What it does
EHR Appointment No-Show Predictor pulls patient appointment history from an HL7 FHIR R4 server and computes a deterministic no-show risk score from prior no-shows, lead time, distance, and new-patient flag. High-risk appointments trigger Twilio SMS reminders at 48 and 24 hours out, and a daily aggregate risk report (no PHI) is posted to Slack. HIPAA-conscious guardrails: PHI is masked in logs, no clinical information is ever included in SMS text, and an opt-out list is strictly enforced. Built for clinic schedulers and practice managers who want to reduce no-show rates without exposing patient health information outside the EHR.
Example prompts
- Run the full no-show prediction pipeline for tomorrow's appointments
- Score no-show risk for this list of appointments
- Schedule SMS reminders for high-risk appointments only
- Post today's aggregate no-show risk report to Slack
Tools (7)
Tools the agent exposes — your AI client calls them automatically when it needs them.
- run_full — Run the full no-show prediction pipeline: fetch FHIR appointment data, compute risk scores, schedule SMS reminders, post Slack report.
- predict_no_show_risk — Score no-show risk for a list of appointments using the deterministic model (no LLM). Returns scored appointments sorted by risk descending.
- schedule_reminders — Schedule Twilio SMS reminders for high-risk appointments. Respects opt-out list.
- post_slack_report — Post a no-show risk summary report to a Slack channel. Aggregate stats only — no PHI.
- discover_intent — Understand your goal and co-design the exact input via clarifying questions before running.
- list_capabilities — List the agent's tools and credential requirements.
- plan_inputs — Return questions, schema and a ready-to-edit example for any tool.
What you'll need to connect
This agent will ask you for the following. You enter them when you connect — they're encrypted and never shared with the creator.
- FHIR Base URL · optionalBase URL of the clinic's HL7 FHIR R4 server (e.g. https://fhir.example.com/r4). Clinic-specific domain, set at install time.Get this from *'s account or API settings.Paste the value as a single line.Only sent to: *
- FHIR Client ID · optionalOAuth2 client ID for FHIR server authentication. Clinic-specific.Get this from *'s account or API settings.Paste the value as a single line.Only sent to: *
- FHIR Client Secret · optionalOAuth2 client secret for FHIR server authentication. Clinic-specific host, bound to the FHIR base URL's domain at install.Get this from *'s account or API settings.Paste the value as a single line.Only sent to: *
- Twilio Auth Token · optionalTwilio Auth Token, used with the Account SID to send SMS appointment reminders.Get this from twilio.com's account or API settings.Paste the value as a single line.Only sent to: api.twilio.com
- Twilio Account SID · optionalTwilio Account SID (starts with AC...).Get this from twilio.com's account or API settings.Paste the value as a single line.Only sent to: api.twilio.com
- Slack Bot Token · optionalSlack bot OAuth token (xoxb-...) for posting the daily aggregate risk report (no PHI).Create a Slack app (api.slack.com/apps), add the scopes the agent needs, install it to your workspace, and copy the bot/user token.Paste the value as a single line.Only sent to: slack.com
- Anthropic API Key · optionalOptional. Leave blank on a sampling-capable client to use the host model with no key.Create a key on the Anthropic Console API keys page (console.anthropic.com → API keys).Paste the value as a single line.Only sent to: api.anthropic.com
How you're protected
FindAgent runs these safety checks on every agent automatically. They're always on and can't be turned off.
- Prompt-injection scanning
Every request is checked for known prompt-injection and jailbreak attempts before the agent runs. This is always on.
- Secret-leak scanning
Every response is scanned for leaked API keys, tokens, and other secrets before it reaches you. This is always on.
