$pip install twosignal

Test, evaluate, and monitor your AI agents

Ship reliable AI with confidence. 2Signal gives you tracing, evaluations, and real-time monitoring — all in one platform.

2Signal / Overview
Total Traces

12,847

+18.2%

Error Rate

2.3%

-0.4%

Avg Latency

245ms

-12ms

Active Evaluators

8

+2 this week

Trace Volume — 30 days
TracesErrors+24.3%
Recent Traces
Trace IDAgentStatusLatency
trc_8f2aCustomerSupportOK312ms
trc_9b1cCodeReviewOK1.2s
trc_a3d7DataAnalysisERROR4.8s
trc_b5e2RAGPipelineOK892ms
trc_c7f4SummarizerOK445ms

0

SDKs

0+

Evaluators

<0

Lines to Instrument

0ms

Latency Overhead

Works with the tools you already use

OpenAI
Anthropic
LangChain
LlamaIndex
CrewAI
Google AI
Mistral
Cohere
Groq
OpenAI
Anthropic
LangChain
LlamaIndex
CrewAI
Google AI
Mistral
Cohere
Groq

Platform

Everything you need to ship reliable AI

From tracing to evaluations to safety guardrails — one platform for the full AI reliability lifecycle.

Tracing

Instrument in 3 lines of code

Add the @observe decorator to any function and 2Signal captures every LLM call, tool invocation, and agent step automatically. Full span trees with latency, cost, and token breakdowns.

Pythonagent.py
1import twosignal as ts2from twosignal import wrap_openai3from openai import OpenAI45ts.init(api_key="ts_...", project="my-agent")6client = wrap_openai(OpenAI())78@ts.observe()9def run_agent(query: str):10    intent = classify_intent(query)11    context = search_knowledge_base(intent)12    response = client.chat.completions.create(13        model="gpt-4o",14        messages=[{"role": "user", "content": query}],15    )16    return response.choices[0].message.content1718run_agent("How do I reset my password?")
Trace Detail
trc_8f2a9b1c
RUNNING
312ms
$0.0042
Span Tree
CustomerSupport.run()
AGENT312ms
classify_intent()
LLM86ms
search_knowledge_base()
TOOL45ms
retrieve_context()
RETRIEVAL38ms
generate_response()
LLM168ms
Evaluations
Groundedness
0.94
Toxicity
0.02
PII Detection
0.00
Relevance
0.88
Latency SLA
1.00
Cost
0.42

Cost Optimization

Cut LLM costs by 30–50%

Route simple queries to smaller, cheaper models automatically. 2Signal analyzes input complexity in real-time and picks the most cost-effective model without sacrificing quality.

  • Complexity-based model routing with fallback chains
  • Per-trace cost tracking across all LLM providers
  • Usage-based optimization recommendations
  • No code changes — configure routing rules in the dashboard
Cost Optimizer — Monthly Summary
SAVINGS FOUNDLast 30 days
Current Spend

$847

With Routing

$423

Savings

50%

Simple queries → GPT-4.1-mini
72% of traffic
Complex queries → GPT-4o
28% of traffic

Safety & Compliance

Safety guardrails built in

Detect prompt injection, PII leaks, toxicity, and bias before they reach your users. Automated alerts when thresholds are breached.

Prompt Injection Detection

Hybrid deterministic + LLM detection catches both known patterns and novel injection attempts.

PII Detection

Automatically flag personally identifiable information leaking through your agent's responses.

Toxicity & Bias

Multi-category bias detection across gender, race, age, disability, and religion with confidence scores.

Compliance Check

Verify agent outputs meet regulatory requirements. Configurable rule sets for your industry.

Evaluators

25+ evaluators, zero config

Run deterministic checks, LLM-as-judge assessments, and safety scans on every trace or in batch. Mix and match to build your quality gate.

Deterministic

ContainsRegex MatchJSON SchemaExact MatchLatency SLACostSimilarityLevenshtein

LLM-based

LLM JudgeGroundednessFactual AccuracyCompliance CheckWorkflow Adherence

Safety

Prompt InjectionPII DetectionToxicityBias DetectionTool Call Validation

How it works

Three steps to reliable AI

01

Instrument

Add the @observe decorator to your agent functions. Every LLM call, tool invocation, and agent step is traced automatically.

02

Evaluate

25+ evaluators auto-run on every trace — deterministic checks, LLM-as-judge, safety scans. No config needed.

03

Ship

Regressions are caught before deploy. Drift detection, alerts, and deployment comparison keep production reliable.

Pricing

Simple, transparent pricing

Start free, scale as you grow. No hidden fees, no surprise bills.

Startup Program: 50% off for 6 months if under $1M ARR. Apply →

Free

$0forever

For side projects and experimentation.

  • 1,000 traces/month
  • 3 evaluators
  • 7-day retention
  • 1 project
  • Community support
Get Started

Pro

$49/month

For developers shipping AI to production.

  • 50,000 traces/month
  • Unlimited evaluators
  • 30-day retention
  • 5 projects
  • Drift detection
  • A/B testing
  • Email support
Start Free Trial
Most Popular

Growth

$79/month

For growing teams with advanced needs.

  • 150,000 traces/month
  • Unlimited evaluators
  • 60-day retention
  • 20 projects
  • Custom dashboards
  • Human review queues
  • Cost optimizer
  • Priority support
Start Free Trial

Team

$149/month

For scaling teams and enterprise workloads.

  • 500,000 traces/month
  • Unlimited evaluators
  • 90-day retention
  • Unlimited projects
  • SSO/SAML
  • RBAC with project-level overrides
  • Audit logs
  • Deployment regression detection
  • Dedicated support
Start Free Trial

Enterprise

Custom trace volumes, unlimited retention, SLA guarantees, dedicated infrastructure, and on-premises deployment options.

Contact Sales

Ready to ship reliable AI agents?

Join thousands of developers who trust 2Signal for testing and monitoring their AI agents. Get started in under 5 minutes.

Free forever for small projects. No credit card required.