Announcing Latitude V2 — an agent issue monitoring platform

A clear path to reliable AI

Production failures become clear signals. Signals become fixes.

80%

Fewer critical errors reaching production

8x

Faster prompt iteration using GEPA (Agrawal et al., 2025)

25%

Accuracy increase in the first 2 weeks

Observability

Capture real inputs, outputs, and context from live traffic. Understand what your system is actually doing, not what you expect it to do.

Full traces

Observe your AI’s behaviour in the most comprehensive way

Usage statistics

Keep track of the token usage and regulate expenses

AI behaviour drifts. Small prompt changes break products in unexpected ways, results get worse and it's hard to tell why. Teams keep tweaking, shipping while hoping the system still works. From hallucinating Your AI to reliable.

Most tools help you see what your AI is doing. The hard part is knowing where it fails and what to change.

Enter the reliability loop

A proven method to understand, evaluate, and fix your AI products

  1. Observability
    Capture real inputs, outputs, and context from live traffic to understand what your system is actually doing

  2. Annotations
    Annotate responses with real human judgment. Turn intent into a signal the system can learn from.

  3. Error analysis
    Automatically group failures into recurring issues, detect common failure modes and keep an eye on escalating issues.

  4. Automatic evals
    Convert real failure modes into evals that run continuously & catch regressions before they reach users.

  5. Prompt manager + optimizer
    Automatically test prompt variations against real evals, then let the system optimize prompts using GEPA to reduce failures over time.

Get started now

Start with visibility. Grow into reliability.

Start the reliability loop with lightweight instrumentation. Go deeper when you’re ready.

Providers

  • OpenAI
  • Anthropic
  • Azure
  • Google AI Platform
  • Amazon Bedrock
  • Cohere
  • Together AI
  • Vertex AI
  • Gemini
  • Groq
  • Mistral AI
  • Ollama
  • LiteLLM
  • Replicate
  • AWS SageMaker
  • Hugging Face Transformers
  • Aleph Alpha
  • IBM watsonx.ai
import { LatitudeTelemetry } from '@latitude-data/telemetry'
import OpenAI from 'openai'

const telemetry = new LatitudeTelemetry(
  process.env.LATITUDE_API_KEY,
  { instrumentations: { openai: OpenAI } }
)

async function generateSupportReply(input: string) {
  return telemetry.capture(
    {
      projectId: 123, // The ID of your project in Latitude
      path: 'generate-support-reply', // Add a path to identify this prompt in Latitude
    },
    async () => {
      const client = new OpenAI()
      const completion = await client.chat.completions.create({
        model: 'gpt-4o',
        messages: [{ role: 'user', content: input }],
      })
      return completion.choices[0].message.content
    }
  )
}

Instrument once

Add OTEL-compatible telemetry to your existing LLM calls to capture prompts, inputs, outputs, and context. This gets the loop running and gives you visibility from day one.

Learn from production

Review traces, add feedback, and uncover failure patterns as your system runs. Steps 1–4 of the loop work out of the box.

Go further when it matters

Use Latitude as the source of truth for your prompts to enable automatic optimization and close the loop. The full reliability loop, when you’re ready.

Build AI you can trust

Works with Vercel AI SDK, LangChain, OpenAI SDK, and most common model providers.

Frequently asked questions

  • What is Latitude?
  • How can I see where my AI fails in production?
  • Is it easy to set up evals in Latitude?
  • How does Latitude turn AI failures into improvements?
  • Does Latitude work with our existing stack?

Build reliable AI.