Mulai dengan Claude Managed Agents

Concept	Description
Agent	The model, system prompt, tools, MCP servers, and skills
Environment	A configured container template (packages, network access)
Session	A running agent instance within an environment, performing a specific task and generating outputs
Events	Messages exchanged between your application and the agent (user turns, tool results, status updates)

Concept	Description
Agent	The model, system prompt, tools, MCP servers, and skills
Environment	A configured container template (packages, network access)
Session	A running agent instance within an environment, performing a specific task and generating outputs
Events	Messages exchanged between your application and the agent (user turns, tool results, status updates)

Buat agen

Buat agen yang mendefinisikan model, system prompt, dan alat yang tersedia.

set -euo pipefail

agent=$(
  curl -sS --fail-with-body https://api.anthropic.com/v1/agents \
    -H "x-api-key: $ANTHROPIC_API_KEY" \
    -H "anthropic-version: 2023-06-01" \
    -H "anthropic-beta: managed-agents-2026-04-01" \
    -H "content-type: application/json" \
    -d @- <<'EOF'
{
  "name": "Coding Assistant",
  "model": "claude-sonnet-4-6",
  "system": "You are a helpful coding assistant. Write clean, well-documented code.",
  "tools": [
    {"type": "agent_toolset_20260401"}
  ]
}
EOF
)

AGENT_ID=$(jq -er '.id' <<<"$agent")
AGENT_VERSION=$(jq -er '.version' <<<"$agent")

echo "Agent ID: $AGENT_ID, version: $AGENT_VERSION"

Tipe alat agent_toolset_20260401 mengaktifkan kumpulan lengkap alat agen bawaan (bash, operasi file, pencarian web, dan lainnya). Lihat Alat untuk daftar lengkap dan opsi konfigurasi per alat.

Simpan agent.id yang dikembalikan. Anda akan merujuknya di setiap sesi yang Anda buat.

Buat lingkungan
Lingkungan mendefinisikan kontainer tempat agen Anda berjalan.
Mulai sesi
Buat sesi yang merujuk agen dan lingkungan Anda.
Kirim pesan dan streaming respons
Buka stream, kirim event pengguna, lalu proses event saat tiba:

environment=$(
  curl -sS --fail-with-body https://api.anthropic.com/v1/environments \
    -H "x-api-key: $ANTHROPIC_API_KEY" \
    -H "anthropic-version: 2023-06-01" \
    -H "anthropic-beta: managed-agents-2026-04-01" \
    -H "content-type: application/json" \
    -d @- <<'EOF'
{
  "name": "quickstart-env",
  "config": {
    "type": "cloud",
    "networking": {"type": "unrestricted"}
  }
}
EOF
)

ENVIRONMENT_ID=$(jq -er '.id' <<<"$environment")

echo "Environment ID: $ENVIRONMENT_ID"

session=$(
  curl -sS --fail-with-body https://api.anthropic.com/v1/sessions \
    -H "x-api-key: $ANTHROPIC_API_KEY" \
    -H "anthropic-version: 2023-06-01" \
    -H "anthropic-beta: managed-agents-2026-04-01" \
    -H "content-type: application/json" \
    -d @- <<EOF
{
  "agent": "$AGENT_ID",
  "environment_id": "$ENVIRONMENT_ID",
  "title": "Quickstart session"
}
EOF
)

SESSION_ID=$(jq -er '.id' <<<"$session")

echo "Session ID: $SESSION_ID"

# Send the user message first; the API buffers events until the stream attaches
curl -sS --fail-with-body \
  "https://api.anthropic.com/v1/sessions/$SESSION_ID/events" \
  -H "x-api-key: $ANTHROPIC_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "anthropic-beta: managed-agents-2026-04-01" \
  -H "content-type: application/json" \
  -d @- >/dev/null <<'EOF'
{
  "events": [
    {
      "type": "user.message",
      "content": [
        {
          "type": "text",
          "text": "Create a Python script that generates the first 20 Fibonacci numbers and saves them to fibonacci.txt"
        }
      ]
    }
  ]
}
EOF

# Open the SSE stream and process events as they arrive
while IFS= read -r line; do
  [[ $line == data:* ]] || continue
  json=${line#data: }
  case $(jq -r '.type' <<<"$json") in
    agent.message)
      jq -j '.content[] | select(.type == "text") | .text' <<<"$json"
      ;;
    agent.tool_use)
      printf '\n[Using tool: %s]\n' "$(jq -r '.name' <<<"$json")"
      ;;
    session.status_idle)
      printf '\n\nAgent finished.\n'
      break
      ;;
  esac
done < <(
  curl -sS -N --fail-with-body \
    "https://api.anthropic.com/v1/sessions/$SESSION_ID/stream" \
    -H "x-api-key: $ANTHROPIC_API_KEY" \
    -H "anthropic-version: 2023-06-01" \
    -H "anthropic-beta: managed-agents-2026-04-01" \
    -H "Accept: text/event-stream"
)

I'll create a Python script that generates the first 20 Fibonacci numbers and saves them to a file.
[Using tool: write]
[Using tool: bash]
The script ran successfully. Let me verify the output file.
[Using tool: bash]
fibonacci.txt contains the first 20 Fibonacci numbers (0 through 4181).

Agent finished.

Mulai dengan Claude Managed Agents

Konsep inti

Prasyarat

Instal CLI

Mulai dengan Claude Managed Agents

Konsep inti

Prasyarat

Instal CLI

Instal SDK

Buat sesi pertama Anda

Yang terjadi

Langkah selanjutnya