Let an agent investigate and act You give a typed task an iterative runtime where the model can inspect evidence, call tools, and delegate. It still finishes through your declared output contract. go academy academy/topics/agent-core website/content-src/academy/course.mjs academy Let an agent investigate and act
ax
Go github.com/ax-llm/ax/packages/go
TypeScript Python Java C++ Go Rust
Unit 5 · Build an agent that can use tools

Let an agent investigate and act

You give a typed task an iterative runtime where the model can inspect evidence, call tools, and delegate. It still finishes through your declared output contract.

agent()8 focused minutesNot started
Unit example (nearest native match)

See the idea in context

helper := axllm.NewAgent("question:string -> answer:string", nil)
  1. Declare the whole task

    The signature keeps the request and final resolution typed.

  2. Provide allowed capabilities

    functions limits the tools the runtime may choose.

  3. Start one agent run

    forward() lets the agent inspect, act, and finish with a resolution.

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/short-agents/tools_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