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 astronomers

Telescope Time Allocation Tracking Agent

Every awarded program is tracked to completion, and at-risk programs are raised with the observatory early enough to matter.

Telescope Time Allocation Tracking Agent: what goes in, what the agent does and what you get

What it does

Three awarded programs on three telescopes means three portals, a pile of allocation letters and an unclear picture of what is actually done. This agent reads the allocation letters and queue status pages and builds one tracker. For each program it compares what was observed to the planned targets and constraints, such as seeing, moon phase and cadence, and calculates how much time is left before the semester ends. It flags programs at risk of not finishing and drafts update requests to the support staff, for example asking to raise a target's priority. After each reply it rechecks the queue. You approve every request before it goes out. Edge case: a target observed under worse conditions than required is not counted as complete.

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, continueApprovedYes, continueNoNo 1 STARTS WHEN Weekly run or new observatory email 2 USES A TOOL Read allocation letters, queue pages and deliverynotices 3 DOES Match executed observations to the planned targets 4 CHECKS THE RESULT Did each executed observation meet its constraints? If not: mark it incomplete and add it back to theremaining list. Back to step 3. 5 DOES Calculate remaining time and observing windows foreach program 6 DOES Flag programs at risk of not finishing 7 DOES Draft update requests to support staff for flaggedtargets 8 YOU APPROVE Astronomer approves each request 9 USES A TOOL Recheck the queue after replies 10 CHECKS THE RESULT Did the risk drop after the request? If not: draft an escalation or suggest relaxing aconstraint for the astronomer to consider. Back to step5. 11 RESULT Program status table and next actions
Read the steps as a list
  1. Weekly run or new observatory email
  2. Read allocation letters, queue pages and delivery notices
  3. Match executed observations to the planned targets
  4. Did each executed observation meet its constraints?If not: mark it incomplete and add it back to the remaining list. Back to step 3.
  5. Calculate remaining time and observing windows for each program
  6. Flag programs at risk of not finishing
  7. Draft update requests to support staff for flagged targets
  8. Astronomer approves each requestThe agent waits here for your OK.
  9. Recheck the queue after replies
  10. Did the risk drop after the request?If not: draft an escalation or suggest relaxing a constraint for the astronomer to consider. Back to step 5.
  11. Program status table and next actions

How it decides

A target counts as done only if its executed observation met the stated constraints. A program is at risk when remaining targets cannot fit in the remaining windows.

  • Remaining windows cover less than the remaining time needed: mark at risk
  • Seeing worse than the program limit: observation is not complete
  • Less than 30 days to semester end with targets left: draft an urgent request
  • Data delivered but not downloaded: remind the astronomer to fetch it

Make it yours

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

  • Programs and telescopes tracked
  • Risk threshold in days to semester end (default 30)
  • Constraint rules per program
  • Run day
  • Request tone

What keeps you in control

It always asks you first

  • Every request sent to observatory staff
  • Any relaxation of a constraint

Hard limits

  • Never send a request to observatory staff without approval
  • Never mark a target complete if constraints were missed

It stops when

  • Done: all programs complete or accepted as incomplete
  • Stop: semester ended

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 happensProgram P2 had 12 targets and 18 hours. By 1 November, 7 targets were observed, but two had seeing at 1.4 arcseconds against a 1.0 limit. The check failed and the agent moved them back to remaining. With 5 targets and 7 hours left, it flagged a risk and drafted a request to raise priority. The astronomer approved, and a week later two were queued.

More agents for astronomers