Research, brief, draft,
hero image and 46 checks in one run.

The trunk routine. It loads your voice, rules and first-hand experience, drafts in four passes with every step streamed live, validates what it wrote, and hands you a draft. It never publishes.

Articles

Your generated content estate: draft through published. Plan new topics in Topic Research.

50left
Articles + Rewrites
0 / 50
75left
Content Refreshes
0 / 75
Plan
Professional
resets the 1st
6 of 6 articles
TitleStatusGateScoreTarget keywordsTagsSyncAssigneeDueCreated
How to Prove You Are An Accredited Investor in 2026
Content Refresh
Pass
94All
95SEO
100AI
88EEAT
accredited investor letter+5
–Aug 30, 12:19 AM
Cost to Build an Apartment Complex in 2026: Apartment Building Cost Calculator
Content Refresh
Pass
91All
81SEO
100AI
100EEAT
cost to build an apartment complex
–Aug 30, 12:13 AM
Using Leverage in Real Estate to Build Wealth and Generate Returns
New Article· Topic Research
Pass
90All
90SEO
93AI
88EEAT
using leverage in real estate+5
–Aug 29, 11:48 PM
What to Look out for in a Multifamily Real Estate Recapitalization
Content Refresh
Pass
75All
81SEO
80AI
63EEAT
multifamily recapitalization+3
–Aug 29, 11:42 PM
The Impact of High Vacancy Rates on Multifamily Property Financing
Content Refresh
Pass
73All
81SEO
70AI
63EEAT
high vacancy rates multifamily
–Aug 29, 11:42 PM
Passive Real Estate Investing: The Passive Investors Guide
New Article· Manual
Pass
91All
93SEO
93AI
88EEAT
passive real estate investing+5
–Aug 29, 3:33 PM
Before the first word

It reads your business,
then it writes.

One system prompt is assembled per run: the standard operating procedures your articles are built to, your positioning and voice, your authors and their credentials, and the compliance rules your industry is gated by. On top of that, the eight documents from your brand knowledge and the fifteen experience facts closest to this topic are retrieved for this article specifically. The first two blocks are cached between runs, so every article starts from the same account of who you are.

VoiceBrand Hub › Brand & Voice
Brand Voice & Tone

Define how your brand sounds, and the author persona it writes as.

Brand Voice & Tone

Direct, specific, and honest. A plain-spoken operator voice, concrete numbers over adjectives, mechanics over hype. Educational and credible without being salesy. Every claim is grounded in how deals actually work, risk is stated plainly, and returns are never overpromised.

Author Persona

You are a multifamily operator and sponsor who understands acquisitions, underwriting, capital markets, and investor reporting from the inside. You've sponsored over $150M in Class B/C value-add apartment communities across Georgia and Texas, and you write the way you'd explain a deal to a smart but busy professional weighing a passive investment. You translate complex syndication mechanics, waterfalls, K-1s, depreciation, refinances, NOI-driven forced appreciation, into clear, practical language without dumbing them down. You never overpromise returns, you flag risk honestly, and you write from real operating experience rather than recycled finance-blog theory. Your goal is to educate accredited investors so they can make confident decisions, not to hype.

Forbidden:hidden gemboastsstunningluxuriousdream homeoasiselevatein today's marketdive inworld-classseamlessgame-changerunparalleled
Opinionswoven in where they fit
Strong opinions
  • Reserves are non-negotiable. We underwrite real operating and capex reserves into every deal: running thin on reserves is how sponsors get forced into bad decisions.
  • Value in multifamily is forced through NOI growth, not bought on market appreciation. If the business plan depends on the market going up, it isn't a business plan.
  • Class B and C workforce housing is more resilient through downturns than Class A, because in a recession people trade down into it, not out of it.
  • Conservative underwriting beats optimistic projections every time. We'd rather under-promise and over-deliver than hit a pro forma that only works in a perfect market.
  • Markets matter more than buildings. We buy in strong, insulated growth markets across the southern U.S., main focus Middle Georgia, because job and population growth drive everything downstream.
  • Sponsor alignment is everything. The GP should have real skin in the game alongside LPs, not just collect fees.
Complianceresolved per site, every run
Industry Governing Body

The regulators and authorities your content must abide by. Search a known body or add your own.

From your compliance packs

Base YMYL Foundation, US Real Estate Syndication, US Regulation D (506b/506c) : enforced by Verand, not editable here.

Quality standards

Your content is in a YMYL (Your Money or Your Life) category, so Google holds your site to a higher quality & trust bar.

Two blocks cached between runs
Four passes

Written in four passes.
Assembled in code.

A long HTML write in one shot times out and drifts, so the draft is written in four: the opening, the body sections, the closing, then a deterministic assembly pass. That last pass is not the model. The disclaimer, the byline, the table of contents and its anchors, the schema graph, the canonical and social tags, the FAQ accordion and the internal links are all generated in code, so they cannot drift and they match the article that was actually written.

Passes 1 to 3the model writes
Drafting H1, hero placeholder, intro, and key takeaways✓
Weaving in first-hand experience from Daniel (2 answers)✓
Finding internal link targets and citable claims for AI answer engines✓
Drafting FAQ, conclusion, and sources✓
Pass 4generated in code, not written
Composing disclaimers and assembling document✓
Internal links: wove 4 from the brief, removed 2 broken✓
Unlinked 1 intro link and 1 self-link✓
Adding Organization + Author + Article + FAQ schema (JSON-LD)✓
Then it is checkedChecklist, after the run
95
SEOi2 to fix
✔
Table of contentsijump-link TOC
✔
Canonical URLirel=canonical
✔
Open Graph tagsiog:title/description/type
✔
Twitter Card tagsitwitter:card/title/description
✔
Title ≠ H1ititle differs from H1
✔
Supporting schema graphiOrganization + BreadcrumbList
✔
Sources · citation schemaiArticle citation property
Your experience

It asks what only
you would know.

Before drafting, Verand derives two to five questions from the brief and skips anything your knowledge base already covers. Your wording is used faithfully: polished for grammar, never for meaning, and never embellished. Answers worth keeping are vetted and banked, so the next article starts from them. Skip every question and the draft falls back to the facts you have already written down, never to invention.

Images

A hero image for
this article, not a stock shelf.

Four modes: none, your own upload, an editorial scene derived from your brand, or a template steered by up to four of your own reference images. Whatever is generated is cropped to 16:9, compressed, given alt text written by a vision model from the finished picture rather than an echo of the headline, and saved under a filename derived from that alt text. In-body images are assessed per section and skipped where they would not help.

Hero imageBrand Hub › Visual Guidelines
Hero image templates

The wide image at the top of every article. Auto derives one from your brand; a template makes every hero match its reference style. Click a template to manage its references.

Auto

Tuned to your brand, no template

Hero 1

3 references

Body imagesassessed per section
Body image style

The pictures between sections, further down each article.

Auto

Editorial photography, tuned to your industry, audience and region.

Styled

3D render

How it works

One run, start to draft.

One pipeline from the brief to the draft. Four of its steps are drafting passes, and every step announces itself on the same live feed.

Start for free
Saved 06:54 PM
01

Start from a brief

A keyword, an angle, the terms and evidence to cover, and the internal links to use. Not a prompt.

Drafting H1, hero placeholder, intro, and key takeaways✓
Weaving in first-hand experience from Daniel (2 answers)✓
Finding internal link targets and citable claims for AI answer engines✓
Drafting FAQ, conclusion, and sources✓
Composing disclaimers and assembling document
02

Draft, streamed live

Four passes, each step named as it happens, on the same feed you can open from anywhere in the app.

Report Card
96
Overalli

Excellent · 3 to fix

Overall 96 · publishable bar 80

✅ Ready to publish
03

Score it, gate it

46 deterministic checks and three dials on the Report Card, plus a gate that reads Pass or Blocked, never a percentage.

Drafted "Multifamily Syndication: How It Works & Returns": 38/43 validators clean, 1 hero + 2 in-body images.

Validation: pass3 images
View in Articles →
04

Land it as a draft

The run ends with a draft in Articles and a receipt of what it did. Publishing is a person's decision.

Questions

What people ask before the first run.

How long it takes, what it refuses to do, and what happens to a claim it cannot stand up.

How long does one article take?

Two to four minutes end to end, and you can watch every step of it. The research pass, the four drafting passes, the images, the validation suite and the citation checks each announce themselves as they run. You can close the window; the run keeps going and the feed picks up where you left it.

Does it publish anything?

No. A generation run ends in a draft in your Articles tab, and on a connected repository it also opens a pull request. Both wait for a person. The generator itself has no path to a live page: every route that changes your site is an action someone takes in the editor, after reading the draft.

What happens to a fact it cannot verify?

The fact-verification standard operating procedure in the prompt tells it to omit the claim or soften it to general framing rather than publish an unverified specific. Separately, every external citation in the finished draft is fetched over HTTP and checked against the banned-source list for your compliance packs. That result becomes the Accuracy meter, so you can see how many of the sources actually resolved.

Why does the run say 38 of 43 checks when you sell 46?

Checks with nothing to judge stay inert instead of failing. Coverage terms, evidence items, secondary keywords and People Also Ask questions only exist on a research-backed brief, so without them those checks report as not applicable, drop out of the run's count and never dent a score. The validation engine is the same 46 either way; the run reports the ones that had something to measure.

Does every article get the quick-answer block at the top?

Only when the live search results for that keyword show a featured snippet, either flagged on the brief by the research routine or seen during the run itself. Then the first pass leads with the query phrased as a question and one self-contained answer of 40 to 55 words that Google can lift. No snippet in the results, no block.

Can I stop it inventing links to pages I do not have?

It already cannot. After drafting, every internal link is checked against the pages Verand has actually crawled on your site; an invented one is unwrapped and its sentence left intact. Then up to four real links from the brief are woven in, and links in the opening paragraph or pointing at the article's own URL are removed deterministically, because a prompt rule is a request and this one is a guarantee.

Article generator

Watch the first one get written.

Your onboarding ends with a real article on a real keyword from your site, drafted, scored and waiting for you to read it.

Verand

Content built to rank in Google and get cited by ChatGPTPerplexityGeminiClaude, with every claim checked before it goes live.

support@verand.ai

© 2026 Verand. All rights reserved. TermsPrivacyAI policyAccessibilitySecurity
Not legal advice. Compliance packs are AI researched and operator reviewed.