EXVIV evidence profile

Langfuse

https://langfuse.com

Review verified moves first. Open the official source or before-and-after evidence when you need the full record.

Public proof receipts

The useful part, first.

These are delayed P0 and P1 receipts from the curated public set. Same-day coverage and the rest of the watchlist stay in a private workspace.

P1launchSep 7, 2026

Langfuse adds evaluator backfills — run evaluators on historical observations

BEFORE

Full-Text Search

AFTER

Run evaluators on historical observations

View evidence

New changelog entry (2026-09-07, top of feed): attaching an evaluator to a rule can now backfill scores across recent historical observations instead of only scoring new data. The removed 'Full-Text Search' entry is older post rotating off the changelog feed.

WHY IT MAY MATTER

A new release or deprecation can change feature parity, migration risk, and the next competitive response.

Open public receipt → Current source ↗

P1integrationSep 2, 2026

Langfuse adds score/cost alerts for evaluators and org-wide feature previews with per-user opt-outs

BEFORE

Experiments CI/CD integration

AFTER

Create alerts for evaluators

View evidence

New Langfuse changelog entries: (1) create score and cost alerts directly from evaluator pages, reviewing every alert linked to its evaluator; (2) organization admins can enable feature previews for the whole org — all current and future members — with global personal opt-outs and per-user controls. Removals are older changelog posts rotating off the feed.

WHY IT MAY MATTER

An ecosystem expansion can add distribution, increase switching costs, or close an adoption gap.

Open public receipt → Current source ↗

P1enterpriseSep 1, 2026

Langfuse ships multi-message evaluator prompts and self-hosted interactive API reference

BEFORE

AFTER

Build multi-message prompts and evaluate multi-modal inputs

View evidence

Two new capabilities: (1) LLM-as-a-Judge evaluators support multi-message prompts and multi-modal input; (2) built-in interactive API reference for self-hosted deployments including air-gapped installations.

WHY IT MAY MATTER

A new security, governance, or deployment capability can open larger accounts and reduce procurement friction.

Open public receipt → Current source ↗

Monitored sources