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)
130
Cost (7d)
$3.27
Posts published (7d)
5
QC rejections (7d)
4

Events / day

newsroom_events recorded · last 14 days

Aug 31Sep 7Sep 1328
Newsroom events recorded per day over the last 14 days Peaked at 31 on Sep 4.
PeriodValue
Aug 3115
Sep 125
Sep 226
Sep 320
Sep 431
Sep 513
Sep 627
Sep 720
Sep 813
Sep 98
Sep 1023
Sep 1119
Sep 1219
Sep 1328

Cost / day

USD attributed to agent calls · last 14 days

Aug 31Sep 7Sep 130.8838
Agent cost in USD per day over the last 14 days Peaked at 1.5878 on Sep 2.
PeriodValue
Aug 310.2619
Sep 10.7559
Sep 21.5878
Sep 30.4479
Sep 40.6764
Sep 50.3595
Sep 60.6481
Sep 70.3573
Sep 80.3848
Sep 90.0189
Sep 100.7752
Sep 110.3969
Sep 120.4578
Sep 130.8838

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

10

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

8

Freshness sweep found a citation that no longer resolves.

Tips promoted

1

Reader-submitted URL ended up in a published article.

  1. Source packs built

    Source pack built — 3/21 items

  2. Rotted links surfaced

    Link rotted — https://www.scworld.com/brief/massive-openclaw-supply-chain-attack-floods-openclaw-with-malicious-skills (403)

  3. Rotted links surfaced

    Link rotted — https://wayin.ai/blog/openclaw-setup-guide/ (403)

  4. Source packs built

    Source pack built — 5/23 items

  5. Rotted links surfaced

    Link rotted — https://clawblog.com/shadow-agent-problem (404)

  6. Rotted links surfaced

    Link rotted — https://example.com/harness-hypothesis (404)

Recent activity

  1. Hero Imagekernel

    Hero image generated for "Four Releases, Three Axes: The Week the Agent Category Stopped Converging"

    $0.10
    Structured detail
    {
  "model": "google/gemini-3.1-flash-image",
  "provider": "openrouter",
  "resolved_model": "google/gemini-3.1-flash-image",
  "_redacted_keys": 3
}
  2. Hero Queuedkernel

    Hero image sync-gen attempt for "Four Releases, Three Axes: The Week the Agent Category Stopped Converging" (google/gemini-3.1-flash-image)

    Structured detail
    {
  "model": "google/gemini-3.1-flash-image",
  "via_queue": false,
  "_redacted_keys": 2
}
  3. Completedcron

    Cron tick — longform draft ingested

    Structured detail
    {
  "scout_chain": [
    {
      "stage": "scout-initial",
      "reason": "Pack contains no on-beat agent/AI content suitable for ClawBlog. Item [1] is a generic AI radar recap (DeepSeek, Meta Muse, AlphaGenome, OpenAI math) — a community-tier digest of widely-covered announcements with no novel angle or consumer-agent specificity; the excerpt provides no substantive material to angle from. Item [2] is a nature sighting (California Brown Pelican) completely off-topic. Item [3] is a Stratechery bundle table-of-contents with no subject matter — just delivery/subscription metadata. None of the three items support a consumer-agent angle, name a recognizable agent product, or reveal a category pattern. The pack is empty of publishable material for this beat.",
      "outcome": "no-pick"
    },
    {
      "stage": "scout-force-pick",
      "outcome": "picked"
    }
  ],
  "_redacted_keys": 4
}
  4. Iterate Exhaustedcron

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

    Structured detail
    {
  "reason": "tick-time-budget",
  "post_id": "268",
  "iterations": 0,
  "final_score": 63,
  "root_post_id": "268",
  "_redacted_keys": 3
}
  5. Claim Groundingkernel

    Claim grounding 75% across 8 bound claim(s)

    Structured detail
    {
  "_redacted_keys": 3
}
  6. QC Rejectedqc-editor· 430e243b-e6b2-47ac-9536-b468dd1dbc70

    QC score 63 — needs revision

    tier2_reasoningdeepseek/deepseek-v4.1-flash$0.0037

    QC reasoning · auto

    Depth
    7
    Voice
    7
    Sources
    2
    Accuracy
    5
    Structure
    8
    Readability
    7
    Seo Hygiene
    7
    Framework Fit
    7
  7. Draftscout+writer· tide· 430e243b-e6b2-47ac-9536-b468dd1dbc70

    Draft submitted: Four Releases, Three Axes: The Week the Agent Category Stopped Converging

    tier1_budget_generationanthropic/claude-opus-5$0.33
    Structured detail
    {
  "pillar": "digest",
  "word_count": 2892,
  "_redacted_keys": 1
}
  8. Costcron

    Scout scout-force-pick — $0.0107

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

    Scout pass — force-pick retry (initial pass returned no-pick)

    tier1_budget_generation
    Structured detail
    {
  "model": "scout-pass-haiku",
  "stage": "scout-force-pick"
}
  10. Costcron

    Scout scout-initial — $0.0085

    tier1_budget_generation$0.0085
    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 — 3/21 items

    Structured detail
    {
  "stats": {
    "fetched": 21,
    "accepted": 3,
    "rejected": 18,
    "candidates": 21,
    "rejectedReasons": {
      "unknown-tier-off-topic": 18
    }
  },
  "pack_id": 281,
  "top_reasons": [
    {
      "count": 18,
      "reason": "unknown-tier-off-topic"
    }
  ]
}
  13. Dispatchedcron

    Cron tick — 21 candidate item(s) (11 URL-filtered + 1 semantic-deduped as recently covered)

    tier1_budget_generation
    Structured detail
    {
  "count": 21,
  "filtered_semantic": 1,
  "semantic_duplicates": [
    {
      "title": "Generating running routes with GPT-6 Astra and ChatGPT Work",
      "reason": "same product launch (GPT-6 Astra) covered from a different angle/use case",
      "matched": "GPT-6 Astra's 36M-View Launch Is Not About the Benchmarks"
    }
  ],
  "filtered_recently_covered": 11
}
  14. Costcron

    Semantic dedup — $0.0038

    tier1_budget_generation$0.0038
    Structured detail
    {
  "model": "semantic-dedup-haiku",
  "_redacted_keys": 1
}
  15. Hero Imagekernel

    Hero image generated for "The Forward Deployed Engineer Is the Agent Stack's Missing Layer"

    $0.10
    Structured detail
    {
  "model": "google/gemini-3.1-flash-image",
  "provider": "openrouter",
  "resolved_model": "google/gemini-3.1-flash-image",
  "_redacted_keys": 3
}
  16. Link Rottedsource-pack

    Link rotted — https://www.scworld.com/brief/massive-openclaw-supply-chain-attack-floods-openclaw-with-malicious-skills (403)

    Structured detail
    {
  "url": "https://www.scworld.com/brief/massive-openclaw-supply-chain-attack-floods-openclaw-with-malicious-skills",
  "reason": "http-403",
  "status": 403,
  "_redacted_keys": 1
}
  17. Link Rottedsource-pack

    Link rotted — https://wayin.ai/blog/openclaw-setup-guide/ (403)

    Structured detail
    {
  "url": "https://wayin.ai/blog/openclaw-setup-guide/",
  "reason": "http-403",
  "status": 403,
  "_redacted_keys": 1
}
  18. Hero Queuedkernel

    Hero image sync-gen attempt for "The Forward Deployed Engineer Is the Agent Stack's Missing Layer" (google/gemini-3.1-flash-image)

    Structured detail
    {
  "model": "google/gemini-3.1-flash-image",
  "via_queue": false,
  "_redacted_keys": 2
}
  19. Completedcron

    Cron tick — longform draft ingested

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

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

    Structured detail
    {
  "reason": "tick-time-budget",
  "post_id": "267",
  "iterations": 0,
  "final_score": 73,
  "root_post_id": "267",
  "_redacted_keys": 3
}
  21. Claim Groundingkernel

    Claim grounding 76% across 7 bound claim(s) · 1 weak

    Structured detail
    {
  "_redacted_keys": 3
}
  22. QC Rejectedqc-editor· 60626df1-5a75-41b5-93d6-820b2e50e5c8

    QC score 73 — needs revision

    tier2_reasoningdeepseek/deepseek-v4.1-flash$0.0026

    QC reasoning · auto

    Depth
    8
    Voice
    7
    Sources
    3
    Accuracy
    7
    Structure
    9
    Readability
    8
    Seo Hygiene
    9
    Framework Fit
    7
  23. Draftscout+writer· tide· 60626df1-5a75-41b5-93d6-820b2e50e5c8

    Draft submitted: The Forward Deployed Engineer Is the Agent Stack's Missing Layer

    tier1_budget_generationanthropic/claude-opus-5$0.31
    Structured detail
    {
  "pillar": "ecosystem",
  "word_count": 2803,
  "_redacted_keys": 1
}
  24. Costcron

    Scout scout-initial — $0.0119

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

    Scout pass — initial angle search

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

    Source pack built — 5/23 items

    Structured detail
    {
  "stats": {
    "fetched": 23,
    "accepted": 5,
    "rejected": 18,
    "candidates": 23,
    "rejectedReasons": {
      "unknown-tier-off-topic": 18
    }
  },
  "pack_id": 280,
  "top_reasons": [
    {
      "count": 18,
      "reason": "unknown-tier-off-topic"
    }
  ]
}
  27. Dispatchedcron

    Cron tick — 23 candidate item(s) (9 URL-filtered + 1 semantic-deduped as recently covered)

    tier1_budget_generation
    Structured detail
    {
  "count": 23,
  "filtered_semantic": 1,
  "semantic_duplicates": [
    {
      "title": "Generating running routes with GPT-6 Astra and ChatGPT Work",
      "reason": "same product launch (GPT-6 Astra) with a use-case demonstration rather than new underlying event",
      "matched": "GPT-6 Astra's 36M-View Launch Is Not About the Benchmarks"
    }
  ],
  "filtered_recently_covered": 9
}
  28. Costcron

    Semantic dedup — $0.0040

    tier1_budget_generation$0.0040
    Structured detail
    {
  "model": "semantic-dedup-haiku",
  "_redacted_keys": 1
}
  29. Hero Imagekernel

    Hero image generated for "Anthropic Holds Claude's Code to a Higher Bar Than Its Own Engineers'"

    $0.10
    Structured detail
    {
  "model": "google/gemini-3.1-flash-image",
  "provider": "openrouter",
  "resolved_model": "google/gemini-3.1-flash-image",
  "_redacted_keys": 3
}
  30. Link Rottedsource-pack

    Link rotted — https://clawblog.com/shadow-agent-problem (404)

    Structured detail
    {
  "url": "https://clawblog.com/shadow-agent-problem",
  "reason": "http-404",
  "status": 404,
  "_redacted_keys": 1
}

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