Thank you for agreeing to write a letter of recommendation (LOR) for a residency applicant.
These guidelines are a joint effort between the Organization of Program Directors Association (OPDA) and the Association of American Medical Colleges (AAMC) to provide a general framework of best practices and relevant content for letter writers to follow when writing an LOR. The framework is recommended but not required. Please note that some specialties have elected to use specialty-specific guidance and/or standardized LORs, including Standardized Letters of Evaluation (SLOEs), Structured Evaluative Letters (SELs), and Standardized Letters of Recommendation (SLORs); these guidelines do not apply to specialty-specific SLOEs, SELs, or SLORs. More information is available in the Program Directors Association Guides for Residency Applicants and from specific specialty organizations.
On This Page:
Guidelines
- Prepare to write the LOR by gathering critical information. Make sure you know which specialty/specialties the applicant is pursuing. Ask for a CV and a draft personal statement if the applicant does not provide them.
- Write the LOR as a focused evaluation of the applicant’s performance, core skills and competencies, and potential for success in residency training in the specialty, rather than a general endorsement of the applicant.
- The content of your LOR should connect specific applicant strengths to the specialty’s performance requirements and/or competencies. You can also base your evaluation on the Graduate Medical Education Competencies.
- For students applying to more than one specialty, LOR content may need to be adjusted to address each specialty’s requirements and competencies.
| DOs | DON’Ts |
|---|---|
| She displayed her professionalism when she [action], resulting in [outcome]. | She works well with others. |
| When faced with [situation], he demonstrated his communication skills by… | He is a good listener. |
| I believe she will be successful as a resident in [specialty] based on her skills in… | I recommend her for any residency program. |
- Briefly describe your role and how you know the applicant. The goal is to provide context for your evaluation. Do not reiterate the applicant’s CV. Provide information on:
- Your role (e.g., faculty, career advisor, clerkship supervisor, research mentor).
- When you worked with the applicant.
- The duration and frequency of your interaction with the applicant.
- The context (e.g., clinical rotation, research, advising).
- Your qualifications/background in assessing candidates for residency training.
| DOs | DON’Ts |
|---|---|
| I was his research mentor from May to August 2025. We interacted weekly… | I have known him for several years. |
| She demonstrated her critical thinking skills when she… | She was responsible for the following tasks… |
- Describe the strengths and the unique contributions the applicant would bring to the residency program. Focus on direct observations of behaviors, skills, and performance.
- Ground general comments with concrete examples of applicant behavior or performance.
- When discussing your observations of the applicant’s performance:
- Provide background information on the situation
- Describe the behavior you observed
- Explain the consequences of the applicant’s actions
- Highlight areas of the applicant’s exceptional performance or describe how the applicant stands out from their peers by demonstrating unique strengths.
- Describe your observations of why the applicant is pursuing residency in the specialty.
- If you note any challenges the applicant faced or areas of potential improvement, share your evaluation of the applicant’s ability to demonstrate progress, potential for growth, and response to feedback.
- You may also explain discrepancies in the applicant’s academic record.
| DOs | DON’Ts |
|---|---|
| He demonstrated his dedication to patient care when [situation]. He reacted by [specific actions], leading to [outcome]. | He was smart and responsible. |
| When starting this rotation, she was challenged by competing responsibilities including [examples]. She was responsive to feedback and reacted by [behavior], which allowed her to better manage her clinical and academic priorities. | She is able to overcome obstacles. |
- Provide your evaluation of the applicant’s readiness for residency and a rationale for your judgment.
- Describe the applicant’s performance in important general or specialty-specific domains relative to expectations for their level of experience or above. For example, does the applicant perform at the level of a leading fourth-year medical student, of an intern/PGY-1, etc.
- When possible, anchor your evaluation of the applicant to relevant standards or benchmarks, such as the ACGME Milestones by specialty.
- If you provide a comparison of the applicant to others, describe the comparison group (e.g., other graduating medical students, all applicants in their cohort, applicants to the specialty) and support your evaluation based on the applicant’s performance.
| DOs | DON’Ts |
|---|---|
| In terms of patient care, he functions at the level of an intern due to his ability to [behavior]. | He is at the top of his cohort. |
| Her interpersonal skills were consistent with those of a PGY-1 because of her ability to [behavior]. | She performed well in this rotation. |
- Be aware of potential sources of bias that might influence your LOR.
- Focus squarely on the applicant’s objective skills, performance, and accomplishments or information relevant to their interest in the specialty.
- Check to ensure that you are using similar language to describe applicants who have the same specialty-specific strengths, regardless of their personal background.
- Consider how personal information or details about an applicant’s background could be perceived through a lens of bias. Personal information should only be included if it is clearly linked to the applicant’s strengths, potential performance, or interest in the specialty. Ask the applicant for permission if you plan to include any information that could be considered private or sensitive.
- Read more about bias and fairness when using AI.
| DOs | DON’Ts |
|---|---|
| She demonstrated her proficiency at [procedural skill] when… | She is very helpful and caring. |
| He stands out for his ability to maintain his composure and appropriately prioritize tasks under stress. For example,… | He dealt with a complicated personal situation when he and his spouse divorced… |
| She grew up in a rural community, inspiring a passion for rural medicine that she pursued through [experience]. | She grew up in a small town with limited opportunities. |
| His interest in child neurology first developed after his brother’s epilepsy diagnosis, and in high school he volunteered with an organization to promote epilepsy awareness and education. | His brother developed epilepsy as a child. |
- Before submitting your letter, review the following formatting considerations:
- Ensure the applicant’s name is spelled properly and correct pronouns are used.
- Write your letter on letterhead paper.
- Include your position and contact information (email address, phone number).
- Review and spellcheck the letter.
- Sign the letter (an electronic signature is acceptable) and include a date.
The Use of Artificial Intelligence (AI)
Generative Artificial Intelligence (genAI) has the potential to support your letter-writing process, including crafting initial drafts of the LOR and editing its content and tone. Regardless of how you use genAI, you remain the author of the letter and are responsible for its content, accuracy, and the assessment it conveys. Although genAI may reduce the effort and time required to produce LORs, consider the following critical factors when deciding whether and how to integrate genAI in your process. Additionally, consult your institution’s policies on AI use, as many institutions are developing governance frameworks for responsible AI adoption:
- Human Oversight: The core value of a letter of recommendation is your authentic, firsthand assessment of the applicant. GenAI should support your writing process, not replace your professional judgment.
- Do not rely on genAI to form your assessment of the applicant. Use it only to articulate an assessment you have already developed through direct observation and interaction.
- Ensure the final letter reflects your voice, perspective, and genuine evaluation. A letter that reads as AI-generated may undermine the credibility of your recommendation.
- Privacy: Sensitive applicant data or any information that could be used to identify the applicant should not be entered into genAI systems where data privacy is compromised. Instead, those data should be protected vigorously with robust security measures.
- Ensure applicant data is only entered into AI tools that are institutionally approved and comply with relevant privacy regulations (e.g., FERPA).
- Do not enter identifiable applicant information into AI tools without first confirming that the tool meets your institution’s data governance requirements.
- Avoid including applicant data while using personal versions of web-based AI tools, because those tools often do not keep your data private.
- Fairness: The prompts and content that go into genAI systems will critically influence the nature and quality of the output. Carefully review and standardize your prompts and uploaded content.
- Screen applicant content to ensure that all content relevant to past performance or future performance potential is included, and all content that is irrelevant is excluded.
- Standardize content input across applicants to ensure fairness (e.g., include transcripts for all, not a subset, of your letters).
- Carefully develop and iterate the prompts used in your process to ensure they are sufficiently comprehensive and specific.
- Review AI-generated drafts for potential linguistic bias. GenAI may introduce differential language patterns when describing applicants from different backgrounds (e.g., agentic vs. communal descriptors). Compare drafts across applicants to ensure consistency in structure, tone, strength of language, and descriptor quality.
- Accuracy: Your role in the process is vital. GenAI can be a powerful assistant, but ultimately you drive and are responsible for the content, structure, and tone of the LOR.
- Expect to read, edit, and iterate through multiple rounds to refine the LOR.
- GenAI output can be contaminated with errors, lack all the facts, or be otherwise inaccurate or exaggerated. Review and edit content so it accurately captures the applicant’s past performance and future potential.
- AI-generated text may produce overly enthusiastic and generic language or reuse the same letter structure. Make sure the final letter reflects your own personal assessment and the unique strengths of each applicant.
For more information, see:
Principles for the Responsible Use of Artificial Intelligence in and for Medical Education
Principles for Responsible AI in Medical School and Residency Selection
Using Generative Artificial Intelligence When Writing Letters of Recommendation
Graduate Medical Education Competencies
In your letter, you may find it helpful to describe how the applicant has, or has not, demonstrated competencies established by the Accreditation Council for Graduate Medical Education (ACGME). These six Core Competencies for graduate medical education are listed below. You may also find it helpful to refer to the AAMC Foundational Competencies and the ACGME Milestones by specialty, which describe observable behaviors and other attributes for each of the competency domains.
Professionalism: Demonstrates a commitment to professionalism and an adherence to ethical principles
Patient Care and Procedural Skills: Provides patient care that is patient and family-centered, compassionate, equitable, appropriate, and effective for the treatment of health problems and the promotion of health. Performs all medical, diagnostic, and surgical procedures considered essential for the area of practice.
Medical Knowledge: Demonstrates knowledge of established and evolving biomedical, clinical, epidemiological, and social-behavioral sciences, including scientific inquiry, as well as the application of this knowledge to patient care.
Practice-based Learning & Improvement: Demonstrates the ability to investigate and evaluate their care of patients, to appraise and assimilate scientific evidence, and to continuously improve patient care based on constant self-evaluation and lifelong learning.
Interpersonal and Communication Skills: Demonstrates interpersonal and communication skills that result in the effective exchange of information and collaboration with patients, their families, and health professionals.
Systems-Based Practice: Demonstrates an awareness of and responsiveness to the larger context and system of health care, including the structural and social determinants of health, as well as the ability to call effectively on other resources to provide optimal health care.
We gratefully acknowledge the members of the AAMC AI in Admissions and Selection Technical Advisory Committee and the GSA Committee on Student Affairs (COSA) for their feedback and input throughout the development of these guidelines.