EAGLE is a diffusion-based deep-learning model that designs full-length nanobody and antibody sequences (both constant and variable regions) entirely in continuous language model (ESM) embedding space, without requiring predefined backbone structures. Analogous to image-generation models conditioned on textual prompts, EAGLE conditions the antibody sequence generation directly on the antigen structure and epitope residues. For a given antigen target, EAGLE can generates over 100,000 candidate antibody/nanobody sequences, which are then structurally modeled using AlphaFold3 (AF3) to prioritize designs exhibiting high structural confidence (ipTM scores).