Agentic Index
Heidi vs Nabla (2026)
Heidi and Nabla are both ambient scribes that write back into the major EHRs, and both are Full on their API, deployment and security. That verdict is the Agentic Index coverage score, graded from each vendor's own published materials.
Heidi leads the grid, 9 of 14 against 7.5. Heidi is self serve with a free tier, scribes in 110 languages, answers clinical questions with citations through Heidi Evidence, and runs Heidi Comms agents for patient calls and messages. Nabla sells through sales, adds dictation and coding, and writes notes, vitals and diagnoses into Epic, athenahealth, Oracle Health, NextGen, Greenway and more, with US or EU hosting. On the grid Heidi is Full on its audit trail and triggers and Partial on memory, where Nabla is Partial, Partial and None. Choose Heidi to start free with patient communications included; choose Nabla for a sales led rollout across a wide range of EHRs.
On the Agentic Index healthcare agent ranking, neither Heidi nor Nabla clears the bar, which asks for all five chart loop capabilities documented in full. Heidi does not document knowledge grounding and RAG in full; Nabla does not document knowledge grounding and RAG in full, nor observability and auditability. 4 of the 69 vendors in the lane clear it. See the healthcare agent ranking
This comparison is published by Agentic Index, an independent agentic AI vendor research platform. Heidi and Nabla are each graded against the same 14 capability Agentic Index taxonomy, from the vendor's own public materials under the Agentic Index verification standard, alongside 955 researched vendors. No vendor pays for placement and no vendor has reviewed this page. How this evidence is graded
Choose Heidi if
- You want to start free and scale up through self serve plans.
- Patient calls and messages should be answered around the clock by agents.
- Clinicians want cited answers to clinical questions in the same product.
Choose Nabla if
- Your organization runs NextGen, Greenway or another EHR beyond the largest three.
- Coding and dictation should sit beside the ambient note.
- You prefer an enterprise contract through sales.
| Feature | H Heidi |
N Nabla |
|---|---|---|
| Action & orchestration | ||
|
Integrations & Tool Calling Ability to connect agents to real systems through native integrations, OAuth-authenticated actions, custom tools, APIs, webhooks, or MCP-compatible tools. |
||
|
HeidiIntegrations & Tool Calling Heidi writes back to the chart through named EHR integrations. In Epic it offers structured writeback and clinical task automation across Hyperspace, Hyperdrive and Haiku, in Oracle Cerner it writes back to MPage components in PowerChart and FirstNet, and with athenahealth it syncs schedules and pushes to chart. Altera, AlayaCare, eClinicalWorks, Veradigm and others are also named, along with Availity eligibility checks and Google and Microsoft 365 tools. Full EHR access sits on the Practice plan. Sourceheidihealth.com/en-us/integrationsread 2026-09-28 |
||
|
NablaIntegrations & Tool Calling Patient history and clinical context are retrieved from the EHR, and Nabla writes back to it. Structured notes export into EHR templates, and vital signs, diagnoses and patient instructions are embedded into charts, flowsheets and clinical fields. This works with Epic, athenahealth, Oracle Health, NextGen, Greenway, Arya and ten more EHRs, plus Nabla Connect as an iFrame inside the EHR. Altera Digital Health is also supported. Nabla Connect goes live in days with little engineering, and Nabla runs in 130+ health organizations. SourceNabla, nabla.com/ehr and nabla.comread 2026-10-05 |
||
|
Workflow Orchestration Ability to sequence, branch, retry, route, and combine deterministic workflow nodes with autonomous agent steps. |
||
|
HeidiWorkflow Orchestration Scribe, Evidence and the Comms agents are separate products, each running its own fixed flow. Agent and Routine automation come under a monthly usage allocation, but Heidi does not say how routines are built or chained. Sourceheidihealth.com/pricingread 2026-09-28 |
||
|
NablaWorkflow Orchestration Ambient notes, dictation and coding run as fixed function products from capture to EHR export. The customer configures no flow, and Nabla names no multiple agents. A generated note can be edited by giving it instructions. SourceNabla, nabla.com and docs.nabla.com llms.txt indexread 2026-10-05 |
||
|
Triggers & Channel Coverage How agents wake up and where they work: schedules, webhooks, message events, CRM events, inbox events, chat, email, voice, and collaboration tools. |
||
|
HeidiTriggers & Channel Coverage Heidi Comms agents answer inbound patient calls and messages 24/7 and run outbound reminders and follow-ups by phone and SMS, and athenahealth schedules sync automatically. Sourcesupport.heidihealth.com/en/articles/13396153-heidi-commsread 2026-09-28 |
||
|
NablaTriggers & Channel Coverage Capture and dictation are started by the clinician inside the EHR or the Nabla app, and Nabla does not say that anything starts them automatically from an event or a schedule. The Connect API creates encounters and their URLs for the EHR, and webhooks report events back to the customer's systems. SourceNabla, nabla.com and docs.nabla.com llms.txt indexread 2026-10-05 |
||
| Knowledge & context | ||
|
Knowledge Grounding & RAG Ability to ground agent behavior in company data through document ingestion, retrieval, external knowledge APIs, semantic search, or RAG layers. |
||
|
HeidiKnowledge Grounding & RAG Heidi Evidence answers from journals and literature (Wiley, Cochrane, BMJ, NEJM), and patient context comes from the EHR list or a pasted copy per session. Evidence draws on sources Heidi curates and does not retrieve from the customer's own knowledge. Sourceheidihealth.comread 2026-09-28 |
||
|
NablaKnowledge Grounding & RAG Notes draw on patient history and clinical context retrieved from the EHR, and coding suggestions are grounded in the encounter, available EHR context and AMA guidelines. This context is assembled for each encounter, and Nabla names no retrieval structure it maintains. The Core API also extracts ICD-10 and LOINC codes into a FHIR compliant structure. SourceNabla, nabla.com/coding and docs.nabla.com llms.txt indexread 2026-10-05 |
||
|
Memory & State Persistence Ability to persist context across a run, conversation, workflow, user, team, or longer-term memory layer. |
||
|
HeidiMemory & State Persistence Per clinician stores carry across sessions. They hold a word library, pinned and customized templates, and note insights that group the corrections a clinician keeps making. Heidi states no lifetime or deletion path, and auto-edit rules are settings applied as rules. Sourceheidihealth.comread 2026-09-28 |
||
|
NablaMemory & State Persistence Custom instructions saved on a note template and personal dot phrases are written by the clinician and applied by the product on each note. Nabla names no memory layer and no learning of a clinician's style. The API also manages dot phrases and custom dictionary entries, and by default Nabla stores no audio. SourceNabla, docs.nabla.com llms.txt index and trust.nabla.com; help.nabla.com/en/articles/922050read 2026-10-05 |
||
| Control & trust | ||
|
Human Oversight & Guardrails Approval steps, consent checkpoints, escalation rules, structured guardrails, policy constraints, and pause/resume controls. |
||
|
HeidiHuman Oversight & Guardrails Nothing goes to the patient until the clinician has read the recap and approved it, and the Comms agent transfers the call to the reception team as soon as a patient asks for a human. Sourceheidihealth.comread 2026-09-28 |
||
|
NablaHuman Oversight & Guardrails Coding keeps every final decision in the clinician's hands. Each suggestion arrives with its rationale and is confirmed by the clinician before it is finalized in the record. Nabla shows the reasoning behind each code, tied to the documented clinical evidence. SourceNabla, nabla.com/codingread 2026-10-05 |
||
|
Security, Identity & Governance RBAC, SSO, auditability, encryption, least-privilege tool access, compliance posture, and data handling policy. |
||
|
HeidiSecurity, Identity & Governance Heidi lists SOC 2 Type II, ISO 27001, ISO 42001, HIPAA, GDPR, Cyber Essentials Plus and UK Class I medical device status, with SSO available and team features on the Practice plan. The reports themselves are requested through Heidi's trust center. Sourceheidihealth.comread 2026-09-28 |
||
|
NablaSecurity, Identity & Governance Compliance covers SOC 2 Type II, ISO/IEC 27001, HIPAA, GDPR, Texas RAMP Level 2 and CIS Level 2, and note retention is configurable. An Admin Portal lets customer administrators add and delete users. Data is encrypted with TLS 1.2 or higher in transit and AES256 at rest. Nabla also claims compliance with CCPA, PIPEDA, NIST standards and the EU AI Act. It names no single sign on and no user roles. SourceNabla, trust.nabla.comread 2026-10-05 |
||
|
Observability & Auditability Traces, logs, execution histories, metrics, audit events, and debugging detail for production agent behavior. |
||
|
HeidiObservability & Auditability Every Comms interaction is logged with its transcript and outcome, and every call keeps a full transcript and recording for review. Scribe sessions have no comparable action record. Sourcesupport.heidihealth.com/en/articles/13396153-heidi-commsread 2026-09-28 |
||
|
NablaObservability & Auditability Each coding suggestion shows its reasoning, with the rationale tied to the clinical record. Webhooks from the Connect and Core APIs report events to the customer's systems. Nabla does not mention an audit log or a lasting record of what the scribe read and wrote. SourceNabla, nabla.com/coding and docs.nabla.com llms.txt indexread 2026-10-05 |
||
|
Deployment & Data Residency Deployment modes and options, including SaaS, dedicated cloud, VPC, on-prem, hybrid, local runtime, and self-hosting. |
||
|
HeidiDeployment & Data Residency Regions are mapped for AU, US, EU, CA and UK, and custom hosting is offered on Enterprise. Heidi does not say how a customer's region gets assigned. Sourceheidihealth.com/developers/additional-resources/region-mappingread 2026-09-28 |
||
|
NablaDeployment & Data Residency Data is hosted on Google Cloud in the US Central region for US clients and in Belgium for non US clients, with speech to text on Azure in US regions and note retention configurable by region. The region follows the client's geography. Nabla does not say whether a customer can pick a different one. Clinical notes are kept 14 days by default, a period each client can change for its region, and audio is not stored by default. SourceNabla, trust.nabla.comread 2026-10-05 |
||
| Solution readiness | ||
|
Prebuilt Agents, Templates & Packs Ready-made workflows, packaged employees, templates, blueprints, industry solutions, and role-specific agents that reduce time-to-value. |
||
|
HeidiPrebuilt Agents, Templates & Packs Standard and advanced templates, template customization and team template sharing on Practice give clinicians ready note formats, and Scribe, Evidence and Comms are separate products. The templates are note formats the clinician uses and shares, not adoptable agents, and there is no agent catalog. Sourcesupport.heidihealth.com/en/articles/8885030-heidi-s-pricing-plans-cost-and-featuresread 2026-09-28 |
||
|
NablaPrebuilt Agents, Templates & Packs Customizable note templates and published specialty custom instructions for cardiology, psychology, pediatrics, dentistry, surgery and weight management are formats and guidance inside one documentation product. Nabla offers no separate agents or template library to adopt. It sells three products (ambient documentation, dictation and coding), used by 85,000+ clinicians. SourceNabla, nabla.com; help.nabla.com/en/articles/5763202read 2026-10-05 |
||
| Platform extensibility | ||
|
Model Flexibility & Routing Ability to work across multiple foundation models, route tasks to different models, or let buyers bring their own providers and keys. |
||
|
HeidiModel Flexibility & Routing No model provider is named, and the customer has no model choice or routing. Sourceheidihealth.com/developersread 2026-09-28 |
||
|
NablaModel Flexibility & Routing Speech to text runs on Azure in US regions. Nabla names no language model provider and no way for customers to choose or route models. Dictation is clinical grade speech recognition built into Epic and other major EHRs. SourceNabla, trust.nabla.com and nabla.comread 2026-10-05 |
||
|
APIs, SDKs & MCP Extensibility Composability layer: stable APIs, SDKs, MCP tool consumption/serving, custom tools, and integration into internal systems. |
||
|
HeidiAPIs, SDKs & MCP Extensibility The Heidi API, with public developer documentation, covers sessions with context and coding, transcription, consult and sectional notes, documents, templates, patient profiles and Ask Heidi. A Heidi Widget comes with an SDK, plus a beta Usage API. The API and Widget are closed to new integrations in Australia and New Zealand. Sourceheidihealth.com/developersread 2026-09-28 |
||
|
NablaAPIs, SDKs & MCP Extensibility Developers building on Nabla's platform get public API documentation at docs.nabla.com. The Core API transcribes audio, generates notes and patient instructions, extracts ICD-10 and LOINC codes as FHIR and supports dictation, dot phrases and custom dictionaries. The Connect API creates encounters, provisions users and sends event callbacks, with OAuth 2.0 client assertions for backends and dated API versions. SourceNabla, docs.nabla.com llms.txt index and nabla.comread 2026-10-05 |
||
|
Testing, Debugging & Optimization Testing, debugging, scoring, retries, fallbacks, quality gates, and optimization loops for improving agent workflows before and after deployment. |
||
|
HeidiTesting, Debugging & Optimization Customers have no evaluation or testing surface for the scribe or Comms agents. Usage and time-saved figures are Heidi's own measurements. Sourceheidihealth.comread 2026-09-28 |
||
|
NablaTesting, Debugging & Optimization Coding quality is checked by regular audits from AAPC certified coders across specialties and by majority vote scoring with ambiguity detection. Nabla runs this quality practice itself and reports 97% or better E/M agreement with expert coders. It names no evaluation or testing surface for customers. SourceNabla, nabla.com/codingread 2026-10-05 |
||
| Specialist automation | ||
|
Browser & Computer Use Browser, desktop, or remote/local computer control for workflows that cannot be handled through stable APIs alone. |
||
|
HeidiBrowser & Computer Use There is no browser or computer control. Heidi reaches EHRs through named integrations, and Heidi Desktop is an app the clinician uses, not an agent operating other software. Sourceheidihealth.com/en-us/integrationsread 2026-09-28 |
||
|
NablaBrowser & Computer Use Nabla embeds in the EHR as an iFrame and exports through integrations. It names no agent that operates a browser or desktop. Dictation runs inside Epic and other major EHRs. SourceNabla, nabla.com/ehr and nabla.comread 2026-10-05 |
||
Pricing snapshot
Sourced from the Index pricing dataset · open each vendor's profile for full detail.
| Pricing | H Heidi |
N Nabla |
|---|---|---|
|
Entry price Lowest public entry point |
Free tier; Clinician $150 per user per month billed annually (July figure, unconfirmed); Practice, team and Enterprise plans | Contact sales |
|
Pricing confidence How public the numbers are |
Public, partial | Contact only |
|
Billing Primary billing axis |
seats (per user per month) | Inference, not stated by the vendor: per clinician. |
|
Variable cost Workload / overage exposure |
Low variable cost | Low variable cost |
|
Free tier / trial Try before you buy |
Free tierTrial
|
No free tier
|
|
Buying motion Self-serve vs sales call |
Mixed | Sales call |
Heidi publishes a free tier and paid plans; Nabla sells through sales with no public price. Confirm current rates in writing.
More comparisons with Heidi or Nabla
Other matchups in healthcare agents
Not the pairing you were after? These compare a different set of healthcare agents on the same 14 capabilities.