Privacy

Accept optional first-party analytics or decline. Functional journey and sound preferences stay on this device.

Read the privacy notice
EvidenceJuly 5, 2026

AI workflow automation proof

Every LLM call in the system is traced — provider, model, input/output tokens, latency, and cost in USD — and the traces feed a live cost dashboard in the admin. Snapshot from the build log (July 2026): 407 traced calls, ~300K tokens, $1.24 total spend across Claude Sonnet, Claude Haiku and OpenAI embedding models.

LLM calls traced

100% (407 of 407)

Proof type
metric
Confidence
verified
Before

AI generation ran untracked: no record of which model was called, what it cost, or how long it took.

After

Each call writes a trace (timestamp, task, provider, model, tokens, cache hits, duration, cost) to an append-only log surfaced on the analytics dashboard — e.g. 407 calls / 299,742 tokens / $1.24 in one development window.

Every LLM call routes through one traced client that appends a JSON line — timestamp, task, provider, model, input/output tokens, duration, cost — to data/llm_traces.jsonl. The 407 calls, ~300K tokens and $1.24 are a straight count and sum over that file for one development window in July 2026. Cost is computed from a per-model price table in code at the time of the call.

This is development traffic, not production load — it says the tracing works, not what the system costs at scale. Cost is derived from a hardcoded price table rather than reconciled against provider invoices, so it drifts when prices change. The "100%" holds only for calls made through the traced client; anything calling a provider SDK directly would not appear.


metricresultimpact