# Editor notes: LumenDesk 2.0 article package

## Deliverables
- `article.md`: 778 words by script count. This excludes the H1 headline, which is also in metadata, and includes the subheads and inline citations.
- `metadata.json`: headline is 61 characters, excerpt is 37 words and search description is 159 characters, all by script count.
- `check.py` and `trim.py` are the helper scripts used to count lengths and make the edits. They aren't for publication.

## Sources used
| Claim area | Source |
|---|---|
| Who can use it, browser only, waitlist, API and EU planned for Q1 2027 with no date or guarantee | S1-announcement.md, "Access" |
| File types, 50 MB limit, OCR needed for scans, drafts only | S1-announcement.md, "Features" |
| 50 → 20 minute median first-draft time from 40 packets | S1-announcement.md, "Vendor test" |
| USD 29/seat/month, 3-seat minimum, 500 uploads per workspace, no rollover, USD 0.08 overage, OCR USD 12, tax excluded | S2-pricing.md, "Current plans" |
| USD 19 screenshot was wrong; no annual offer | S2-pricing.md, "Correction" |
| No base-model training, 30-day default storage, 24 h active deletion, backups up to 30 more days | S3-data-policy.md, "Handling" |
| External model provider, no on-device mode, no claim of zero retention or compliance | S3-data-policy.md, "Processing" |
| 6 PDFs, 5 correct page citations, 1 wrong page, informal, untested areas | S4-independent-review.md, "Method" |

## How the corrections and claims were handled
- **Price:** The article uses USD 29 per seat, from S2-pricing.md, "Correction." USD 19 appears only to explain the correction, so readers who saw the launch screenshot know why the price changed. Ignore the S5 suggestion to lead with USD 19.
- **Pricing calculations:** I calculated these from S2. Three seats × USD 29 = USD 87. Adding OCR at USD 12 brings it to USD 99. For 750 uploads, the extra 250 × USD 0.08 = USD 20. All amounts are before tax. The 750-upload case is a made-up example, not a source figure.
- **Vendor's timing claim:** The article attributes this to LumenDesk and includes the vendor's own caveats. It covers drafting only, leaves out human checking, doesn't show end-to-end time saved and has no task-level results published. The article doesn't present it as time saved.
- **Independent review:** The article describes it as small and informal, which is how DeskLab describes it. It doesn't turn the result into an accuracy percentage.
- **Available now vs. planned:** What's available now is limited to existing Team customers in Canada and the US, in the browser app. The API and EU access are described only as planned for Q1 2027, with no date or guarantee.
- **No hands-on testing:** Per editorial-brief.md, the article says Kingy hasn't tested the product. Its advice to start with a document you already know the answer to is framed as a suggestion for readers, not as something we did. It follows the approach in voice-sample.md.

## S5 claims left out, with reasons
S5-internal-notes.txt describes itself as "unverified writer notes" and "leads requiring verification." None of its claims are in the article.
| S5 claim | Why it's excluded |
|---|---|
| "Eliminates hallucinations" | No source supports it. S4 found one wrong page citation in six, and S1 says the tool only drafts answers. |
| "GDPR certified" | No source supports it. S3, "Processing," says the policy doesn't claim guaranteed regulatory compliance. EU availability is only planned (S1, "Access"). |
| "Runs fully offline" | S3, "Processing," contradicts it. Requests go to an external model provider, and there's no on-device mode. |
| "Saves every team 60% of their work time" | The source is unnamed ("someone said"). S1, "Vendor test," says the vendor's figure doesn't establish end-to-end time saved. |
| "Lead with USD19" | S2, "Correction," says this price was wrong. |
| Customer quote "We fired our paperwork department" | It has no named source or permission. It's also a slogan, which the editorial brief says to avoid. |

## Assumptions and limitations
- I treated the dates and policies in the fixtures as authoritative within the scenario. I didn't do any outside research.
- The source packet doesn't say whether existing Team customers pay extra for the assistant. The article treats S2 Team pricing as the cost of access and doesn't claim the assistant is free or costs extra on top of it. **An editor should confirm this.**
- No source covers when waitlisted customers will get access, whether Team customers outside Canada and the US are included, or whether DOCX files count differently toward uploads. The article doesn't speculate on these points.
- Word counts depend on how you count. My script counts citations like "S1-announcement.md," as one word each. Other counters could differ by a few words, but the total is well inside the 600–800 range.
