Apache 2.0 · local-first · BYOK judge

LLM observability for production apps and agents.

Cognifity builds infrastructure for AI in production. Verdict — our first product — captures supported LLM calls, stores traces locally by default, and helps teams measure quality drift with calibrated PASS/FAIL rubrics.

Verdict v0 focuses on the LLM-call layer. Agent-run graphs and task-success metrics are on the roadmap.
Apache 2.0
Open-source SDK and evaluation packages
3 providers
Anthropic, OpenAI, and Google capture paths
BYOK
Judge scoring uses your provider key
Local
SQLite by default, Postgres when needed
Meet Verdict

Statistical drift detection for the LLM stack you actually run.

Most LLM observability starts with latency, tokens, and errors. Verdict adds quality monitoring: capture supported provider calls, group similar prompts, evaluate sampled responses with a rubric, and compare recent behavior against a reference window.

One line to instrument

verdict.init() captures supported Anthropic, OpenAI, and Google SDK calls. No proxy in front of your traffic. Keep normal SDK code and opt into content capture only when you need it.

Statistical rigor, not vibes

Fisher's exact for binary PASS/FAIL dimensions, Mann-Whitney U for continuous scores, Cliff's δ for effect-size gating, and Benjamini-Hochberg correction across dimensions.

Honest calibration workflow

Calibration scripts compare judge decisions against your own human labels. Public benchmarks are treated as sanity checks, not proof that a judge is calibrated for your workload.

See the full Verdict methodology
Why Cognifity

Engineered for teams that need evidence, not guesswork.

Production AI teams already have logs, latency charts, and token dashboards. Cognifity products focus on the harder operational question: did behavior change for the workloads your users actually run?

01

Statistical rigor by default

Fisher's exact for binary PASS/FAIL dimensions, Mann-Whitney U for continuous scores, Cliff's δ effect-size gating, and Benjamini-Hochberg correction across dimensions.

02

Honest about what works

The repo includes workflows for judge calibration, live capture checks, and injected drift tests. We say what v0 catches today and keep agent-run outcomes in the roadmap until they ship.

03

Open source, no lock-in

Verdict is Apache 2.0. Run it locally, inspect the code, keep your traces in your own storage, and bring your own provider key for judge-based scoring.

04

Cloud-agnostic, model-agnostic

Hexagonal architecture, storage adapters for SQLite/Postgres/in-memory, and provider adapters for Anthropic, OpenAI, and Google. Keep the evaluation layer separate from provider SDKs.

What it looks like in production

Three drift modes that quietly cost enterprises money.

Silent model update

A provider, model, or prompt change shifts refusal behavior on support traffic.

Verdict captures the calls, tracks structural signals, and helps you compare recent windows against a baseline so a reviewer can inspect affected traces quickly.

Signal: refusal-rate and quality drift by workload
Pre-flight model swap

Your team wants to compare models without trusting a global average.

Use pairwise comparison and workload grouping to inspect where a candidate model helps, hurts, or needs more labels before you switch production traffic.

Risk: blind swap → workload-specific evidence
Cost runaway

A prompt change alters response length and token usage.

Captured traces include tokens, latency, cost estimates, finish reason, errors, and optional redacted content, so cost and quality investigations start from the same evidence.

Signal: token, latency, and response-length movement

Try Verdict in 60 seconds.

Clone the Apache 2.0 repo, run the smoke test, and capture your first supported provider call locally. Enterprise inquiries are reviewed by the team directly.