---
type: "post"
slug: "raindrop-introduces-signals-2-0-for-frontier-model-classification"
title: "Raindrop Signals 2 turns production traces into narrow classifiers"
description: "Signals 2 combines deterministic filters, small semantic heads, and selective frontier-model calls for low-latency monitoring."
retrieval_nugget: "Signals 2 combines deterministic filters, small semantic heads, and selective frontier-model calls for low-latency monitoring."
published_at: "2026-08-22"
updated_at: "2026-08-22"
record_date: "2026-08-22"
date_kind: "scheduled_at"
topics: ["observability","agent-evals","monitoring","classification"]
entities: ["raindrop.ai"]
editorial_format: "brief"
basket_id: "64af3bcb-1c2d-42a9-a664-91510a61d75a"
basket_revision: 1
source_urls: ["https://www.raindrop.ai/blog/signals-2-frontier-classification"]
visual_decision: "text_only"
recovery_incident: "NR-2026-08-15-HERMES-SITE-COPY"
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:raindrop-introduces-signals-2-0-for-frontier-model-classification"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:2bdf833cf212166a07f6f64d15a353833decad17816f63c94b27c9189c9a7019","reviewed_at":"2026-08-15T20:30:00.000Z","source_evidence_count":1,"verified_claim_count":2}
routes: {"html":"https://newruntime.com/posts/raindrop-introduces-signals-2-0-for-frontier-model-classification/","markdown":"https://newruntime.com/posts/raindrop-introduces-signals-2-0-for-frontier-model-classification.md","json":"https://newruntime.com/posts/raindrop-introduces-signals-2-0-for-frontier-model-classification.json"}
---

# Raindrop Signals 2 turns production traces into narrow classifiers

## Retrieval answer

Signals 2 combines deterministic filters, small semantic heads, and selective frontier-model calls for low-latency monitoring.

Raindrop Signals 2 creates narrow binary classifiers from traces produced by live AI applications. A signal can ask whether an agent broke a rule, lost the user's intent, or misused memory, and the input may include multi-turn dialogue, tool calls, and subagent traces.

The system combines deterministic filters, a small semantic classifier, and selective frontier-model calls when uncertainty rises. Raindrop reports median latency around 100 milliseconds and costs up to 1,600 times lower than GPT-5.6 Sol at xhigh effort on its evaluated workloads. Those figures are vendor benchmarks.

The architectural idea is stronger than the headline number: expensive judgment should scale with ambiguity rather than raw traffic. A production monitor can handle common cases cheaply, escalate uncertain examples, and feed reviewed mistakes back into the classifier. That creates an observable drift loop instead of an unlimited LLM-as-judge bill.

## Source

- [Raindrop](https://www.raindrop.ai/blog/signals-2-frontier-classification)