The guidelines provide recommendations on the reliability of clinical predictors and prediction models for neuroprognostication in critically ill adults with moderate–severe traumatic brain injury (msTBI). The authors reviewed the literature to assess the reliability of predictors and models used to predict outcomes such as mortality and functional recovery. They used the GRADE methodology to evaluate the quality of evidence, desirability of outcomes, values and preferences, and resource use. The review identified ten clinical variables and nine grading scales as relevant predictors. The authors emphasized that many articles varied in defining "poor" functional outcomes, so they treated "poor" as "unfavorable" for consistency. They found that only the presence of bilateral pupillary nonreactivity on admission, conditional on accurate assessment without confounding from medications or injuries, was deemed moderately reliable for counseling surrogates regarding 6-month functional outcomes or in-hospital mortality. The CRASH-basic, CRASH-CT, IMPACT-core, IMPACT-extended, and IMPACT-lab models were recommended as moderately reliable in predicting 14-day to 6-month mortality and functional outcomes. The authors emphasized that when using moderately reliable predictors or models, clinicians must acknowledge "substantial" uncertainty in the prognosis. The guidelines aim to help clinicians provide formal reliability assessments of individual predictors and prediction models when counseling surrogates of patients with msTBI. The guidelines also highlight the importance of considering the patient's potential for long-term disability and diminished quality of life when making decisions about life-sustaining treatments. The authors concluded that these guidelines provide recommendations on the formal reliability of individual predictors and prediction models of poor outcome when counseling surrogates of patients with msTBI and suggest broad principles of neuroprognostication. The guidelines emphasize the need for clinicians to acknowledge the uncertainty inherent in neuroprognostication and to use reliable predictors and models when possible. The authors also noted that the reliability of predictors and models can vary based on the context and the specific outcomes being predicted. The guidelines are intended for clinicians responsible for counseling patients with msTBI and their surrogates.The guidelines provide recommendations on the reliability of clinical predictors and prediction models for neuroprognostication in critically ill adults with moderate–severe traumatic brain injury (msTBI). The authors reviewed the literature to assess the reliability of predictors and models used to predict outcomes such as mortality and functional recovery. They used the GRADE methodology to evaluate the quality of evidence, desirability of outcomes, values and preferences, and resource use. The review identified ten clinical variables and nine grading scales as relevant predictors. The authors emphasized that many articles varied in defining "poor" functional outcomes, so they treated "poor" as "unfavorable" for consistency. They found that only the presence of bilateral pupillary nonreactivity on admission, conditional on accurate assessment without confounding from medications or injuries, was deemed moderately reliable for counseling surrogates regarding 6-month functional outcomes or in-hospital mortality. The CRASH-basic, CRASH-CT, IMPACT-core, IMPACT-extended, and IMPACT-lab models were recommended as moderately reliable in predicting 14-day to 6-month mortality and functional outcomes. The authors emphasized that when using moderately reliable predictors or models, clinicians must acknowledge "substantial" uncertainty in the prognosis. The guidelines aim to help clinicians provide formal reliability assessments of individual predictors and prediction models when counseling surrogates of patients with msTBI. The guidelines also highlight the importance of considering the patient's potential for long-term disability and diminished quality of life when making decisions about life-sustaining treatments. The authors concluded that these guidelines provide recommendations on the formal reliability of individual predictors and prediction models of poor outcome when counseling surrogates of patients with msTBI and suggest broad principles of neuroprognostication. The guidelines emphasize the need for clinicians to acknowledge the uncertainty inherent in neuroprognostication and to use reliable predictors and models when possible. The authors also noted that the reliability of predictors and models can vary based on the context and the specific outcomes being predicted. The guidelines are intended for clinicians responsible for counseling patients with msTBI and their surrogates.