AI-generated training plans are rated sub-optimal to moderate by experts and improve with detailed input, and adaptive (HRV-guided) training improves submaximal markers but not performance; none of this has been tested in triathletes
Interpretation
Expert raters judged ChatGPT running plans sub-optimal, improving with more input (Düking 2024, 22 criteria), and LLM strength plans moderate (Havers 2025, 10 coaches, 27 criteria); detailed prompts gave better, more stable programmes but identical prompts still varied (Yang 2026, 11 experts); some plans for fictional type 2 diabetes patients had serious safety issues (Akrimi 2025). ChatGPT answered general exercise questions better than 9 personal trainers on 6 of 9 questions (D'hoe 2026). HRV-guided endurance training improved submaximal markers (g = 0.296) but not performance (g = 0.079) versus predefined plans (Düking 2021, 8 studies, 198 participants). Apps gave a non-significant 476.75 steps/day in 1740 general adults (Romeo 2019), and supervised training beat unsupervised in older adults (Lacroix 2017, SMD 0.51 for strength). Graded limited: expert ratings of paper plans, fictional profiles and mismatched populations; no trial of app, AI or human coaching in triathletes; commercial adaptive algorithms unpublished.
Practical implication
Use apps and AI tools for structure, load progression and general explanations, give them detailed information, check plans against basic principles, and keep injury, illness and medical decisions with a clinician or experienced coach. Inference from expert ratings and other populations, not tested in age-group triathletes.
Sources
8 sources, independently verified.
Three ChatGPT six-week running plans with increasing input detail, rated by coaching experts on 22 criteria (1-5 scale). Plans were sub-optimal; a median rating of 3 was given 0, 6 and 13 times for plans 1-3; the least-informed plan was rated lower than the most detailed on 15 criteria. Authors advise against using ChatGPT plans without expert feedback. Paper ratings of a fictional profile; number of raters not in abstract.
10 experienced coaches rated hypertrophy and strength plans from GPT-3.5 (ChatGPT, Copilot) and Google Gemini on 27 criteria: overall quality moderate, tool differences on only 1-2 criteria, one tool most inconsistent. LLM plans can be an initial framework but expert supervision remains crucial. Fictional advanced trainee.
Simple and detailed prompts each entered four times into GPT-4 (8 programmes), rated blind by 11 experts on a 15-item scale. Detailed prompts scored higher for personalisation, safety, feasibility and overall (not effectiveness) and gave more stable outputs, but repeated identical prompts still produced structurally and qualitatively different programmes.
Discussion paper with preliminary data: three fictional patient profiles, three prompts each, reviewed by three coaching experts. Some plans had serious safety issues, especially for patients with secondary diseases or complications; most included key training principles but had deficits such as feasibility; detailed prompts tended to rate better.
9 level-4 personal trainers supplied frequent questions and their answers; ChatGPT 3.5 answered the same questions; 18 trainers and 9 topic experts rated them. ChatGPT scored higher overall on 6 of 9 questions (correctness 5, comprehensibility 6, actionability 5); trainers never scored higher. General information questions, not individual plans.
8 studies, 198 participants, 9 interventions. HRV-guided plans usually had fewer moderate/high-intensity sessions than predefined plans. HRV-guided training improved submaximal physiological parameters (g = 0.296, 95% CI 0.031 to 0.562) but not performance (g = 0.079) or VO2peak (g = 0.171) significantly; fewer performance non-responders.
9 RCTs, 1740 adults; in 6 studies apps produced a non-significant increase of 476.75 steps per day (95% CI -229.57 to 1183.07; P = .19). Apps were more effective over less than 3 months and when targeting activity alone. General adults, not athletes.
11 studies in healthy adults aged 65+. Supervised balance/resistance training beat unsupervised for muscle strength/power (SMD 0.51) and several balance measures (e.g. test batteries 0.53, dynamic balance 0.35); advantage larger against fully unsupervised programmes. Few studies, moderate quality (median PEDro 5).