{
  "schema_version": "1.1",
  "id": "atlas-prompting",
  "slug": "prompting",
  "title": "Prompting",
  "url": "https://feed7.dev/atlas/prompting",
  "current_answer": null,
  "implementation_consequence": null,
  "agent_context": null,
  "confidence": "auto_collected",
  "last_verified": null,
  "last_updated": null,
  "evidence": [
    {
      "schema_version": "1.1",
      "id": "auto-3518047f01",
      "slug": "how-evals-and-prompts-shape-agent-behavior-preetika-bhat-3518047f01",
      "url": "https://feed7.dev/p/how-evals-and-prompts-shape-agent-behavior-preetika-bhat-3518047f01",
      "title": "How Evals and Prompts Shape Agent Behavior — Preetika Bhateja & Daniel Bump, YouTube Ads",
      "why_included": "Start with a few core tasks, inspect traces, change one component at a time, and protect a separate test set.",
      "summary": "Production agent behavior should be improved through a loop of tool design, small eval sets, trace review, and calibrated judges—not prompt tweaks based on one bad run.",
      "practical_implication": "Build evals early, inspect traces, and change one prompt, tool, rubric, or model component at a time. Compare human and LLM ratings, maintain a high-agreement golden set, and use ablations to establish whether a change actually improves the agent.",
      "agent_context": "The YouTube Ads team recommends optimizing a focused set of agent tools before larger evals, then starting with **a few core tasks** and testing both desired behavior and prohibited actions. Explanations help diagnose multi-dimensional outcomes such as accuracy and brand safety.\n\nBuild evals early, inspect traces, and change one prompt, tool, rubric, or model component at a time. Compare human and LLM ratings, maintain a high-agreement golden set, and use ablations to establish whether a change actually improves the agent.\n\nDo not tune against isolated nondeterministic failures. Keep a sparingly used **test set**, refresh it with production data, monitor judge disagreement, and define launch gates before iteration makes the rubric a moving target.",
      "source": {
        "name": "AI Engineer",
        "url": "https://www.youtube.com/watch?v=xyL2Ltkh-SA",
        "published_at": "2026-07-24T00:00:00.000Z"
      },
      "source_class": "video",
      "content_type": "Video",
      "layer": "benchmark",
      "domains": [
        "coding"
      ],
      "topics": [
        "agent-evals",
        "agent-reliability",
        "prompting"
      ],
      "verification": {
        "status": "source_linked",
        "label": "Source Linked",
        "method": "source_feed",
        "verified_at": null
      },
      "uncertainty": [],
      "connected_context": null,
      "lifecycle": "New",
      "published_at": "2026-07-24T00:00:00.000Z",
      "modified_at": "2026-07-24T00:00:00.000Z",
      "supersedes": [],
      "expires_at": null,
      "formats": {
        "html": "https://feed7.dev/p/how-evals-and-prompts-shape-agent-behavior-preetika-bhat-3518047f01",
        "json": "https://feed7.dev/p/how-evals-and-prompts-shape-agent-behavior-preetika-bhat-3518047f01.json",
        "markdown": "https://feed7.dev/p/how-evals-and-prompts-shape-agent-behavior-preetika-bhat-3518047f01.md"
      }
    }
  ],
  "conflicting_sources": [],
  "superseded_claims": [],
  "corpus_evidence": [
    {
      "title": "AISPA: User-Centric System Prompt Auditing for Large Language Model Applications",
      "url": "https://arxiv.org/abs/2607.28617v1",
      "source_name": "arXiv",
      "published_at": "2026-07-30T17:58:58+00:00",
      "summary": "AISPA turns system-prompt review into an eight-dimension audit. Its survey suggests builders should test prompts for user protection and conflicting instructions, not merely check that safeguards exist."
    },
    {
      "title": "Persona Engineering: A Field Guide to AI Synthetic Personas — Ishan Anand, InsightSciences.ai",
      "url": "https://www.youtube.com/watch?v=YnNF55QV0zs",
      "source_name": "AI Engineer",
      "published_at": "2026-07-29T20:15:35+00:00",
      "summary": "Synthetic personas can extend existing research, but they are forecasts, not extra respondents. Ground prompts richly and validate each setup against human data before using it."
    },
    {
      "title": "The Unreasonable Effectiveness of Separating the Task from the Model — Maxime Rivest & Isaac Miller",
      "url": "https://www.youtube.com/watch?v=GgLQ02aO-hs",
      "source_name": "AI Engineer",
      "published_at": "2026-07-23T17:45:06+00:00",
      "summary": "DSPy separates an AI task’s contract from its model, prompt, tools, and harness, letting builders swap or optimize implementations while holding behavior against the same evals."
    },
    {
      "title": "How Temperature Shapes Ideological Discourse in Retrieval-Augmented Generation?",
      "url": "https://arxiv.org/abs/2607.11783v1",
      "source_name": null,
      "published_at": null,
      "summary": "A RAG study finds that retrieved ideology carries into answers and varies with sampling temperature, so source audits and decoding tests should be evaluated together."
    },
    {
      "title": "asgeirtj/system_prompts_leaks",
      "url": "https://github.com/asgeirtj/system_prompts_leaks",
      "source_name": null,
      "published_at": null,
      "summary": "A maintained archive of extracted system prompts from 100+ AI products — Claude Fable 5, Claude Code, ChatGPT 5.5, Gemini, Cursor — useful for studying how vendors actually instruct their agents."
    },
    {
      "title": "Direct agents with visual prompts in Design Mode",
      "url": "https://cursor.com/blog/design-mode",
      "source_name": null,
      "published_at": null,
      "summary": "Cursor's Design Mode lets you prompt agents visually in a running app: click or multi-select elements, draw annotations on a frozen frame, or narrate by voice; the agent gets each element's xpath, props, and styles."
    }
  ]
}