[
  {
    "id": "agent-work-is-becoming-supervisory",
    "data": {
      "observation": "Agent work is becoming supervisory: the scarce act is increasingly deciding what to ask, inspect, accept, or redirect, not typing the implementation.",
      "observed": "2026-05-15T00:00:00.000Z",
      "source": "Tom",
      "context": "Pattern noticed while using desktop and cloud coding agents across this repository.",
      "related_claims": [],
      "related_thoughts": [
        "thoughts/agent-harness-is-the-new-ide"
      ],
      "related_projects": [
        "projects/thinkinglabs"
      ],
      "tags": [
        "agents",
        "workflows"
      ]
    },
    "body": "The work still contains engineering judgment, but the high-friction motion has shifted. I spend more of the loop shaping the task boundary, reviewing diffs, and deciding whether the output deserves to become source."
  },
  {
    "id": "frontier-models-follow-complex-instructions",
    "data": {
      "observation": "Frontier models such as GPT-5.5 and Claude Opus 4.7 are now good enough at detailed, complex instruction following that a well-structured harness can behave like a practical workflow engine.",
      "observed": "2026-05-21T00:00:00.000Z",
      "source": "Tom",
      "context": "Noticed while configuring an internal prototypes repository whose agent harness owns setup, GitHub checks, app configuration, commits, pushes, and validation.",
      "related_claims": [],
      "related_thoughts": [
        "thoughts/agent-harnesses-are-state-machines"
      ],
      "related_projects": [
        "projects/agent-harness"
      ],
      "tags": [
        "agents",
        "frontier-models",
        "harnesses",
        "workflows"
      ]
    },
    "body": "The model capability matters, but the harness is the multiplier. Detailed skills let broad instructions decompose into domain-specific operating procedures, so the agent can follow a long workflow without the top-level prompt becoming unreadable."
  },
  {
    "id": "github-scaling-pressure-from-agent-generated-repos",
    "data": {
      "observation": "GitHub has scaling pressure that can show up as a broken experience through intermittent errors, and agent-generated repository volume is one likely contributor.",
      "observed": "2026-05-15T00:00:00.000Z",
      "source": "Tom",
      "context": "Read-mode note: OpenClaw-like workflows, autonomous research loops, and independent prototyping can generate large numbers of repositories, pushing GitHub in ways that feel visible at the product edge.",
      "related_claims": [],
      "related_thoughts": [
        "thoughts/agent-harnesses-will-move-onto-the-shelf"
      ],
      "related_projects": [],
      "tags": [
        "agents",
        "github",
        "infrastructure",
        "workflows"
      ]
    },
    "body": "The failure mode is not just individual users creating more projects. Agents make repo creation cheap enough that experimentation, research scaffolding, and autonomous prototyping can produce a much larger tail of repositories, branches, issues, and automation events than the pre-agent workflow implied."
  }
]