists