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 physicists

Detector Calibration Run Agent

Current, reliable calibration constants

Detector Calibration Run Agent: what goes in, what the agent does and what you get

What it does

Detectors need regular calibration with radioactive sources, pulsers or reference signals, and stale constants quietly bias physics results. This agent books calibration runs in the run plan, on schedule and after any hardware change. It reads the calibration data, fits gain, offset and timing constants per channel, and checks fit quality. It compares the new constants with previous ones and flags drift beyond tolerance, along with patterns such as one readout board drifting together. Poor fits are refit, and if they stay poor, it requests a repeat run with more statistics. It records which physics runs used which constants. You approve new constants before they are loaded into data processing. Edge case: a channel that keeps failing calibration is masked and logged.

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 Calibration due or hardware changed 2 USES A TOOL Book calibration run in the run plan 3 USES A TOOL Read calibration source and pulser data 4 USES A TOOL Fit gain, offset and timing constants per channel 5 CHECKS THE RESULT Are fits good and drift within tolerance? If not: refit bad channels and request a repeat run iffits stay poor. Back to step 3. 6 DOES Compare new constants with the current set and listchanged channels 7 YOU APPROVE Physicist approves constants 8 RESULT Constants loaded with version note
Read the steps as a list
  1. Calibration due or hardware changed
  2. Book calibration run in the run plan
  3. Read calibration source and pulser data
  4. Fit gain, offset and timing constants per channel
  5. Are fits good and drift within tolerance?If not: refit bad channels and request a repeat run if fits stay poor. Back to step 3.
  6. Compare new constants with the current set and list changed channels
  7. Physicist approves constantsThe agent waits here for your OK.
  8. Constants loaded with version note

How it decides

It accepts constants with good fits and flags changes beyond tolerance.

  • Mask failing channels
  • Flag drift
  • Rerun bad fits

Make it yours

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

  • Tolerance
  • Schedule
  • Channels
  • Report format

What keeps you in control

It always asks you first

  • Loading constants

Hard limits

  • Never loads constants without approval

It stops when

  • Done: loaded
  • Stop: hardware fault

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 happensAfter two front-end boards were replaced on September 22, the agent booked a source run. Fits for 1,018 of 1,024 channels were good. Six channels on the new boards showed gain shifts of 7%, above the 2% tolerance, and poor fits. The agent refit them with a wider peak window, and four passed. It requested a repeat run for the other two, which then passed. The physicist approved the new constants.

More agents for physicists