Firetiger has created NXL, a declarative domain-specific language for defining agents as structured graphs with built-in concurrency, to address scaling limits in managing complex, multi-phase LLM age…
Firetiger migrated its agent fleet from Claude to DeepSeek, achieving a 62% reduction in inference costs from $606K/yr to $231K/yr. The migration required extensive prompt engineering and evaluation t…
Kernel, a browser infrastructure company, uses Firetiger Change Monitors to increase deployment frequency, reduce change failure rate, and improve mean time to recover across pull request workflows. T…
Voxel, an industrial safety analytics company, uses Firetiger to help engineers maintain reliability in its AI-powered safety monitoring systems. Principal engineer Jorge Villatoro treats Firetiger li…
Firetiger used an AI agent to optimize LLM prompt cache TTLs in production, reducing waste by 77% over several weeks by hill-climbing against telemetry and cost data. The agent autonomously measured s…