Built for AI agents. Friendly to humans too.

curl https://automatebusinessnow.com/api/v1/employees \
  -H "Authorization: Bearer abn_YOUR_KEY_HERE"

curl https://automatebusinessnow.com/api/v1/chat \
  -H "Authorization: Bearer abn_YOUR_KEY_HERE" \
  -H "Content-Type: application/json" \
  -H "X-Request-ID: req_your_trace_id_123" \
  -d '{
    "employeeSlug": "copywriter",
    "prompt": "Visitor asks whether Detroit Auto Parts has brake pads in stock",
    "latencyProfile": "website_chat",
    "responseFormat": "plain_text",
    "stream": true
  }'

Use latencyProfile: "website_chat" plus responseFormat: "plain_text" for website chat widgets. This keeps replies short and optimized for live storefront response time. Every chat response includes requestId, latencyMs, and the X-ABN-Request-ID header for support debugging. Set stream: true or send Accept: text/event-stream to receive start, text, done, or error SSE events.

curl https://automatebusinessnow.com/api/v1/app-agents/chat \
  -H "Authorization: Bearer abn_YOUR_KEY_HERE" \
  -H "Content-Type: application/json" \
  -H "X-ABN-End-User-ID: visitor_hash_123" \
  -H "X-Request-ID: req_payroll_george_001" \
  -d '{
    "agent": {
      "name": "George",
      "instructions": "You are the payroll app assistant. Use payroll tools for payroll facts. Never invent pay numbers."
    },
    "messages": [
      { "role": "user", "content": "Why is Maria's net pay lower this run?" }
    ],
    "tools": [
      {
        "name": "get_employee_paycheck",
        "description": "Fetch paycheck details for an employee in a pay run.",
        "input_schema": {
          "type": "object",
          "additionalProperties": false,
          "properties": {
            "employee_id": { "type": "string" },
            "payrun_id": { "type": "string" }
          },
          "required": ["employee_id", "payrun_id"]
        }
      }
    ],
    "context": {
      "tenant_id": "company_123",
      "screen": "payrun_detail",
      "payrun_id": "run_456"
    }
  }'

Use /api/v1/app-agents/chat when the assistant belongs to your product, not to ABN. Your backend sends messages and tool schemas. ABN returns requires_action with tool calls when data is needed. Your backend executes the tool, appends a tool_result block, then calls ABN again for the final answer.

curl https://automatebusinessnow.com/api/v1/images \
  -H "Authorization: Bearer abn_YOUR_KEY_HERE" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A pixel-art mushroom on cream paper",
    "aspectRatio": "1:1",
    "quality": "high",
    "style": "illustration"
  }'

Pass prompt, aspectRatio, quality, and style; ABN selects the right model internally. The API is capability-native, not model-native - that's the whole point.

curl https://automatebusinessnow.com/api/v1/voice/synthesize \
  -H "Authorization: Bearer abn_YOUR_KEY_HERE" \
  -H "Content-Type: application/json" \
  -o spoken.mp3 \
  -d '{
    "text": "Hi there, thanks for calling Hearth Coffee.",
    "voice": "warm-female",
    "format": "mp3",
    "model": "fast"
  }'

Catalog voices: warm-female, deep-male, energetic-female, british-male, young-female, podcast-host. Stream returns audio/mpeg or audio/L16 (PCM 16kHz) for voice-agent pipelines. Billed at 1 credit per 50 characters (model: "fast") or 1 credit per 25 characters (model: "quality"). Use the ABN catalog voice keys shown here.

curl https://automatebusinessnow.com/api/v1/voice/transcribe \
  -H "Authorization: Bearer abn_YOUR_KEY_HERE" \
  -F "audio=@recording.mp3" \
  -F "language=en"

Returns text + word-level timestamps. Accepts mp3, wav, m4a, ogg, webm up to 25 MB. Add -F "diarize=true" for speaker labels. Billed at 1 credit per 2 seconds of audio.