logcat.ai

• Build ramdump and crash forensics: drgn, vmcoreinfo, ramdump parsing, post-mortem analysis under customer deadlines. • Reason across scheduler, memory management, and driver internals. • Ground remediations in kernel source.

• Ingest and reason over robotics artifacts: rosbags (including MCAP), DDS discovery and QoS logs, ros2_control / Nav2 / MoveIt failures. • Diagnose Jetson / L4T boot and platform issues. • Handle the spatial and timing layer: TF2, sensor calibration, time synchronization.

• Parse and correlate dual-OS cockpit dumps: QNX SLOG2, DLT traces, Android IVI logs, perfetto, pcap, CAN. • Solve cross-clock-domain correlation across DLT ECU time, QNX monotonic, kernel monotonic, and Android boottime/realtime. • Build the automotive diagnostic path: UDS, DoIP, DTCs.

• Instrument the product so every investigation, especially human-corrected ones, becomes structured training data. • Build the eval harness for diagnostic accuracy. Root-cause correctness has to be measured, not eyeballed. • Distill expensive deep-investigation runs into small, fine-tuned models that hold the quality bar at a fraction of the cost. • Deploy inference, including on-prem and airgapped SLMs for customers whose logs cannot leave their environment.

• Build parsers and analysis for modem traces: DIAG, QMI, QXDM/QCAT, modem ramdumps and crash logs • Map observed failures to root cause across NAS, RRC, and L1/L2, and across the RIL / radio HAL interface into Android • Encode cellular-stack reasoning the platform uses to ground remediations