Providers ship silent model changes with no version bump and no changelog. Same 200 OK, same latency — but JSON fidelity slips and outputs drift. Standard monitoring is blind to it. I build the early-warning layer that isn't.
Open-source engine · Apache-2.0 · privacy-preserving by design · you own every result.
For teams shipping on OpenAI, Anthropic, Mistral or any third-party LLM API — where a silent model change means broken JSON, degraded answers, and support tickets before you know why.
Two-person teams pitch with a deck. I pitch with a reproducible, seeded backtest you can re-run yourself.
In the backtest, detection occurred during the 0.8% misrouting window — 38 days before the official postmortem and 19 days before the escalation became visible to users. The methodology is hash-committed, so the next call is a prediction, not a postmortem.
Evidence: live dashboard · open-source engine · dev.to writeup · pip install seismograph-probe
One email listing the LLM APIs you depend on. No call, no system access, no NDA needed.
Your top-3 silent-drift exposures, ranked, with the exact metrics that would move first. Yours to keep either way.
If the map warrants it: canary probes on your real model tuples, tuned thresholds, alerts wired into Slack or PagerDuty. Fixed price, reviewable deliverable.
Flat pricing, concrete deliverables, fixed timelines. No open-ended “let's chat” retainers to start.
~48 hours · no system access
Zero risk. You leave with a watchlist worth more than the time it took.
~1 week · reviewable deliverable
standing early-warning line
Cheaper than one bad week in production.
Need it built into your stack and handed over working? A full Proof-of-Process Build (in-VPC probe fleet wired to your alerting, runbook, handover) is scoped per engagement — ask in your scan.
Only derived, non-reversible features cross the boundary — token counts, a JSON-valid flag, SHA-256 hashes. Raw text is never stored or transmitted.
Numeric signals carry Laplace DP noise with a tracked epsilon budget. Aggregated, anonymised, defensible.
Probes deploy inside your perimeter. Your data never depends on my infrastructure. Audit-grade evidence export for compliance.
I don't sell you a model, so I have no reason to tell you it's fine. The engine is Apache-2.0 and auditable line by line.
The Anthropic routing bug degraded output for weeks at 0.8% of traffic while every dashboard stayed green — a seeded backtest flags it 38 days before the postmortem. Your free scan takes one email and ~48 hours.
App-level observability tells you your outputs got worse. It can't tell you whether the model itself changed — and it's often channel-conflicted (it sells to the providers it would have to indict). SEISMOGRAPH watches the provider side, neutrally, across time.
The free scan: your top-3 drift exposures within ~48h. The Baseline: live canary probes, tuned thresholds, a written report, and an alerting plan — a reviewable deliverable in about a week, not an open-ended retainer.
Raw prompts and outputs never leave your perimeter — only DP-noised aggregate features. Probes run in your VPC. You own every artifact. Full technical detail is in the open-source repo.
Because it's falsifiable. The 38-day Claude Sonnet 4 call was made on a seeded, reproducible backtest you can re-run. The methodology is hash-committed up front.
Honest answer: the public network effect (cross-org quorum) compounds with adoption and is early. Today the value is the in-VPC early-warning layer and the neutral monitoring — which stand on their own. I'd rather tell you that than oversell it.
Send me the model APIs you depend on. Within ~48 hours you get your top-3 silent-drift exposures and the metrics that move first — plus a fixed quote if you want the Baseline.
or email me directly: tatyan.radchenko@gmail.com