Weβre excited to release Muse Spark 1.3 with improved performance on agentic and coding tasks, and a focus on real-world usability.
Key capabilities:
β Sustains longer-horizon work across multiple workflows in a single thread
β More actively collaborates with users: it asks clarifying questions, flags when it's stuck, confirms before consequential actions
β Better calibrated on its own limits instead of hallucinating outcomes
β ~20% fewer tool calls and ~25% fewer tokens vs. Muse Spark 1.2 in internal comparisons