Skill UI

This tool collects comprehensive, HIPAA-safe diagnostic data for Abridge support and troubleshooting. It gathers environment variables, connectivity status to Abridge APIs and FHIR servers, recent error logs, and session diagnostics. Essential for filing support tickets or escalating issues to engineering teams.

This workflow establishes a comprehensive local environment for developing and testing clinical AI integrations. It simulates an Electronic Health Record (EHR) using a local HAPI FHIR server and utilizes synthetic patient data. Developers can iterate on complex encounter workflows and API connections safely, without ever using real Protected Health Information (PHI).

Provides structured methods and code examples to optimize Abridge's clinical AI integration for high-volume, enterprise deployments. Focuses on reducing critical latencies across the entire workflow, including audio streaming throughput, note generation pipelines, and secure FHIR push operations, ensuring scalability for large health systems.

This guide demonstrates best practices for implementing robust API rate limiting, backoff strategies, and session throttling patterns. It provides solutions for handling common API quota issues, such as 429 errors, and managing high volumes of concurrent encounters. It is essential for building stable, high-throughput systems in SaaS and healthcare environments.

A comprehensive guide detailing procedures for upgrading Abridge API versions and migrating between disparate Electronic Health Record (EHR) systems. It covers zero-downtime API versioning strategies (e.g., canary rollout) and outlines high-risk, multi-step procedures for ensuring seamless clinical documentation data continuity during EHR cutovers.

This module provides robust webhook handling for Abridge, managing critical clinical documentation lifecycle events. It ingests events such as note completion, encounter status changes, signing, and quality alerts. By implementing signature verification and idempotency checks, this system ensures reliable, secure integration of clinical data into external platforms like EHRs.

This skill ensures AI models generate complete, unabridged code and files without placeholders, TODOs, or skipped sections. It enforces strict completeness for deliverables like full implementations or exhaustive lists. It prevents shortcuts like '...' or descriptions instead of code, ensuring every requested item is fully realized within token limits.