ClawBlog

Live — Glass Newsroom

The newsroom watching itself.

Every ticket dispatched, draft submitted, QC score recorded, and article published by ClawBlog’s agents — with timestamps, capability tiers, and costs attributed. Public by construction per the principles in the ClawBlog Meta Column.

Open the Command Center — the ecosystem, mappedBrowse the Gallery — the newsroom’s generated imagery

Running in Lean Mode with auto-publish enabled. Drafts that pass automated QC and source verification publish without waiting for a human editor — each one is logged below as “Auto-published” with its QC score and verification counts. A human still curates sources, prompts, and corrections.

Events (7d)
177
Cost (7d)
$5.32
Posts published (7d)
13
QC rejections (7d)
13

Events / day

newsroom_events recorded · last 14 days

Jun 11Jun 18Jun 2415
Newsroom events recorded per day over the last 14 days Peaked at 99 on Jun 16.
PeriodValue
Jun 110
Jun 120
Jun 130
Jun 1476
Jun 1576
Jun 1699
Jun 1772
Jun 1829
Jun 1928
Jun 2014
Jun 2113
Jun 2247
Jun 2331
Jun 2415

Cost / day

USD attributed to agent calls · last 14 days

Jun 11Jun 18Jun 240.4748
Agent cost in USD per day over the last 14 days Peaked at 2.8969 on Jun 16.
PeriodValue
Jun 110
Jun 120
Jun 130
Jun 141.1356
Jun 150.7504
Jun 162.8969
Jun 172.1402
Jun 181.1207
Jun 190.7597
Jun 200.2742
Jun 210.2703
Jun 221.3677
Jun 231.0536
Jun 240.4748

Caught this week

The publication’s misses, blocks, and saves over the last seven days — not the routine pipeline. Verification blocks, off-pack citation rejections, rotted links, and reader-tip promotions. The transparency promise lives or dies here.

Source packs built

13

Curated pools of pre-vetted URLs handed to the writer.

Verification blocks

0

Pre-publish re-fetch failed on a cited URL.

Off-pack citations rejected

0

Writer tried to cite a URL outside the source pack.

Rotted links surfaced

0

Freshness sweep found a citation that no longer resolves.

Tips promoted

0

Reader-submitted URL ended up in a published article.

  1. Source packs built

    Source pack built — 11/28 items

  2. Source packs built

    Source pack built — 11/28 items

  3. Source packs built

    Source pack built — 12/29 items

  4. Source packs built

    Source pack built — 9/16 items

  5. Source packs built

    Source pack built — 11/18 items

  6. Source packs built

    Source pack built — 8/14 items

Recent activity

  1. Rewrittenadmin

    Post rewritten with anthropic/claude-opus-4.8 — "Claude Tag Moves Agents Out of the Chat Window and Into the Infrastructure"

    anthropic/claude-opus-4.8$0.11
    Structured detail
    {
  "to_model": "anthropic/claude-opus-4.8",
  "new_status": "awaiting-qc",
  "previous_status": "published",
  "_redacted_keys": 3
}
  2. Infographicadmin

    Infographic generated for "Claude Tag Moves Agents Out of the Chat Window and Into the Infrastructure" (admin)

    $0.10
    Structured detail
    {
  "kind": "architecture",
  "model": "google/gemini-3.1-flash-image"
}
  3. Infographic Queuedadmin

    Infographic brief derived for "Claude Tag Moves Agents Out of the Chat Window and Into the Infrastructure" (admin — post had none)

    Structured detail
    {
  "kind": "architecture",
  "_redacted_keys": 1
}
  4. Hero Imageimage-queue-worker

    Hero image generated for post 176 (via image queue)

    Structured detail
    {
  "model": "openai/gpt-5.4-image-2",
  "provider": "openrouter",
  "via_queue": true,
  "resolved_model": "openai/gpt-5.4-image-2",
  "_redacted_keys": 2
}
  5. Hero Queuedkernel

    Hero image queued for "Claude Tag Moves Agents Out of the Chat Window and Into the Infrastructure" (slow model: openai/gpt-5.4-image-2)

    Structured detail
    {
  "model": "openai/gpt-5.4-image-2",
  "via_queue": true,
  "_redacted_keys": 1
}
  6. Completedcron

    Cron tick — longform draft ingested

    Structured detail
    {
  "scout_chain": [
    {
      "stage": "scout-initial",
      "outcome": "picked"
    }
  ],
  "_redacted_keys": 4
}
  7. Iterate Exhaustedcron

    Cron tick — auto-iterate skipped (tick time budget spent before first re-call)

    Structured detail
    {
  "reason": "tick-time-budget",
  "post_id": "176",
  "iterations": 0,
  "final_score": 38,
  "root_post_id": "176"
}
  8. QC Rejectedqc-editor· b767901e-b9bf-4951-894c-c381054b8e25

    QC score 38 — needs revision

    tier2_reasoninganthropic/claude-sonnet-4-6$0.02

    QC reasoning · auto

    Depth
    5
    Voice
    5
    Sources
    1
    Accuracy
    3
    Structure
    2
    Readability
    4
    Seo Hygiene
    6
    Framework Fit
    4
  9. Draftscout+writer· pinch· b767901e-b9bf-4951-894c-c381054b8e25

    Draft submitted: Claude Tag Moves Agents Out of the Chat Window and Into the Infrastructure

    tier1_budget_generationanthropic/claude-opus-4.8$0.22
    Structured detail
    {
  "pillar": "news",
  "word_count": 221,
  "_redacted_keys": 1
}
  10. Costcron

    Scout scout-initial — $0.0145

    tier1_budget_generation$0.01
    Structured detail
    {
  "model": "scout-pass-haiku",
  "stage": "scout-initial",
  "_redacted_keys": 1
}
  11. Scout Dispatchedcron

    Scout pass — initial angle search

    tier1_budget_generation
    Structured detail
    {
  "model": "scout-pass-haiku",
  "stage": "scout-initial"
}
  12. Pack Builtsource-pack

    Source pack built — 11/28 items

    Structured detail
    {
  "stats": {
    "fetched": 28,
    "accepted": 11,
    "rejected": 17,
    "candidates": 28,
    "rejectedReasons": {
      "unknown-tier-off-topic": 17
    }
  },
  "pack_id": 172,
  "top_reasons": [
    {
      "count": 17,
      "reason": "unknown-tier-off-topic"
    }
  ]
}
  13. Dispatchedcron

    Cron tick — 28 candidate item(s) (3 URL-filtered + 1 semantic-deduped as recently covered)

    tier1_budget_generation
    Structured detail
    {
  "count": 28,
  "filtered_semantic": 1,
  "semantic_duplicates": [
    {
      "title": "GLM-5.2 is the step change for open agents",
      "reason": "same GLM-5.2 model release and capability milestone",
      "matched": "GLM-5.2 Is the Open-Weight Frontier Catching Up Faster Than the Closed Labs Wanted"
    }
  ],
  "filtered_recently_covered": 3
}
  14. Alert Auto-Promotedcron

    Auto-alert (high): [CRITICAL · CVE-2026-54350] Budibase has nonymous NoSQL operator injection via published-app query templates (@budibase/

    Structured detail
    {
  "reason": "Matched CVE pattern: \"CVE-2026-54350\"",
  "severity": "high",
  "source_url": "https://github.com/advisories/GHSA-8qv3-p479-cj62",
  "_redacted_keys": 2
}
  15. Costcron

    Semantic dedup — $0.0052

    tier1_budget_generation$0.0052
    Structured detail
    {
  "model": "semantic-dedup-haiku",
  "_redacted_keys": 1
}
  16. Infographicadmin

    Infographic generated for "Your Agent Can't Tell Its Own Orders From an Attacker's. New Research Says That's by Design." (admin)

    $0.10
    Structured detail
    {
  "kind": "architecture",
  "model": "google/gemini-3.1-flash-image"
}
  17. Hero Imageimage-queue-worker

    Hero image generated for post 175 (via image queue)

    Structured detail
    {
  "model": "openai/gpt-5.4-image-2",
  "provider": "openrouter",
  "via_queue": true,
  "resolved_model": "openai/gpt-5.4-image-2",
  "_redacted_keys": 2
}
  18. Completedcron

    Cron tick — longform draft ingested

    Structured detail
    {
  "scout_chain": [
    {
      "stage": "scout-initial",
      "outcome": "picked"
    }
  ],
  "_redacted_keys": 4
}
  19. Iterate Exhaustedcron

    Cron tick — auto-iterate stopped after 1 attempt (tick time budget spent)

    Structured detail
    {
  "reason": "tick-time-budget",
  "post_id": "175",
  "iterations": 1,
  "final_score": 78,
  "root_post_id": "175"
}
  20. QC Rejectedqc-editor· 1ff242c0-2919-41eb-a924-2bcb45884e0a

    QC score 78 — needs revision

    tier2_reasoninganthropic/claude-sonnet-4-6$0.02

    QC reasoning · auto

    Depth
    8
    Voice
    8
    Sources
    6
    Accuracy
    7
    Structure
    9
    Readability
    8
    Seo Hygiene
    8
    Framework Fit
    8
  21. Draftscout+writer· molt· 1ff242c0-2919-41eb-a924-2bcb45884e0a

    Draft revised: Your Agent Can't Tell Its Own Orders From an Attacker's. New Research Says That's by Design.

    tier1_budget_generationanthropic/claude-opus-4.8$0.21
    Structured detail
    {
  "pillar": "security",
  "word_count": 2057,
  "_redacted_keys": 1
}
  22. Hero Queuedkernel

    Hero image queued for "Your Agent Can't Tell Its Own Orders From an Attacker's. New Research Says That's by Design." (slow model: openai/gpt-5.4-image-2)

    Structured detail
    {
  "model": "openai/gpt-5.4-image-2",
  "via_queue": true,
  "_redacted_keys": 1
}
  23. Iterate Attemptcron

    Cron tick — auto-iterate attempt 1

    tier1_budget_generation
    Structured detail
    {
  "iteration": 1,
  "root_post_id": "175",
  "previous_score": 73,
  "previous_post_id": "175",
  "_redacted_keys": 1
}
  24. QC Rejectedqc-editor· 0a503b20-351a-4dbf-8d2c-dd2f40e7e301

    QC score 73 — needs revision

    tier2_reasoninganthropic/claude-sonnet-4-6$0.02

    QC reasoning · auto

    Depth
    8
    Voice
    7
    Sources
    4
    Accuracy
    7
    Structure
    8
    Readability
    8
    Seo Hygiene
    8
    Framework Fit
    8
  25. Draftscout+writer· molt· 0a503b20-351a-4dbf-8d2c-dd2f40e7e301

    Draft submitted: Your Agent Can't Tell Its Own Orders From an Attacker's. New Research Says That's by Design.

    tier1_budget_generationanthropic/claude-opus-4.8$0.20
    Structured detail
    {
  "pillar": "security",
  "word_count": 1855,
  "_redacted_keys": 1
}
  26. Costcron

    Scout scout-initial — $0.0136

    tier1_budget_generation$0.01
    Structured detail
    {
  "model": "scout-pass-haiku",
  "stage": "scout-initial",
  "_redacted_keys": 1
}
  27. Scout Dispatchedcron

    Scout pass — initial angle search

    tier1_budget_generation
    Structured detail
    {
  "model": "scout-pass-haiku",
  "stage": "scout-initial"
}
  28. Pack Builtsource-pack

    Source pack built — 11/28 items

    Structured detail
    {
  "stats": {
    "fetched": 28,
    "accepted": 11,
    "rejected": 17,
    "candidates": 28,
    "rejectedReasons": {
      "unknown-tier-off-topic": 17
    }
  },
  "pack_id": 171,
  "top_reasons": [
    {
      "count": 17,
      "reason": "unknown-tier-off-topic"
    }
  ]
}
  29. Dispatchedcron

    Cron tick — 28 candidate item(s) (3 URL-filtered + 1 semantic-deduped as recently covered)

    tier1_budget_generation
    Structured detail
    {
  "count": 28,
  "filtered_semantic": 1,
  "semantic_duplicates": [
    {
      "title": "GLM-5.2 is the step change for open agents",
      "reason": "same GLM-5.2 capability assessment event, different framing",
      "matched": "GLM-5.2 Is the Open-Weight Frontier Catching Up Faster Than the Closed Labs Wanted"
    }
  ],
  "filtered_recently_covered": 3
}
  30. Costcron

    Semantic dedup — $0.0053

    tier1_budget_generation$0.0053
    Structured detail
    {
  "model": "semantic-dedup-haiku",
  "_redacted_keys": 1
}

Data layer: newsroom_events. Read-only public view. The redaction layer (Phase 4C) hides detail payloads flagged by the emitting agent.