A faster prior authorization still needs an owner
A payer API can move a prior authorization request without assigning the next task. What practices should ask about response ownership and the 2027 CMS requirements.
Thyra Blog
Clinical workflow, endocrinology, and the questions a practice should ask before adopting new software.
Start here
Onboarding, from the physician founder’s perspective.
A founder's experience with a stalled EHR rollout shows how implementation can shift the work of getting a practice ready onto the practice itself.
Read the article →Inbox & clinical workflow
A payer API can move a prior authorization request without assigning the next task. What practices should ask about response ownership and the 2027 CMS requirements.
AI should sort the inbox so the doctor can decide. Here is where we draw the line.
After-hours inbox work is usually unfinished follow-up care, not simple message reading. Fragmented tools, not notification volume, push it into evenings and weekends.
Most healthcare AI platforms still solve only one slice of the workflow. Learn what separates AI scribe tools from full clinical workflow systems that combine documentation, inbox triage, orders, and protocols in shared patient context.
Endocrinology & CGM
A clinical look at RAG-based tools that let clinicians ask natural-language questions across a patient's entire chart, and what separates real longitudinal search from note-search with a chat box.
CGM review still requires three browser tabs in 2026. Why connectivity is not integration, what a single-tab workflow looks like, and how to pilot one without replacing your EHR.
A longitudinal patient record connects information over time with traceable sources. Explore how context supports endocrine chart review and inbox work.
CGM data is abundant. Clinical time is not. A scalable CGM workflow needs automated summaries, trend comparison, and defensible documentation in one screen.
EHR overlay vs replacement
A founder's experience with a stalled EHR rollout shows how implementation can shift the work of getting a practice ready onto the practice itself.
Most EHR pilots track logins and satisfaction. The metrics that actually predict success are follow-up task completion, time to next clinical action, and care plan alignment.
A polished demo does not prove a clinical AI tool will reduce after-hours work or survive compliance review. The 5-category pilot scorecard and the metrics that actually predict success.
EHR onboarding depends on workflow configuration, migration, training, and access. Compare the operational requirements of a focused pilot and a full replacement.
AI safety, compliance & interoperability
The EU's ProtectEU strategy has reignited the encryption backdoor debate. Here is why mandated backdoors are structurally incompatible with HIPAA's Security Rule, and what US clinics should track.
A practical framework for IT admins decommissioning a legacy EHR: how long to keep read-only access, state retention rules, and who stays liable for old-system data requests.
EHR overlay implementation is a phased workflow redesign, not a one-day install. Here is a practical blueprint starting with inbox management, documentation, and fax handling.
RBAC controls who can open a chart. Audit log monitoring catches employees who technically can but shouldn't. Here's what IT admins should require from an EHR vendor.
Founder build log
A clinical inbox is not email. It is a task engine with safety requirements. Here is how to design one that routes, owns, and resolves work deterministically.
44 published articles, organized by topic.
A payer API can move a prior authorization request without assigning the next task. What practices should ask about response ownership and the 2027 CMS requirements.
AI should sort the inbox so the doctor can decide. Here is where we draw the line.
After-hours inbox work is usually unfinished follow-up care, not simple message reading. Fragmented tools, not notification volume, push it into evenings and weekends.
Most healthcare AI platforms still solve only one slice of the workflow. Learn what separates AI scribe tools from full clinical workflow systems that combine documentation, inbox triage, orders, and protocols in shared patient context.
After-hours EHR work persists when follow-up remains manual after the note is finished. Explore inbox classification, context, and clinician-reviewed responses.
Most clinics avoid a dedicated inbox triage role because the barrier is governance, not awareness. Here is why staffing alone does not reduce inbox burden and what operating model works better.
Outpatient EHRs optimized the note. The inbox became the channel for non-visit care, and it lacks a safety-grade triage layer.
Not all AI scribes are equal. A maturity model helps clinics evaluate what they are actually buying and what level of trust it deserves.
A clinical look at RAG-based tools that let clinicians ask natural-language questions across a patient's entire chart, and what separates real longitudinal search from note-search with a chat box.
CGM review still requires three browser tabs in 2026. Why connectivity is not integration, what a single-tab workflow looks like, and how to pilot one without replacing your EHR.
A longitudinal patient record connects information over time with traceable sources. Explore how context supports endocrine chart review and inbox work.
CGM data is abundant. Clinical time is not. A scalable CGM workflow needs automated summaries, trend comparison, and defensible documentation in one screen.
Prior auth is the most hated workflow in healthcare. Automation helps, but only if it addresses the real bottlenecks: data assembly, payer rules, and follow-up tracking.
A founder's experience with a stalled EHR rollout shows how implementation can shift the work of getting a practice ready onto the practice itself.
Most EHR pilots track logins and satisfaction. The metrics that actually predict success are follow-up task completion, time to next clinical action, and care plan alignment.
A polished demo does not prove a clinical AI tool will reduce after-hours work or survive compliance review. The 5-category pilot scorecard and the metrics that actually predict success.
EHR onboarding depends on workflow configuration, migration, training, and access. Compare the operational requirements of a focused pilot and a full replacement.
Compare a focused workflow pilot with a full EHR replacement. Check the data source, permissions, supported connections, and operational requirements before deciding.
AI scribes assist with documentation. An EHR overlay addresses selected workflows alongside an existing system. Compare their scope and confirm supported connections.
How AI-native EHR workflows with Smart Inbox, Smart Search, and SMART on FHIR overlay are transforming endocrinology and primary care. Built by an endocrinologist for specialty and primary care practices.
Data migration is the highest-risk phase of any EHR transition. A structured playbook reduces surprises, protects patient safety, and preserves operational continuity.
The EU's ProtectEU strategy has reignited the encryption backdoor debate. Here is why mandated backdoors are structurally incompatible with HIPAA's Security Rule, and what US clinics should track.
A practical framework for IT admins decommissioning a legacy EHR: how long to keep read-only access, state retention rules, and who stays liable for old-system data requests.
EHR overlay implementation is a phased workflow redesign, not a one-day install. Here is a practical blueprint starting with inbox management, documentation, and fax handling.
RBAC controls who can open a chart. Audit log monitoring catches employees who technically can but shouldn't. Here's what IT admins should require from an EHR vendor.
Ambient AI scribes record patient conversations, which means wiretapping law, not just HIPAA, applies. Here is what consent, notice, and opt-out workflows should look like state by state.
RBAC misconfiguration in shared endocrinology/primary care EHRs causes both HIPAA exposure and clinician friction. Here's how IT admins should structure roles, scopes, and audits.
HTI-1 forces certified EHRs to disclose how predictive AI tools are built, trained, and validated. Here's what it actually requires, and what it doesn't.
AI can draft SOC 2 and ISO 27001 policy language fast, but evidence validation, control testing, and auditor sign-off still require human review. Here's where the line sits.
AI chart audits scan for HCC coding gaps, unsupported diagnoses, and documentation-to-billing mismatches at a scale manual review cannot match. Here is what they actually catch.
TEFCA creates a national framework for nationwide query-based data exchange through QHINs. Here is what it actually requires, what it does not, and how it should factor into EHR vendor selection.
A practical guide for IT admins on what happens to patient audio after ambient AI scribe transcription, including retention windows, model training risk, and the exact contract language to demand.
A practical comparison of open-source data-exchange APIs and commercial FHIR platforms, covering ONC certification support, maintenance burden, and who owns security risk over time.
A decision framework for IT admins weighing a SMART on FHIR overlay against a full EHR replacement, covering time-to-value, data risk, staff disruption, and cost.
A technical breakdown of screen scraping versus FHIR and Direct exchange, why reverse-engineered integrations persist in health IT, and what admins should verify before trusting a vendor's data pipeline.
Data interoperability in an EHR runs on three standards that solve different problems: FHIR for real-time API queries, C-CDA for structured clinical documents, and Direct messaging for secure transport between organizations.
FHIR support is now a baseline claim, not a buying signal. A five-level FHIR maturity model and verified ONC data on what operational EHR interoperability really requires in 2026.
AI safety in healthcare is now a workflow control problem. Here is what healthcare IT leaders should verify in audit logs, approval workflows, and source grounding before deploying an AI EHR.
An EHR contract should be evaluated like an implementation and workflow risk document, not just a software quote. The right checklist focuses on go-live scope, pilot metrics, data rights, exit terms, and what can be proven before a full switch.
AI hallucinations in clinical workflows pose significant patient safety risks. Essential prevention strategies include data grounding, deterministic rules, and audit trails.
FHIR R4 is the API standard that enables modern EHR systems to effectively participate in the health data ecosystem, ensuring interoperability and compliance with ONC requirements.
ONC certification is the gateway to the US healthcare market. Here is what the process actually involves, what it costs, and where new vendors get stuck.
HIPAA compliance is not a checkbox. For cloud-native EHRs, it requires deliberate architecture decisions around encryption, access control, and audit logging.
A clinical inbox is not email. It is a task engine with safety requirements. Here is how to design one that routes, owns, and resolves work deterministically.
Keep exploring