From d1e9dfbfdb83663123ffc4639b8d8156f79c17bf Mon Sep 17 00:00:00 2001
From: Richard Abrich
+ An 18-step add-patient-note workflow on the official
+ OpenEMR public demo, run both ways and judged by one
+ arm-independent OCR check, with a distinct
+ parameterized note per run. Both arms succeeded every
+ time: 20/20 compiled, 10/10 for a Claude computer-use
+ agent. The agent doesn't fail here — the
+ difference is what each run costs.
+
- 7.7× faster
+ 1.8× faster
- median run: 4.9s compiled vs 37.5s agent
+ median run: 39.2s compiled vs 70.4s agent
- $0 vs $0.27
+ $0 vs $0.55
model cost per run, at list price
@@ -175,25 +184,61 @@ export default function ComparePage() {
- 5.1s vs 43.4s
+ 0 vs ~24
- 95th-percentile latency
+ model calls per run
- Same task, same success check, 100 compiled replays
- against 20 runs of a Claude computer-use agent: both
- arms passed 100% on our simple demo app, so the
- difference isn't success rate, it's what
- repetition costs.
+ Run the task 500 times and the ratios compound: about
+ $275 and ten hours of wall clock through the agent,
+ versus $0 and about five and a half hours compiled,
+ with every action auditable against the demonstrated
+ script. The compiled arm's price of entry is a
+ one-minute human demonstration; the agent needs only a
+ prompt.
+
+ Caveats, disclosed up front: the OpenEMR demo is a
+ shared public instance that anyone can modify and that
+ resets daily, so this is a field result, not a
+ CI-reproducible one. The agent arm is N=10 (agent runs
+ cost real money and real load on a shared service), so
+ its 100% carries wide error bars. Results are pinned
+ to claude-sonnet-5 with the computer_20251124 tool on
+ 2026-07-08; newer models will differ. The OCR success
+ check errs conservative on dense EMR text and is
+ identical for both arms.
+
+ Because the OpenEMR numbers depend on a live shared
+ instance, we keep the same head-to-head on MockMed,
+ the demo clinic app that ships with openadapt-flow,
+ as the benchmark anyone can rerun deterministically:
+ 100 compiled replays against 20 agent runs, both arms
+ 100%, 4.9s vs 37.5s median, $0 vs $0.27 per run at
+ list price. Same orchestrator, same agent harness,
+ same style of OCR check.
- We measured it
+ We measured it on a real EMR
+
+ The reproducible anchor
+
+
+ On the same harness under injected UI drift, a hybrid + mode — compiled replay first, agent fallback + only on a detected halt — matched agent + reliability (20/20) at roughly one-eighth the + agent's cost per successful run. Details and + caveats (synthetic detected-halt drift, assumed drift + mix) in the repo. +
+