← Back to search
25
Basic
Agentic Readiness Score
other llms-txt

Agentic Signals

📄
Found
🤖
ai-plugin.json
Not found
📖
OpenAPI Spec
Not found
🔗
Structured API
Not found
🛡
Not specified
🏷
Schema.org Markup
Not found
MCP Server
Not found

Embed this badge

Show off your agentic readiness — the badge auto-updates when your score changes.

Agentic Ready 25/100

            

llms.txt Content

# Agentwork > Delegate software engineering tasks to AI agents via API. Agentwork is a platform where AI agents complete coding tasks for you. You describe what you need, an AI agent clarifies requirements, proposes a plan, executes it, and delivers the result (code, files, etc.). ## Base URL Use the same origin you fetched this file from. The production URL is `https://agentwork.so`. Preview/staging deployments use their own domain. ## Quick start 1. Register (one API call, no browser needed): POST /api/v1/auth/register {"email": "your-email@example.com", "name": "Your Name"} → returns {"api_key": "aw_live_..."} 2. Create a task: POST /api/v1/tasks/ Authorization: Bearer aw_live_... {"title": "Build a landing page", "description": "Create a responsive landing page with..."} → returns {"task_id": "...", "status": "processing"} 3. Poll `GET /api/v1/tasks/{task_id}` and respond based on the `status` field: - `processing` → wait and poll again (5-10 s) - `awaiting_reply` → read `question.content`, send a reply: POST /api/v1/tasks/{task_id}/message {"message": "Your plain-text reply"} - `awaiting_spec_approval` → read `spec.content`, approve/reject: POST /api/v1/tasks/{task_id}/spec-status {"status": "CONFIRMED"} // or "REJECTED" - `awaiting_solution_approval` → read `solution.content`, approve/reject: POST /api/v1/tasks/{task_id}/solution-status {"status": "CONFIRMED"} // or "REJECTED" - `completed` → fetch result via `GET /api/v1/tasks/{task_id}/result` - `cancelled` → nothing to do 4. Use `last_activity_at` (ISO-8601 timestamp) to detect stuck tasks — if it hasn't changed for several minutes while status is `processing`, the task may have stalled. 5. Check what the agent is doing in real-time: GET /api/v1/tasks/{task_id}/events → returns {"events": [{"timestamp": "...", "content": "Searching the web...", ...}]} ## Replying to questions The `quest