Feature Requests

Notes contain references/links to the information source
When Heidi generates a note and specific statements or data seem incorrect, it is often helpful to as Heidi something to the extent of "why did you claim that the creatinine increased", "where did you get the information that the patient had a negative ANA", "why did you include melanoma in the past medical history", etc. Sometimes this is due to hallucination/error made by the model and no source can be identified, sometimes this identifies erroneous information accidentally included in the context, sometimes it identifies a legitimate source of the information/statement, and sometimes it has even identified that information from multiple patients was accidentally merged in the transcript. It would be very helpful if the note itself linked back to the source of the information (from transcript, context, etc.) by default for each statement or piece of data. i.e. if I hovered my cursor over a lab value in the investigations section, an 'alt text' would appear stating "Mr Jones Consult.pdf, page 4, line 20" explaining where that value was found. Of if in the HPI there was a statement that "the pain was positional" hovering over it would reveal a pop-up stating "transcript line 103 'it hurts more when I am lying flat'", etc. Any text that Heidi has added to the note that cannot be directly referenced back to the context or transcript could perhaps be coloured red, to identify that this information was generated by Heidi as an inference or speculation and may warrant closer review. Not only would the make it much easier to edit the notes and check reliability afterward, but requiring Heidi to do so would presumably act as a robust final check of the generated note to ensure accuracy.
0
·
Context
Persistent Evidence Library + Structured Templates for Longitudinal Clinical Care
Hi Heidi Team, I would like to request a feature enhancement for Heidi Evidence and workflow management, particularly for counselling and longitudinal care settings. Current challenge: At the moment, Evidence appears to work more session-by-session, requiring clinicians to repeatedly upload or reintroduce context (intake notes, assessments, relevant emails, previous themes, treatment goals, etc.). While prompts/templates help, there is still significant manual effort to maintain consistency and avoid missing relevant context. Requested features: Persistent Client Evidence Library A client-level evidence repository that persists across sessions and can be referenced automatically or selectively by Heidi. Examples of items that could live in the library: * Intake forms and informed consent * Assessment reports (e.g., Strong Interest Inventory, EQ-i, psychometrics, WPI, MBTI, ADHD-related assessments, etc.) * Session summaries and key themes * Treatment/career goals * Clinician notes or important observations * Client emails containing clinically relevant context * Homework or reflections The goal would be for Heidi to reference these over time rather than requiring repeated uploads each session. Structured Templates / Program Guidance The ability to create reusable program templates or clinician prompts that gently guide Heidi’s reasoning and outputs. For example: * Career counselling program structure (session-by-session) * Clinical intake template * ADHD-informed framework * Assessment debrief framework * Reflective questioning style preferences Rather than rigid scripting, this would act as a lightweight “guidance layer” so Heidi stays aligned with the clinician’s preferred structure, tone, and workflow without excessive prompting every time. Team / Supervisor Access (Clinic Model) For group practices: * clinicians maintain primary access to their clients * supervisors/practice owners can access records when clinically appropriate and consented to * continuity is preserved if a clinician leaves the practice * permissions are role-based This would support ethical continuity of care while maintaining appropriate boundaries and oversight. Use case: I work in counselling/career development and increasingly longitudinal care. Heidi is powerful, but the current workflow requires considerable re-contextualizing. A persistent evidence library, along with structured guidance/templates would significantly improve consistency, reduce cognitive load, and enhance continuity across sessions. Thank you for considering this feature request.
2
·
Context
Load More
→