In an era of personalized medicine, an increased effort is being made to identify patients likely to benefit from targeted therapy. By limiting treatment to selected patients, both unnecessary cost and toxicity may be avoided. Restricting the use of anti–epidermal growth factor receptor (anti-EGFR)–targeted agents in metastatic colorectal cancer to only patients with KRAS exon 2 wild-type tumors has become well-established in clinical practice. However, lack of KRAS exon 2 mutations does not necessarily predict response, and a significant proportion of patients with KRAS wild-type tumors do not benefit from therapy with cetuximab or panitumumab. Further characterization is needed of the subset of patients with KRAS exon 2 wild-type tumors who are likely to benefit from anti-EGFR therapy. Recent data suggest that patients with KRAS mutations at loci other than exon 2, and those with other RAS mutations, might not benefit from EGFR-directed therapy. This article briefly reviews established work on KRAS exon 2 mutations, but focuses primarily on emerging data on non–exon 2 KRAS mutations and additional RAS and BRAF mutations and how this information may impact clinical decision-making.