Multi-step LLM workflow timeout

What engineers usually see

  • •Workflow with multiple LLM calls times out
  • •Cannot identify which step was slow
  • •Total latency exceeds acceptable threshold
  • •No per-step timing breakdown

Why this is hard to debug

Multi-step workflows accumulate latency. You can't see which step contributed most without instrumentation. Receipts show timing for each LLM call in the workflow.

Minimal repro

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_OPENAI_KEY',
  baseURL: 'https://aibadgr.com/v1'
});

// Step 1: Analyze input
const analysis = await client.chat.completions.create({
  model: 'gpt-4o-mini',
  messages: [{role: 'user', content: 'Analyze: ...'}]
});

// Step 2: Generate response
const response = await client.chat.completions.create({
  model: 'gpt-4o-mini',
  messages: [{role: 'user', content: 'Based on analysis...'}]
});

This request routes through AI Badgr and returns a stable request ID that links to an execution record.

Note: AI Badgr is OpenAI-compatible and works as a drop-in proxy. No SDK changes required — only the base_url changes.

What a per-request execution record makes visible

  • Latency per workflow step
  • Which step was slowest
  • Cumulative workflow latency
  • Parallelization opportunities
  • Timeout optimization suggestions

Run 1 request → get receipt

Change your base URL to https://aibadgr.com/v1 and run your request.

The response includes an X-Badgr-Request-Id header that links to a receipt showing latency, retries, tokens, cost, and failure stage for that specific execution.

Get API Key

Not the engineer?
Share this page with your dev and ask them to run one request through AI Badgr. That's all that's needed to get the receipt.

This kind of thing only makes sense when you can actually see what happened to a single request from start to finish, instead of trying to piece it together from scattered logs.