Blog

Execution-aware coding agents: a radar DSP use case

Claude saw the source. LOCI exposed what the compiled executable would actually do — early enough to change the coding plan.

Aurora Labs TeamAurora Labs3 min readUse Case, Embedded, AI Agents

Executive summary

A real radar DSP hot path was ported from Python/NumPy to embedded C with Claude Code. Claude's initial plan was sound: reuse the existing C FFT, validate against NumPy, then optimize. LOCI added an execution signal from the compiled executable and revealed an arithmetic difference hidden by the source: fused multiply-add behavior. Claude used that signal to change its plan before relying on target-hardware discovery.

The co-reasoning flow

  1. Developer intent. Port the radar Doppler hot path to embedded C.
  2. Claude plans. Reuse the C FFT and validate against NumPy.
  3. LOCI signal. Compiled execution shows fused multiply-add behavior.
  4. Claude reasons. The 1e-9 mismatch is execution behavior, not just tolerance.
  5. Plan adjusts. Port the NumPy FFT behavior operation by operation, and control fusion.
  6. Code. Implement the execution-aware plan.

Measured result

FFT beforeFFT afterAccuracy
71.1 µs43.4 µsBit-exact with the Python reference

Why not just give Claude the workload or binary?

Binary or workload as contextLOCI's execution signal
Claude can inspect artifacts and infer intent from what is visible.LOCI provides a purpose-built signal about compiled execution behavior and its implications.
The agent still has to infer which low-level details materially change behavior.The signal surfaces execution differences that can change the plan — here, arithmetic fusion hidden behind equivalent-looking source.
Typical loop: Plan → Code → Run → Discover → FixExecution-aware loop: Plan → LOCI → Reason → Adjust → Code

Claude reasons about what to build. LOCI reasons about how it will behave.

LOCI is pre-run execution prediction for AI coding agents. No target-hardware run was needed to discover the execution difference in this use case.