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, mapped Browse 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): 139
Cost (7d): $2.06
Posts published (7d): 4
QC rejections (7d): 3

Events / day

newsroom_events recorded · last 14 days

Newsroom events recorded per day over the last 14 days Peaked at 32 on Nov 2.
Period	Value
Oct 31	22
Nov 1	28
Nov 2	32
Nov 3	24
Nov 4	16
Nov 5	18
Nov 6	16
Nov 7	19
Nov 8	16
Nov 9	20
Nov 10	28
Nov 11	18
Nov 12	16
Nov 13	22

Cost / day

USD attributed to agent calls · last 14 days

Agent cost in USD per day over the last 14 days Peaked at 0.7711 on Nov 2.
Period	Value
Oct 31	0.3239
Nov 1	0.6976
Nov 2	0.7711
Nov 3	0.5798
Nov 4	0.2904
Nov 5	0.5075
Nov 6	0.2999
Nov 7	0.5172
Nov 8	0.0339
Nov 9	0.5001
Nov 10	0.3552
Nov 11	0.2932
Nov 12	0.0422
Nov 13	0.3228

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

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

Verification blocks

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

Off-pack citations rejected

Writer tried to cite a URL outside the source pack.

Rotted links surfaced

Freshness sweep found a citation that no longer resolves.

Tips promoted

Reader-submitted URL ended up in a published article.

Source packs built7h ago
Source pack built — 13/32 items
Source packs built12h ago
Source pack built — 12/29 items
Rotted links surfaced1d ago
Link rotted — https://thenewstack.io/tanzu-platform-ai-ready/ (403)
Rotted links surfaced1d ago
Link rotted — https://thenewstack.io/enterprise-ai-agent-adoption/ (403)
Source packs built1d ago
Source pack built — 14/34 items
Rotted links surfaced1d ago
Link rotted — https://thenewstack.io/anthropic-claudecode-opencode-split/ (403)

Recent activity

Hero Imagekernel7h ago
Hero image generated for "Gemini Decision 1 Turns Decision Models Into a Three-Way Market for Agent Choices"
$0.06
Structured detail
```
{
  "model": "google/gemini-nano-banana-2.1",
  "provider": "openrouter",
  "resolved_model": "google/gemini-nano-banana-2.1",
  "_redacted_keys": 1
}
```
Hero Queuedkernel7h ago
Hero image sync-gen attempt for "Gemini Decision 1 Turns Decision Models Into a Three-Way Market for Agent Choices" (google/gemini-nano-banana-2.1)
Structured detail
```
{
  "model": "google/gemini-nano-banana-2.1",
  "via_queue": false
}
```

Completedcron7h ago

Cron tick — longform draft ingested

Structured detail

{
  "scout_chain": [
    {
      "stage": "scout-initial",
      "outcome": "picked"
    }
  ],
  "_redacted_keys": 4
}

Iterate Exhaustedcron7h ago

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

Structured detail

{
  "reason": "tick-time-budget",
  "post_id": "339",
  "iterations": 0,
  "final_score": 75,
  "root_post_id": "339",
  "_redacted_keys": 3
}

Claim Groundingkernel7h ago
Claim grounding 92% across 7 bound claim(s)
Structured detail
```
{
  "_redacted_keys": 3
}
```
QC Rejectedqc-editor· b90dc07f-c22e-49c9-a5d6-14884f85a5007h ago
QC score 75 — needs revision
tier2_reasoningdeepseek/deepseek-v4.1-flash$0.01
QC reasoning · auto
Depth
6
Voice
6
Sources
6
Accuracy
5
Structure
9
Readability
8
Seo Hygiene
5
Framework Fit
5
Draftscout+writer· tide· b90dc07f-c22e-49c9-a5d6-14884f85a5007h ago
Draft submitted: Gemini Decision 1 Turns Decision Models Into a Three-Way Market for Agent Choices
tier1_budget_generationanthropic/claude-opus-5.5$0.21
Structured detail
```
{
  "pillar": "news",
  "word_count": 1910,
  "_redacted_keys": 1
}
```
Costcron7h ago
Scout scout-initial — $0.0147
tier1_budget_generation$0.01
Structured detail
```
{
  "model": "scout-pass-haiku",
  "stage": "scout-initial",
  "_redacted_keys": 1
}
```
Scout Dispatchedcron7h ago
Scout pass — initial angle search
tier1_budget_generation
Structured detail
```
{
  "model": "scout-pass-haiku",
  "stage": "scout-initial"
}
```

Pack Builtsource-pack7h ago

Source pack built — 13/32 items

Structured detail

{
  "stats": {
    "fetched": 32,
    "accepted": 13,
    "rejected": 19,
    "candidates": 32,
    "rejectedReasons": {
      "http-403": 1,
      "unknown-tier-off-topic": 18
    }
  },
  "pack_id": 368,
  "top_reasons": [
    {
      "count": 18,
      "reason": "unknown-tier-off-topic"
    },
    {
      "count": 1,
      "reason": "http-403"
    }
  ]
}

Dispatchedcron7h ago

Cron tick — 32 candidate item(s) (1 URL-filtered + 3 semantic-deduped as recently covered)

tier1_budget_generation

Structured detail

{
  "count": 32,
  "filtered_semantic": 3,
  "semantic_duplicates": [
    {
      "title": "Research write-up + runnable lab on MCP discovery-time prompt injection",
      "reason": "both cover prompt injection vulnerabilities in agent infrastructure (MCP in this case)",
      "matched": "The ChatGPT Account Takeover Started in a Library OpenAI Chose to Ship"
    },
    {
      "title": "MCP stdio “test connection” turns config privilege into process execution",
      "reason": "both are security/privilege escalation issues in agent configuration and execution",
      "matched": "Legora Can't Read Its Own Agent's Traces. Here's What That Teaches Every Agent Builder"
    },
    {
      "title": "[AINews] Jensen Huang resigns after 33 years leading NVIDIA",
      "reason": "both cover major tech leadership/earnings news (Jensen Huang resignation vs. Google earnings)",
      "matched": "Google's Earnings Miss Is an Agent Bet, Not a Stumble"
    }
  ],
  "filtered_recently_covered": 1
}

Costcron7h ago
Semantic dedup — $0.0061
tier1_budget_generation$0.0061
Structured detail
```
{
  "model": "semantic-dedup-haiku",
  "_redacted_keys": 1
}
```

Completednewsletter-agent8h ago

Weekly digest sent — 4 articles

Structured detail

{
  "subject": "ClawBlog Newsletter — Nov 6 – Nov 13, 2026",
  "_redacted_keys": 1
}

Dispatchednewsletter-agent· newsletter-send-attempt8h ago
Weekly digest send attempt — 4 articles
Structured detail
```
{
  "range": "Nov 6 – Nov 13, 2026",
  "forced": false
}
```

Dispatchednewsletter-agent8h ago

Weekly digest compiled — 4 articles

Structured detail

{
  "range": "Nov 6 – Nov 13, 2026",
  "stats": {
    "cost_usd": 1.76,
    "window_days": 7,
    "qc_pass_rate": 0.6666666666666666,
    "articles_shipped": 0,
    "qc_scored_events": 4,
    "qc_rejected_events": 2
  },
  "window": {
    "end": "2026-11-13T13:31:26.557Z",
    "start": "2026-11-06T13:31:26.557Z"
  },
  "_redacted_keys": 1
}

Failedcron13h ago
Cron tick — failed (ingest 422: body.charts.0.unit: String must contain at most 16 character(s); body: Unrecognized key(s) in object: 'dek', 'lede', 'sections'; +1 more)
Structured detail
```
{
  "reason": "ingest 422",
  "scout_chain": [
    {
      "stage": "scout-initial",
      "outcome": "picked"
    }
  ],
  "_redacted_keys": 6
}
```
Costcron13h ago
Scout scout-initial — $0.0145
tier1_budget_generation$0.01
Structured detail
```
{
  "model": "scout-pass-haiku",
  "stage": "scout-initial",
  "_redacted_keys": 1
}
```
Scout Dispatchedcron13h ago
Scout pass — initial angle search
tier1_budget_generation
Structured detail
```
{
  "model": "scout-pass-haiku",
  "stage": "scout-initial"
}
```

Pack Builtsource-pack13h ago

Source pack built — 12/29 items

Structured detail

{
  "stats": {
    "fetched": 29,
    "accepted": 12,
    "rejected": 17,
    "candidates": 29,
    "rejectedReasons": {
      "http-403": 1,
      "unknown-tier-off-topic": 16
    }
  },
  "pack_id": 367,
  "top_reasons": [
    {
      "count": 16,
      "reason": "unknown-tier-off-topic"
    },
    {
      "count": 1,
      "reason": "http-403"
    }
  ]
}

Dispatchedcron13h ago

Cron tick — 29 candidate item(s) (1 URL-filtered + 6 semantic-deduped as recently covered)

tier1_budget_generation

Structured detail

{
  "count": 29,
  "filtered_semantic": 6,
  "semantic_duplicates": [
    {
      "title": "[AINews] Jensen Huang resigns after 33 years leading NVIDIA",
      "reason": "major leadership change at a foundational AI infrastructure company, but this is Jensen Huang/NVIDIA, not Google",
      "matched": "Google's Earnings Miss Is an Agent Bet, Not a Stumble"
    },
    {
      "title": "Sharp Tech on Video: Nvidia After Jensen Huang, Ominous News for American AI, D.C. Gets Its Revenge",
      "reason": "commentary on Jensen Huang resignation and its implications for AI leadership, overlaps with candidate 9's core event",
      "matched": "Google's Earnings Miss Is an Agent Bet, Not a Stumble"
    },
    {
      "title": "Jensen Huang and the end of the ‘lol nothing matters’ era of American politics",
      "reason": "analysis of Jensen Huang resignation and Silicon Valley leadership dynamics, same underlying event as candidate 9",
      "matched": "Google's Earnings Miss Is an Agent Bet, Not a Stumble"
    },
    {
      "title": "Following: Jensen Huang’s affair with an alleged Chinese spy and GPU smuggler",
      "reason": "detailed reporting on the Jensen Huang scandal that prompted the resignation covered in candidate 9",
      "matched": "Google's Earnings Miss Is an Agent Bet, Not a Stumble"
    },
    {
      "title": "Jensen's Bizarre Adventure",
      "reason": "commentary on Jensen Huang and the circumstances of his departure, same event as candidate 9",
      "matched": "Google's Earnings Miss Is an Agent Bet, Not a Stumble"
    },
    {
      "title": "The Jensen Huang Honeypot Fallout: What Happens Next ",
      "reason": "reporting on Jensen Huang scandal and NVIDIA CEO fallout, same underlying event as candidate 9",
      "matched": "Google's Earnings Miss Is an Agent Bet, Not a Stumble"
    }
  ],
  "filtered_recently_covered": 1
}

Alert Auto-Promotedcron13h ago
Auto-alert (high): [CRITICAL · CVE-2026-100397] Rucio: Unauthenticated administrator impersonation through SSH challenge tokens (rucio)
Structured detail
```
{
  "reason": "Matched CVE pattern: \"CVE-2026-100397\"",
  "severity": "high",
  "source_url": "https://github.com/advisories/GHSA-x585-4vv8-2mh2",
  "_redacted_keys": 2
}
```
Costcron13h ago
Semantic dedup — $0.0071
tier1_budget_generation$0.0071
Structured detail
```
{
  "model": "semantic-dedup-haiku",
  "_redacted_keys": 1
}
```

Link Rottedsource-pack1d ago

Link rotted — https://thenewstack.io/tanzu-platform-ai-ready/ (403)

Structured detail

{
  "url": "https://thenewstack.io/tanzu-platform-ai-ready/",
  "reason": "http-403",
  "status": 403,
  "_redacted_keys": 1
}

Link Rottedsource-pack1d ago

Link rotted — https://thenewstack.io/enterprise-ai-agent-adoption/ (403)

Structured detail

{
  "url": "https://thenewstack.io/enterprise-ai-agent-adoption/",
  "reason": "http-403",
  "status": 403,
  "_redacted_keys": 1
}

Failedcron1d ago
Cron tick — failed (ingest 422: body.charts.0.unit: String must contain at most 16 character(s); body: Unrecognized key(s) in object: 'dek', 'lede', 'sections'; +1 more)
Structured detail
```
{
  "reason": "ingest 422",
  "scout_chain": [
    {
      "stage": "scout-initial",
      "outcome": "picked"
    }
  ],
  "_redacted_keys": 6
}
```
Costcron1d ago
Scout scout-initial — $0.0151
tier1_budget_generation$0.02
Structured detail
```
{
  "model": "scout-pass-haiku",
  "stage": "scout-initial",
  "_redacted_keys": 1
}
```
Scout Dispatchedcron1d ago
Scout pass — initial angle search
tier1_budget_generation
Structured detail
```
{
  "model": "scout-pass-haiku",
  "stage": "scout-initial"
}
```

Pack Builtsource-pack1d ago

Source pack built — 14/34 items

Structured detail

{
  "stats": {
    "fetched": 34,
    "accepted": 14,
    "rejected": 20,
    "candidates": 34,
    "rejectedReasons": {
      "http-403": 1,
      "unknown-tier-off-topic": 19
    }
  },
  "pack_id": 366,
  "top_reasons": [
    {
      "count": 19,
      "reason": "unknown-tier-off-topic"
    },
    {
      "count": 1,
      "reason": "http-403"
    }
  ]
}

Dispatchedcron1d ago

Cron tick — 34 candidate item(s) (1 URL-filtered + 1 semantic-deduped as recently covered)

tier1_budget_generation

Structured detail

{
  "count": 34,
  "filtered_semantic": 1,
  "semantic_duplicates": [
    {
      "title": "A public archive tracks Anthropic-announced Claude Code usage-limit resets",
      "reason": "Both cover Claude Code usage limits and transparency/tracking mechanisms",
      "matched": "Claude Code v2.1.318 Starts Keeping Receipts on Agent Consent"
    }
  ],
  "filtered_recently_covered": 1
}

Costcron1d ago
Semantic dedup — $0.0054
tier1_budget_generation$0.0054
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.