These answers draw in part from “DistruptABA: Stop Wasting Time: ChatGPT Strategies for Busy BCBAs” by Mellanie Page (BehaviorLive), and extend it with peer-reviewed research from our library of 27,900+ ABA research articles. Clinical framing, BACB ethics code references, and cross-links below are synthesized by Behaviorist Book Club.
View the original presentation →It depends on how you use it. Entering any protected health information (PHI) such as client names, dates of birth, diagnosis codes, or session details into standard ChatGPT accounts likely violates HIPAA because the data is processed on external servers. OpenAI offers enterprise plans with Business Associate Agreements, which may provide HIPAA-compliant options. The safest approach is to use ChatGPT only for generating templates, formatting structures, and generic content, then manually add all client-specific information yourself. Always consult your organization's compliance officer before using any AI tool with clinical information.
Prompt engineering is the practice of crafting specific, structured input instructions that guide ChatGPT to produce more accurate and useful output. It matters for BCBAs because vague prompts produce generic, often inaccurate content, while well-structured prompts can generate clinically relevant material that requires less editing. Effective prompts typically include a role specification, specific task description, target audience, desired format, relevant constraints, and quality criteria. BCBAs are actually well-positioned for this skill because the field emphasizes operational definitions and precise specification of conditions and criteria.
ChatGPT can help you draft templates and structural frameworks for behavior intervention plans, but it should never generate the clinical content of a BIP. The tool has no knowledge of your specific client, their assessment data, their reinforcement history, their family context, or their environmental variables. You can use it to format sections, generate parent-friendly language for concepts you have already identified, or create implementation checklists. However, the assessment-based clinical reasoning that drives a BIP must come from you as the qualified practitioner. Always treat AI output as a first draft requiring substantial professional revision.
Custom GPTs are specialized ChatGPT instances that you build with persistent instructions, specific behavioral guidelines, and optional reference documents. For BCBAs, they can serve as dedicated assistants for recurring tasks. For example, you could build a custom GPT that formats session notes according to your organization's template, generates caregiver-friendly summaries at a specific reading level, or creates staff training quiz questions based on specific behavioral procedures. The advantage over regular ChatGPT is consistency: your custom GPT applies the same rules every time without re-prompting.
Evaluate AI output the same way you would evaluate content from a non-expert: check every technical term for correct usage, verify that behavioral principles are described accurately, confirm that any referenced procedures align with evidence-based practice, and assess whether the content is appropriate for the intended audience. Be especially alert for common AI errors like conflating positive and negative reinforcement, misusing punishment terminology, describing procedures that blend incompatible approaches, or stating clinical recommendations without empirical support. If you lack expertise to evaluate content in a specific area, the AI tool should not be used for that topic.
Using ChatGPT does not automatically violate the Ethics Code, but specific uses can create ethical issues. Confidentiality requirements (Code 2.04) are implicated when client information is entered. Competence boundaries (Code 1.05) are relevant if you use AI to generate content in areas you cannot independently evaluate. Responsibility for services (Code 2.01) means you bear full accountability for any AI-assisted clinical work. The Ethics Code does not currently mention AI specifically, but its principles around competence, confidentiality, honesty, and evidence-based practice all apply directly to how you use these tools.
Avoid using ChatGPT for any task requiring clinical judgment about a specific client, including functional behavior assessment analysis, treatment selection, and progress determination. Avoid entering any identifiable client information without HIPAA-compliant safeguards. Avoid using it to generate content in clinical areas where you lack the expertise to evaluate accuracy. Avoid using it to make supervisory decisions or evaluate supervisee performance. Avoid relying on it for information about current BACB requirements or state regulations, as training data may be outdated. Any task where errors could directly affect client safety or welfare warrants special caution.
ChatGPT can help you translate technical behavioral concepts into plain language, generate multiple versions of training handouts at different reading levels, create visual instruction outlines, develop quiz questions to assess caregiver understanding, and draft scripts for training demonstrations. Provide the AI with the specific behavioral concept, the target reading level, and the format you want. Then review the output for technical accuracy, cultural appropriateness, and alignment with the specific client's programming. This approach can help you create higher-quality caregiver materials more efficiently while maintaining your clinical standards.
Several settings are important for professional use. In the data controls section, consider opting out of model training so your inputs are not used to improve the model. Configure custom instructions with your professional context so the tool consistently produces outputs appropriate for behavior analysis. If your organization has a ChatGPT Team or Enterprise plan, ensure you are using the organizational workspace rather than a personal account. Set your default model to the most capable version available. Review the memory feature and decide whether persistent memory is appropriate for your professional use case, keeping confidentiality requirements in mind.
Frame the conversation around risk management rather than technology adoption. Staff are likely already using AI tools, and the absence of a policy creates more risk than a thoughtful policy does. Present concrete examples of both beneficial uses and potential risks, particularly around confidentiality and clinical accuracy. Propose a simple framework that categorizes tasks by risk level, specifies review requirements for each level, and establishes clear prohibited uses. Offer to pilot the framework with a small team and report on outcomes. Organizations that proactively develop AI policies position themselves ahead of inevitable regulatory requirements.
The ABA Clubhouse has 60+ on-demand CEUs including ethics, supervision, and clinical topics like this one. Plus a new live CEU every Wednesday.
Ready to go deeper? This course covers this topic with structured learning objectives and CEU credit.
DistruptABA: Stop Wasting Time: ChatGPT Strategies for Busy BCBAs — Mellanie Page · 2 BACB Ethics CEUs · $20
Take This Course →We extended these answers with research from our library — dig into the peer-reviewed studies behind the topic, in plain-English summaries written for BCBAs.
280 research articles with practitioner takeaways
279 research articles with practitioner takeaways
258 research articles with practitioner takeaways
2 BACB Ethics CEUs · $20 · BehaviorLive
Research-backed educational guide with practice recommendations
Side-by-side comparison with clinical decision framework
You earn CEUs from a dozen different places. Upload any certificate — from here, your employer, conferences, wherever — and always know exactly where you stand. Learning, Ethics, Supervision, all handled.
No credit card required. Cancel anytime.
All behavior-analytic intervention is individualized. The information on this page is for educational purposes and does not constitute clinical advice. Treatment decisions should be informed by the best available published research, individualized assessment, and obtained with the informed consent of the client or their legal guardian. Behavior analysts are responsible for practicing within the boundaries of their competence and adhering to the BACB Ethics Code for Behavior Analysts.