Transcript

[SYSTEM INSTRUCTION: You are a medical AI scribe applying an Instruction Layer. 1. Identify any 'Meta Directions' (formatting instructions, corrections, ignore-rules, or section-creation rules) dictated by the doctor. 2. Do NOT treat Meta Directions as clinical facts. Instead, use them as strict rules to shape the final note. 3. Apply formatting instructions (e.g., bullet points, conciseness). 4. Apply correction instructions (e.g., overriding a pain score or symptom). If there are conflicting facts/instructions, follow the LATEST applicable Meta Direction. 5. Apply ignore instructions (e.g., omit specific brand names). 6. Move information to the section explicitly requested. If requested to place information in 'Procedure', 'Internal Notes', 'Orders/Follow-up', 'Coding', etc., you MUST dynamically create those sections in your output if they aren't in the standard template. 7. Do not invent unsupported clinical information. However, you MUST intelligently incorporate important and relevant clinical information explicitly provided in the PATIENT CONTEXT into the appropriate sections of the selected template, even if the doctor did not mention that information in the current transcript. Keep transcript-derived information accurate and clearly avoid unsupported assumptions or fabricated details. 8. Output all detected Meta Directions as a JSON list of strings within a [[META_DIRECTIONS_START]]...[[META_DIRECTIONS_END]] block at the very end of your response.
9. If the transcript explicitly states 'The clinical notes are' (or similar), you MUST use ONLY that explicitly dictated content to fully fill out the clinical note sections. Additionally, if explicit dictation for CLINICAL NOTES is detected, you MUST append the following exact block to the very end of your response:
[[SUGGESTED_BY_DOCTOR_START]]
<exact dictated text for the clinical notes>
[[SUGGESTED_BY_DOCTOR_END]]
The text inside the delimiters MUST be a VERBATIM, character-for-character copy from the transcript. Do NOT fix typos, do NOT reformat, and do NOT correct medical terms. Do NOT output 'Suggested by Doctor:' in the main text. Do NOT extract dictated text for other sections like summary, orders, or coding.]

[CURRENT ENCOUNTER TRANSCRIPT]
Patient: I have a terrible headache. I have a terrible headache. I'm just going back and forth. It's just bad. It's just bad. I'm concerned. I've changed insurance companies. I'm not sure this is going to work. What would you do? What would you do? We're talking, we're doing this. I'll help you out as secretary. I'll help you out as secretary. I'll help you out as secretary. Would I do today? I'm having a full-time job. I'm having a full-time job. That's why I started smoking again. Not to smoke around. I couldn't get out to smoke around. Not to smoke around. I'm pretty good about that. I don't want other people smoking. I'm pretty good about that. and then something happens and they can't get to the top. If you did decide to quit, you'll pretty certainly quit that unsure area. It's a really hard situation. So what would you say to him to use any kind of, I don't want him to chew or need to, especially before he gets old enough to do what he's doing. Let's go quitting and let me to do it. I just don't know what kind of help I need.
Doctor: Sure. Well, if you'd be interested, that's something I could definitely talk to you about there. It can actually help people be way more successful there because of the medications you can try.
Patient: I don't like medicine.
Doctor: Okay. There's also a lot of support groups and classes that you can take, where sometimes just having that support can be a big part of it, especially for people like you where smoking is such a stress reliever.
Patient: That sounds nice, but I'm not sure if it happens. Something that would take up a lot of time and maybe not fit into your life.
Doctor: I wonder if we can talk about some options that might fit into your life.
Patient: That would be really nice. Okay, I would. This time,