DEV Community: Krutika Galvankar

We Got Tired of Measuring AI Visibility With Just One Citation Score

Krutika Galvankar — Tue, 27 Oct 2026 16:38:49 +0000

"Are you mentioned by ChatGPT" — yes or no. That's where we started too, and we kept running into the same problem: the yes/no was hiding the actual story. So we built four things to go past the single snapshot.

Citation Stability — Getting cited once? Could be luck. We started tracking whether it holds up across repeated checks, so you actually know if a win is real or a one-time fluke.

AI Engine Agree/Disagree — We ask Gemini, ChatGPT, Perplexity, and Claude the exact same question. Turns out they don't always agree with each other. We now show you exactly where they split, instead of collapsing that into one flat answer.

Mention & Citation Consistency — One scan is a snapshot, not a track record. We track how reliably each question gets answered the same way over time, so you know which numbers to actually trust and which ones to take with a grain of salt.

Retrieval Readiness — This one we're proudest of. For every question you're missing, we show you the page that got cited instead of yours, score both against the question, and surface real, checkable signals — page structure, whether that domain shows up elsewhere in your results — that help explain the gap. And we're upfront about what the score actually means: it's the closest-matching passage we could find, not a verified or complete answer to the question. A low score usually just means the page doesn't address that question yet — not that we missed something better.

None of this came from a whiteboard. Every one of these checks got built off a real scan, a real false positive, or a real "wait, why did that happen" moment — and we tested each one against real data before shipping it.

Curious where your own brand actually stands with AI? Try it free at https://www.webscore.dev/

GEO is the new SEO — and most sites are failing at it

Krutika Galvankar — Thu, 13 Aug 2026 17:33:16 +0000

I built a tool that checks how visible your site is to AI engines like ChatGPT, Perplexity, and Gemini — and the results are eye-opening.

Meta tags, backlinks, Core Web Vitals — the SEO checklist is well-known. But there's a new game in town: Generative Engine Optimization (GEO).

When someone asks ChatGPT "what's the best tool for X?", does your brand show up? When Perplexity answers a question in your niche, does it cite you?

Most sites have no idea.

What GEO actually checks
After building the GEO agent in WebScore, here are the signals that actually matter for AI engine visibility:

llms.txt
AI crawlers look for /llms.txt — a plain-text file that tells LLMs what your site is about and what they're allowed to use. Think robots.txt but for AI. Most sites don't have one.
E-E-A-T signals
Experience, Expertise, Authoritativeness, Trustworthiness. AI models are trained to favour sites with clear author attribution, About pages, Contact pages, and organisation schema. Missing any of these? You're invisible.
FAQ schema
Structured FAQPage JSON-LD gives AI engines pre-digested Q&A pairs to pull from. It's one of the highest-ROI things you can add.
Authority citations
Pages that cite 2+ authoritative sources (Wikipedia, government sites, academic papers) get 27.5% more AI visibility according to research. AI engines use outbound authority links as credibility signals.
Wikidata entity
ChatGPT, Gemini, and Perplexity use Wikidata to validate brand facts — founding date, industry, HQ, products. Without a Wikidata entry, AI engines have no structured knowledge graph anchor for your brand.
Crawl access
Are GPTBot, ClaudeBot, PerplexityBot, and GoogleOther allowed in your robots.txt? Many sites accidentally block them.

What we found running it on real sites
~60% of sites block at least one major AI crawler unintentionally
~80% have no llms.txt
~70% are missing FAQ schema entirely
Sites with Wikidata entries get cited 3x more often in AI responses
How we measure it
The GEO agent in WebScore runs live checks against your URL and returns:

AI Mention Rate — how often your brand appears in AI responses
Citation Rate — how often AI engines link back to you as a source
Issue list — specific fixes ranked by impact

https://www.webscore.dev/
No signup. Results in ~60 seconds.

How to Track Your Brand's Visibility in ChatGPT, Gemini, Perplexity & Claude (With Code)

Krutika Galvankar — Fri, 07 Aug 2026 13:05:09 +0000

AI search engines like ChatGPT, Gemini, Perplexity, and Claude are
changing how people discover brands. Instead of clicking through
Google results, users now ask AI — and the AI picks who to mention.

The question is: is your brand being mentioned?

Most tools to answer are built for marketers, not developers. So I built webscore-sdk — an npm package that lets you measure this programmatically.

What is GEO?

GEO (Generative Engine Optimization) is the practice of improving
your brand's visibility in AI-generated answers. Think of it like
SEO, but instead of ranking on Google, you're trying to get mentioned
when someone asks ChatGPT "what's the best tool for X?"

Two key metrics matter:

Mention rate — % of relevant prompts where your brand appears
Citation rate — % of prompts where your website is linked

Install

npm install webscore-sdk

Quickstart

import { WebScore } from 'webscore-sdk'

const client = new WebScore('your_api_key')

const result = await client.geo.scan('https://yoursite.com')

console.log(result.mentionRate)  // e.g. 67
console.log(result.citationRate) // e.g. 42
console.log(result.sentiment)    // "positive"
console.log(result.score)        // 0–100 GEO score

Get a free API key at webscore.dev.

Free Tier

The free plan includes 10 GEO scans to try it out — no credit
card required. Paid plans with higher limits are coming soon.

npm: webscore-sdk

Live tool: webscore.dev

API docs: webscore.dev/api-docs

Would love feedback on the prompt methodology or the
mention/citation split. Drop a comment below!