The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Urgent care antibiotics: AI decision support that drafts stewardship plans
In urgent care, the hard part of a viral URI visit often isn't the diagnosis — it's the antibiotic conversation when a patient expects a prescription. Here's how I'd solve it with AI: stewardship decision support in the visit that applies guideline criteria and drafts a no-antibiotic or delayed-prescription plan for the clinician to approve.
In one JAMA Internal Medicine analysis of 2014 claims, 45.7% of urgent care visits for antibiotic-inappropriate respiratory diagnoses received antibiotics, vs 24.6% in EDs: https://pubmed.ncbi.nlm.nih.gov/30014128/
How I'd set it up:
1. During the visit, the tool pulls symptom duration, Centor/McIsaac items, and any rapid strep or flu results already in the chart.
2. It scores the case against guideline criteria and suggests a no-antibiotic plan, a delayed prescription, or "consider antibiotics — clinician review."
3. It drafts a plain-language patient explanation and a follow-up text if symptoms worsen.
4. The urgent care clinician reviews the suggestion, edits the wording, and decides whether to prescribe. Nothing is ordered or sent without that approval.
5. Approvals, overrides, and follow-up replies are logged for audit.
It doesn't diagnose or prescribe. Red-flag symptoms use fixed rules that escalate to the clinician.
PHI stays in your environment, any vendor that touches it signs a BAA, and every suggestion is logged.
What's the hardest patient conversation about antibiotics in urgent care?
More at huzaifatahir.dev
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
Clients often start with the same request: "Let's build an AI agent."
My counter-question is always: which manual process actually costs you time, errors, or money right now?
My selection rule: remove it first. If it can't be removed, simplify it. If it's still needed, automate it with a plain script. Only then add an integration or an agent. Often the best result is the process that no longer exists.
Safe automation means real scenarios, error handling, and alerts. Without alerts, a workflow can silently lose data for weeks. I always define what stays with a human and what goes to the system.
Question for you: which process would you automate first, and why is it still manual?
Service for audit and implementation: https://contra.com/s/BmWLbgFU-ai-automation-from-your-dream-to-working-implementation?r=auto_booster
AI-Powered Physiotherapy Clinic Dashboard | Smart Appointment Scheduling
A modern AI-powered dashboard concept designed for physiotherapy clinics to simplify appointment scheduling, therapist management, and daily operations. The interface focuses on improving workflow efficiency with an intuitive calendar, smart booking experience, patient scheduling, and a clean visual system.
The design features an elegant and minimal UI, helping healthcare professionals manage appointments, therapists, and patient availability with ease. Every screen is crafted to deliver a fast, accessible, and user-friendly experience while maintaining a premium SaaS aesthetic.
so nice work
I’ve been working on a small skill called Manual Orchestrator to make longer projects with AI agents easier to manage.
The problem started with a familiar situation: one chat would accumulate plans, implementation details, corrections, and test results. By the time I was ready for the next phase, I wanted a fresh conversation without losing the decisions we’d already made.
Manual Orchestrator gives that process some structure. One chat acts as the orchestrator: it breaks the work into stages and writes a prompt for the next one. I run that prompt in a new session, then bring the result back. The orchestrator reviews it against the stage’s criteria before preparing the next prompt. If something needs fixing, I go back to the same worker session.
The skill also keeps a record in the project with the current stage, decisions, evidence, and next steps. That makes it easier to pause, resume, or hand the work to another session.
The handoff is manual. I choose when to open a session and carry the result back. The orchestrator and worker sessions can also use different agent CLIs, with the prompt adapted to the capabilities available.
It’s open source and still a work in progress. I’m using it to learn what helps in practice and where the workflow needs to improve. Installation has been checked for Codex, Claude Code, and Gemini CLI, but the full workflow hasn’t been tested across every CLI or version.
If you try it, I’d be interested in hearing what works and where it gets in your way.
