Log in Go Pro
Go Pro

Workflow Hub

Share your best AI workflow. We could show it to 2M+ people.

Every day, we feature the community's top-voted AI workflow in The Rundown newsletter.

Coordinate Urgent Veterinary Dental Surgery With ChatGPT

I used ChatGPT as an emergency care coordinator for my dog, Mopsy. My 10-year-old dog developed a dental abscess that caused severe swelling around her eye. An ophthalmologist told us that the pressure was already damaging her eye and had partially torn her retina, so treating the infected tooth quickly became urgent. I started calling veterinary offices myself, but I repeatedly hit the same obstacles: emergency hospitals did not perform dental surgery, specialty dentists were booked, and most primary-care veterinarians required a consultation, bloodwork, and a separate surgical appointment. After more than a dozen calls and over two hours of research and calling, I was overwhelmed and asked ChatGPT to help. ChatGPT researched veterinary practices within an hour’s drive of my house, filtered for clinics that actually performed dental extractions or oral surgery, found their contact information, and sent urgent, individualized emails from my Gmail. The emails explained Mopsy’s situation and asked each practice to call me if they could fit her in for surgery within 48 hours. We ultimately contacted more than 20 practices. At the same time, ChatGPT created a live outreach tracker containing every clinic we had called or emailed, along with phone numbers, email addresses, availability, responses, status, and next steps. I shared it with my husband so we could stay up to date as ChatGPT worked. When veterinary offices replied to my emails, ChatGPT read the responses in Gmail and updated the shared spreadsheet, allowing both of us to see what was happening without duplicating work. In less than half an hour, one veterinarian responded that they could evaluate Mopsy the next morning, run her pre-anesthetic bloodwork on-site, review the results immediately, and take her straight back for surgery if she was cleared. What started as me frantically calling veterinary offices one at a time became an AI-supported search, outreach, and tracking operation. I still made the medical decisions and handled the phone calls that mattered, but I only had to speak with viable options. AI took over the repetitive research, emailing, organization, and response tracking that I did not have the bandwidth to handle during an emergency. Step-by-step: 1. I began calling veterinary offices to find urgent dental surgery for Mopsy. 2. I documented the barriers I encountered, including emergency hospitals without dental surgery, booked specialty dentists, and primary-care veterinarians requiring multiple appointments. 3. I asked ChatGPT to research practices within an hour’s drive that performed dental extractions or oral surgery. 4. ChatGPT gathered each clinic’s contact information and sent individualized urgent emails from my Gmail explaining Mopsy’s condition and asking about surgery within 48 hours. 5. ChatGPT contacted more than 20 practices and created a shared live tracker with each clinic’s contact details, availability, responses, status, and next steps. 6. As replies arrived in Gmail, ChatGPT read them and updated the shared spreadsheet so my husband and I could coordinate without duplicating work. 7. I made the medical decisions and handled phone calls with viable options. One veterinarian ultimately offered an evaluation, on-site bloodwork, and possible same-day surgery the next morning.
Anon Stingray
  • ChatGPT
3

Build an AI orchestration skill with cheaper delegated agents

I made an orchestration skill to help me build faster while using my expensive Astra and Fable tokens carefully. The skill plugs into Astra or Fable and delegates tasks that can happen in parallel to multiple subagents running cheaper models suited to the work. This is especially useful for researching or finding data on the web or on my computer, analyzing code, collecting context, and indexing. The most expensive, newest models focus on maintaining delegation control, doing the difficult reasoning and strategic planning, and judging whether everything is coming together correctly. The cheaper agents handle the lighter-weight work, especially implementing code from the plans. The core idea is simple: the expensive model plans, briefs, and judges; cheaper agents do the reading and building. When I ask Claude or GPT to build the skill, I specify five things: Step-by-step: 1. I define a triage ladder: work can happen inline, with one agent, through a parallel fan-out, or in a multi-stage workflow. I choose the approach based on the task shape and include examples from my domain. 2. I define parallel versus sequential execution based on data dependencies. Independent pieces run in parallel, while anything that needs another piece’s output runs afterward. I never split one change into separate planner, coder, and tester roles. 3. I define model routing with a mandatory model pin: judgment work goes to the mid-tier model, mechanical bulk work goes to the cheap model, and every agent call names its model so nothing silently uses premium billing. 4. I define a brief template and a return-envelope cap. Every delegation includes the goal, inputs, output file path, definition of done, and constraints. Every agent returns a 250-word summary instead of raw files. 5. I define a cost gate with specific numbers. Below N agents, the workflow proceeds automatically; above N agents, it states the estimate and waits for approval.
Nate Grahek
  • ChatGPT
  • Claude Code
1