Based on what buyers actually ask
Auto-generated tagsFeatureAI-powered
Human Signal
An EEAT checker that tells you what to add, not what to reword
Human Signal is the EEAT checker built into the WriteWorks editor. It reads a draft for evidence of experience, expertise, authority and trust, then measures information gain: what the draft says that AI answers and the top-ranking pages don't already. The result is a 0 to 100 score and a list of fixes ranked by impact, each one asking for substance, such as a result you measured or a named method, rather than a rewrite.
7-day trial · Cancel anytime
Google Search Console
Google Analytics 4
Google Ads
Ahrefs
Semrush
DataForSEO
Firecrawl
Tavily
Exa
Parallel
G2
WordPress
Webflow
Contentful
Sanity
Payload
BaseHub
Framer
Notion
Gamma
v0
Slack
Linear
Atlassian
Monday.com
Granola
Klaviyo
Customer.io
OpenAI Ads
Claude and MCP clients The platform
See WriteWorks in Action
This is the working product, not a mockup: the same visibility scores, briefs and published content your team would be looking at. Start a free trial and point it at your own domain, or take the tour of what sits behind the screen.
Home
Ask AI
Opportunities128
Research
Create
Editor
Automations
Sheets
Projects
Documents
Measure
Context
Support
Settings
Sign out
SCSam Cartersam@example.com
WRITEWORKS
Create/Editor
Search brands, prompts, competitors…⌘K
New1.2M (62%) leftAsk AI
The challenge
Why EEAT advice rarely changes a draft
Vague guidance, consensus content and polish mistaken for substance.
EEAT advice is vague
"Show more experience" is easy to say and hard to act on. Writers need to know which paragraph is missing what.
Drafts repeat the consensus
A page that says what every AI answer and every top result already says gives search and AI engines no reason to cite it.
Polish gets mistaken for substance
Rewording a generic paragraph makes it read better without making it more useful. Scores that reward phrasing reward the wrong work.
Third parties hold the citation
Roundups, reviews and forums are quoted ahead of your own pages, and nothing tells you which source displaced you.
The solution
How Human Signal works
A quoted rubric, information gain against real answers, and fixes ranked by impact.
Run Human Signal from the Human tab and it checks the draft against a rubric: first-hand experience (tested, implemented, measured), a concrete outcome, named specifics, a lesson or mistake, specific figures, named methods, caveats, an author byline and credentials, primary sources, original data, verifiable claims, dated facts, disclosure of interest, and no hype. Each credited item must quote the draft.
Information gain is measured against the answers AI engines already give for your tracked prompts, and against the top organic results for the target query, with the leading pages read in full and your own site excluded. Fixes on consensus flags show which engines already say it.
Flags cover generic claims, repeating the AI consensus, missing experience, unsupported claims, stacked hedges, flat rhythm and stock AI phrasing. Missing-experience fixes come with interview questions to ask the expert, and you can highlight the flagged passages in the draft.
Sentence rhythm, vocabulary range, hedging, stock phrases, lists of three and paragraph shape are read as typical, watch or pattern. They coach the writing and don't estimate who wrote it. Natural voice is capped at a small share of the score, so adding substance moves it and rewording barely does.
Success story
What real brands fixed with WriteWorks
What each brand fixed, measured before and after with the same audit, in their own words.
“Turning caching on made our pages 2.5 times faster for crawlers. While we were in there, we fixed the headings too: guides with a clean heading structure went from 32% to 100%.”
S4
Capabilities
What the EEAT checker scores
Six dimensions, weighted towards evidence.
Experience
Evidence the author has done the thing: tested, implemented, measured.
Expertise
Named methods, specific figures and the caveats an expert would add.
Authority
Byline, credentials and primary sources.
Trust
Verifiable claims, dated facts, disclosure and no hype.
Information gain
What the draft adds beyond AI answers and top results.
Run history
Re-run after edits and see the score move.
Time savings
What changes
From a quality checklist to a fix list.
TaskBeforeWith WriteWorksTime saved
Run an EEAT audit on a draftA checklist and a judgement callScored rubric with quotes from the draftThe review pass
Find what the draft addsRead the top results yourselfInformation gain against AI answers and top pagesHours of research
Brief the expertGeneric "add more experience"Interview questions tied to the gapA back-and-forth
Included
What's included
Everything in the Human tab.
Human tab in the editor review panel, beside Search and Brand
0 to 100 score: experience, expertise, authority, trust, information gain, natural voice
Evidence counts for at least 85% of the score, style for no more than 15%
Rubric items credited only with a quote from the draft
Information gain against stored AI answers for your tracked prompts
Information gain against the top organic results for the target query
Flags: generic claim, repeats AI consensus, missing experience, unsupported claim, hedge stacking, flat rhythm, stock AI phrasing
Interview questions for missing-experience fixes
Highlight flagged passages in the draft
Style readings that are not an AI detector
Needs at least 300 words; uses AI tokens from your plan
Built for
Who uses it
Everyone who touches the draft.
Writers
Concrete prompts for the experience and detail a draft is missing.
Editors
An EEAT checker that shows its evidence, quote by quote.
SEO leads
Information gain SEO measured against real AI answers and top pages, not guesses.
Subject-matter experts
Answer the interview questions and the draft gains what only you know.
Featured story
GraftPal
“A near-perfect audit score made it easy to think the job was done. WriteWorks found the one gap that mattered: none of our homepages said who we are in a way a machine could read. We added Organization markup in every market and dated every FAQ page, and key pages carrying the schema AI expects went from 92% to 100%. Small changes, and a much clearer picture of GraftPal for AI.”
GraftPal team
Read the full story0% → 100%
Market homepages with Organization markup
20% → 100%
Articles and FAQs with a modified date
6.7x
Faster median server response to crawlers
FAQ
Frequently asked questions
Everything teams typically ask before getting started.
What is an EEAT checker?+
An EEAT checker reviews content for the signals of experience, expertise, authoritativeness and trustworthiness that Google's quality guidelines describe. Human Signal does this inside the WriteWorks editor and goes a step further: every credited signal is backed by a quote from the draft, and every gap comes with the specific thing to add.
What is information gain in SEO?+
Information gain is what a page adds that other pages on the same question don't. Information gain SEO is the practice of writing for it, on the basis that a page repeating the consensus gives search and AI engines little reason to rank or cite it. Human Signal measures it against the answers AI engines already give for your tracked prompts and the top organic results for your target query.
Is Human Signal an AI detector?+
No. Its style readings coach rhythm and phrasing and don't estimate who wrote the text. If you need a probability that a draft reads as AI-written, that is AI Likelihood, a separate card in the same tab available with the AI Detection add-on.
How do I raise my Human Signal score?+
Add substance. A result you measured, a mistake you learned from, a named method, a specific figure, a primary source or a dated fact will move the score. Rewording the same generic point barely does, by design.
Does it work on short drafts?+
It needs at least 300 words to score. Below that there isn't enough text to judge evidence fairly.
Where does it sit in the editor?+
In the review panel, which has three tabs: Search for SEO and answer-readiness checks, Human for Human Signal, and Brand for voice and banned terms.
The review panel
Three tabs, three questions
Search
SEO, answer-readiness and citation checks on structure, keywords and sources.
See the Search checksHuman
Human Signal: evidence of experience and original thinking, and what to add.
Brand
Voice, tone and banned terms against your brand profile.
See brand voice Explore more
Keep exploring
Related solutions, adjacent use cases, and platform features.
Run an EEAT audit on your next draft
Human Signal scores experience, expertise, authority, trust and information gain, and tells the writer exactly what to add.