See failures, cost, and latency in production You add traces, usage and cost accounting, cache policy, cancellation, bounded retries, and safe logs. Debug output becomes evidence for tests and operations. go academy academy/topics/production-observability website/content-src/academy/course.mjs academy See failures, cost, and latency in production
Unit 11 · Ship AI systems you can operate

See failures, cost, and latency in production

You add traces, usage and cost accounting, cache policy, cancellation, bounded retries, and safe logs. Debug output becomes evidence for tests and operations.

9 focused minutesNot started
Unit example (nearest native match)

See the idea in context

program := axllm.NewAx("text:string -> label:string", nil)
usage := program.GetUsage()
  1. Trace the run

    tracer connects model and tool activity to the surrounding request.

  2. Make cancellation possible

    abortSignal lets callers stop work that is no longer useful.

  3. Control repeated work

    contextCache makes reuse an explicit operational policy.

Run itIn your own project
go get github.com/ax-llm/ax/packages/go

import axllm "github.com/ax-llm/ax/packages/go"

client := axllm.NewAI("openai", map[string]axllm.Value{"apiKey": os.Getenv("OPENAI_API_KEY")})
classify := axllm.NewAx("review:string -> sentiment:class \"positive, negative, neutral\"", nil)

Set OPENAI_APIKEY in your environment before running provider-backed code.

In the ax repo

From a clone of the ax repo:

npm run example -- go src/examples/go/long-agents/smart_defaults_agent.go
Active practice

Show that you can use it

Answer 2 in a row to learn this · attempt 1
Keep exploring

Source-backed follow-up