{
  "schema_version": "1.1",
  "id": "archive:https://www.youtube.com/watch?v=7GMKdpLsxwU",
  "slug": "the-missing-layer-design-taste-in-ai-agents-hassan-el-mghari-together-ai-00err2g",
  "url": "https://feed7.dev/p/the-missing-layer-design-taste-in-ai-agents-hassan-el-mghari-together-ai-00err2g",
  "title": "The Missing Layer: Design Taste in AI Agents — Hassan El Mghari, Together AI",
  "why_included": "Treat an agent’s first UI as a draft: encode recurring design dislikes, supply visual references, split work into focused prompts, and reserve time for iteration.",
  "summary": "Hallmark encodes recurring AI-generated UI patterns to avoid and supplies theme references; the speaker says **over 10,000 people** tried it. He recommends spending another **10–20%** on UI refinement and showed GLM 5.2 iteration beside an Opus result that cost **five times as much**.",
  "practical_implication": "Keep design preferences in a reusable skill or agent file, attach screenshots and references, and describe the user and interaction in detail. Build a base, then iterate feature by feature, using a sufficiently capable faster model where it fits.",
  "agent_context": "Hallmark encodes recurring AI-generated UI patterns to avoid and supplies theme references; the speaker says **over 10,000 people** tried it. He recommends spending another **10–20%** on UI refinement and showed GLM 5.2 iteration beside an Opus result that cost **five times as much**.\n\nKeep design preferences in a reusable skill or agent file, attach screenshots and references, and describe the user and interaction in detail. Build a base, then iterate feature by feature, using a sufficiently capable faster model where it fits.\n\nThe visual comparisons were selected demos rather than a systematic design evaluation. Avoiding familiar gradients or typography can remove obvious tells, but it does not by itself establish usability, accessibility, or a coherent product identity.",
  "source": {
    "name": "AI Engineer",
    "url": "https://www.youtube.com/watch?v=7GMKdpLsxwU",
    "published_at": "2026-08-21T15:00:06.000Z"
  },
  "source_class": "video",
  "content_type": "Video",
  "layer": "craft",
  "domains": [
    "coding"
  ],
  "topics": [
    "design-engineering",
    "interface-quality",
    "skills"
  ],
  "verification": {
    "status": "source_linked",
    "label": "Source Linked",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "The visual comparisons were selected demos rather than a systematic design evaluation. Avoiding familiar gradients or typography can remove obvious tells, but it does not by itself establish usability, accessibility, or a coherent product identity."
  ],
  "connected_context": {
    "meaning": "This confirms portable design skills as a practical way to steer agents away from recurring generic UI patterns, while adding an iterative workflow and a claimed cost-capability tradeoff between models. Against the prior candidates, it does not establish design quality as a universal checklist: selected demos and pattern avoidance still leave usability, accessibility, brand coherence, and subjective evaluation unresolved.",
    "corpus_size": 545,
    "generated_at": "2026-08-23T18:04:57.010Z",
    "connections": [
      {
        "title": "Nutlope/hallmark",
        "source_name": "GitHub",
        "source_url": "https://github.com/Nutlope/hallmark",
        "feed7_url": "https://feed7.dev/p/hallmark-0f5n823",
        "reason": "The talk supplies usage and workflow context for Hallmark’s installable themes, critique rules, and generated-UI checks, while retaining the repository’s narrow focus on recurring patterns."
      },
      {
        "title": "Ending AI Slop — Thais Castello Branco, Taste Labs",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=lCBf9slCanI",
        "feed7_url": "https://feed7.dev/p/ending-ai-slop-thais-castello-branco-taste-labs-1bcbp7n",
        "reason": "Taste Labs explains why Hallmark-style explicit constraints can check some design properties, while style and creativity still require audience-specific human preference evidence."
      },
      {
        "title": "cathrynlavery/diagram-design",
        "source_name": "GitHub",
        "source_url": "https://github.com/cathrynlavery/diagram-design",
        "feed7_url": "https://feed7.dev/p/diagram-design-1456lje",
        "reason": "Diagram Design demonstrates the same portable-skill approach in a narrower domain, extending taste constraints with explicit branding and accessibility requirements."
      },
      {
        "title": "Prototyping as Leadership: How a CTO Ships with AI Agents — Hursh Agrawal, The Browser Company",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=bdHaOXZOhcM",
        "feed7_url": "https://feed7.dev/p/prototyping-as-leadership-how-a-cto-ships-with-ai-agents-hursh-agrawal-t-1f1csz2",
        "reason": "The recommendation to build a base and refine feature by feature aligns with bounded agent work followed by personal testing and review, keeping design ownership with the human."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-08-21T15:00:06.000Z",
  "modified_at": "2026-08-21T15:00:06.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/the-missing-layer-design-taste-in-ai-agents-hassan-el-mghari-together-ai-00err2g",
    "json": "https://feed7.dev/p/the-missing-layer-design-taste-in-ai-agents-hassan-el-mghari-together-ai-00err2g.json",
    "markdown": "https://feed7.dev/p/the-missing-layer-design-taste-in-ai-agents-hassan-el-mghari-together-ai-00err2g.md"
  }
}