{
  "id": 16012917,
  "title": "Steer, Don’t Rewrite: Annotate Agent Trajectories 2 Faster in Live Environments with onPanda",
  "url": "https://urgent.news/2026/10/22/steer-dont-rewrite-annotate-agent-trajectories-2-faster-in-live",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-10-22T07:12:28.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/diyer22/steer-dont-rewrite-annotate-agent-trajectories-2x-faster-in-live-environments-with-onpanda-56o8"
  },
  "original_language": "en",
  "account": "onPanda is an open-source LLM alignment data annotation tool that simplifies the process of annotating multi-turn agent trajectories in live environments. Unlike existing agent annotation tools, onPanda enables annotators to edit reasoning, content, and tool_calls in real-time, rather than rewriting outputs after the fact. This approach offers several advantages, including faster annotation, high-quality preference data, and fine-grained token-level supervision.",
  "summary": "Dynamically connect to agent environments and annotate multi-turn SFT and preference data with tool_calls and reasoning online Existing agent annotation tools (such as Potato and Argilla ) mostly support assigning attributes or adding textual feedback to completed trajectories. However, editing trajectories to construct high-quality multi-turn agent SFT data presents two core challenges: Coupled…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}