Purpose: Pembrolizumab combined with chemotherapy is the standard of care for early-stage triple-negative breast cancer (TNBC) following KEYNOTE-522. However, real-world data on immune-related adverse events (irAEs) remain limited. We evaluated the incidence, severity, and clinical consequences of irAEs in a real-world cohort and compared outcomes with KEYNOTE-522. Methods: We conducted a retrospective cohort study of patients with stage II–III TNBC treated according to the KEYNOTE-522 regimen at two Ontario cancer centres between June 2022 and May 2024. Data on irAEs, treatment discontinuation, and pathological complete response (pCR) were collected and contextualized against trial outcomes. Results: Among 79 patients, the pCR rate was higher than that reported in KEYNOTE-522 (77.2% vs. 64.8%). irAEs were documented in 51.9% of patients, compared with 33.5% in the trial. Permanent discontinuation due to irAEs occurred in 22.8% of patients, compared with 15.7% reported in KEYNOTE-522. Most discontinuations occurred during the neoadjuvant phase. Conclusions: Real-world patients experienced higher observed rates of low-grade irAEs and treatment discontinuation than reported in KEYNOTE-522; however, differences in study design limit direct comparison. These findings highlight the need for optimized toxicity management and further study of the impact of treatment duration on long-term outcomes.