Protect Patient Data
Learn what can and cannot go into an LLM. Use the PHI safety checker to build good habits from day one.
Actively maintained field guide
SLP + LLM
Field Guide
A free clinical knowledge resource for speech-language pathologists who use LLMs in their clinical writing — and want to get better at reading what comes back.
I How do I use LLMs well in my clinical writing?
O How do I tell when LLM writing is meeting the client — and when it isn't?
I/O = input/output. In computing, how a system receives and sends information. In SLP, what we study every day: how people take in language and produce it. This guide covers both directions — writing the input, reading the output.
New here?
Start Here
This isn't about learning to use LLMs. It's about articulating what you already know (your clinical expertise) clearly enough that any tool can work with it.
See It In Action
Interactive Demo
Watch how a well-crafted prompt produces clinically useful output. These are pre-generated examples: no API calls, no data sent anywhere.
Clinician
AI Response requires clinical review
Explore
Find What You Need
Enter from any angle. The guide is organized around four questions: What do I need to know? What am I trying to do? Where do I work? Did I do it right?
Learn
Foundations
Core principles, PHI safety, how LLMs work, prompt patterns, evidence base, ethical decision trees, and model comparison.
8 guidesGlossary
Every term defined from both sides, clinical and technical. SLPs and developers finally speaking the same language.
25 termsResearch Digests
Structured summaries of peer-reviewed studies on LLMs in healthcare and clinical documentation, focusing on what the evidence actually says.
6 studies Do
Goal Bank
Measurable, evidence-referenced goals organized by domain. Every goal answers four questions and includes individualization guidance. Starting points, not copy-paste solutions.
Growing collectionPrompt Library
Each prompt is an inventory of what a competent clinician knows (assessment frameworks, legal requirements, clinical reasoning) made actionable.
12 promptsTasks
Goal writing, documentation, communication, compliance, clinical reasoning, and material creation — each with its multi-step workflows and matching prompts.
6 tasks · 6 workflows Adapt
Settings
Schools, medical/acute, SNF/rehab, early intervention, private practice, and university supervision.
6 settingsDomains
Articulation, language, fluency, voice, pragmatics, cognitive-linguistic, dysphagia, AAC, literacy, and hearing.
10 domainsClinical Patterns
Map your clinical philosophy to LLM interaction strategies. Naturalistic, discrete trial, family-centered; each approach is different.
6 patterns Verify
Reading LLM Writing
Learn to read LLM-generated clinical text the way you'd read a student clinician's draft — including eight worked antipatterns: output that looks plausible and fails clinically.
The skill + 8 antipatternsCase Studies
De-identified clinical scenarios showing real SLP workflows with LLMs: what worked, what failed, and lessons learned.
5 casesPolicy Templates
Adaptable LLM governance templates for schools, hospitals, private practices, and clinical education programs.
4 templatesAI Updates
Breaking changes, privacy updates, and policy shifts for ChatGPT, Claude, Gemini, DeepSeek, and other tools SLPs use. What changed and what to do about it.
Rolling feedResources
Digital media literacy, full references, changelog, and supporting materials.
3 resourcesOrigin
Why This Exists
SLPs spend more time on paperwork than almost any other clinical task. LLM-assisted clinical writing is real work that deserves real craft — both in producing the artifact and in reading it critically against the actual client.
The Gap
LLM-assisted documentation is becoming part of clinical practice. That work deserves the same rigor as any clinical skill — including the ability to read what a model produces and know where it meets the client and where it doesn't.
The Background
This resource is built by a school-based speech-language pathologist in New York who also writes software. That dual lens — clinical practice and software development — drives everything here.
The Problem
Paperwork is where clinical knowledge becomes a legal document. If new tools are going to touch that process, clinicians (not vendors) need to define the standards.
The Position
SLP/IO isn't pro-LLM or anti-LLM. It's pro-clinician. This resource is free because the knowledge it organizes already belongs to the profession. We're just making it easier to use.
Harmonic Systems is the studio behind SLP/IO, a small operation where clinical practice and software development overlap. SLP/IO is its first public resource: a living document where the rigor of speech-language pathology meets the capability of modern language models.
Sustainability
Prompts Worth the Water
Every AI query costs electricity and water. A shared, maintained reference is a better use of resources than thousands of clinicians asking chatbots the same questions independently. When you do use an LLM, make it count.
Low-Value Use
- Asking "what are good IEP goals for articulation?" (this already exists everywhere)
- Pasting one progress note and asking AI to "make it sound better"
- Generating generic parent letters you'll rewrite anyway
- Running the same prompt every session instead of saving a reusable template
- Using a chatbot as a search engine for information in your own files
High-Value Use
- Correlating a semester of progress notes to identify patterns across goals
- Building a reusable documentation guide for your setting that you use all year
- Reframing deficit-based language into strengths-based, neurodiversity-affirming descriptions
- Synthesizing research across multiple sources into a team evidence summary
- Drafting complex medical necessity arguments with your specific clinical data
The position: Being thoughtful about AI isn't just about clinical ethics. It's about resource ethics. Reformatting a three-line note isn't worth the compute. Surfacing patterns across a semester of data, or finding language that honors a student's dignity while meeting legal documentation requirements — that's worth it.
Background
About This Resource
SLP/IO is a Harmonic Systems project, built by a speech-language pathologist and software developer who has spent years writing the same IEP goals, progress notes, and evaluation reports that you write.
This resource is free, independent, and not affiliated with any vendor or institution. The knowledge inside it isn't new — it's what competent clinicians already know, organized in a way that makes it usable with modern tools and readable with a critical eye.
LLM-assisted clinical writing is real work that deserves real craft. The question was never "should SLPs use LLMs?" It's "who defines what good looks like, and who notices when it doesn't?" The answer should be clinicians.
This resource was developed with LLM writing tools and reviewed through clinical judgment.
About Harmonic Systems: A small, independent studio in the Hudson Valley region of New York, built by a school-based speech-language pathologist who also writes software. SLP/IO is an attempt to bridge the gap between what clinicians need and what the technology conversation currently offers.
Connect
Get Involved
Want to contribute, collaborate, or push back?
This guide gets better when clinicians challenge it. If you've found a use case we missed, a principle that needs nuance, or something that's flat-out wrong, that's exactly the kind of feedback that matters.
Have an LLM-generated clinical artifact you've been thinking about? Submit a specimen — your noticings help build the field's shared vocabulary for reading AI-assisted clinical writing.
Send feedback