How to optimise for ChatGPT, Claude, and Perplexity (GEO) — in Kolkata
A Generative Engine Optimization (GEO) playbook covering llms.txt, citation-grade content, and the entity-graph signals LLM crawlers actually use. Calibrated to Kolkata — local industry mix: fnb, retail, finance.
GEO ≠ SEO. LLM crawlers don't use rankings; they use citation density, entity strength, and structured data.
llms.txt + llms-full.txt is the new robots.txt for LLM ingestion.
Local angle for Kolkata: fnb + retail.
Why this matters in Kolkata
This guide applies the playbook to Kolkata. Local economic mix: fnb, retail, finance, healthcare.
- State
- West Bengal
- Population (urban)
- 15M+
- Average CPC (₹)
- Typical CAC (₹)
- fnb
- retail
- finance
- healthcare
- media
Salt Lake · Park Street · New Town · Howrah
Step-by-step in Kolkata
- Step 01
Publish llms.txt and llms-full.txt
Per the llmstxt.org convention: /llms.txt is a Markdown index of your high-value pages. /llms-full.txt is the concatenated full content. These guide LLM crawlers to canonical sources without scraping HTML.
- Step 02
Strengthen entity grounding
Use schema.org sameAs to link your brand entity to Wikipedia (if eligible), Crunchbase, LinkedIn, and Wikidata. LLMs disambiguate entities through this graph.
- Step 03
Write for citation, not ranking
LLMs cite specific claims with named sources. Format: '<claim> — <source>'. Avoid passive aggregation; use named expert quotes, named methodologies, and named benchmarks.
- Step 04
Build the FAQ surface aggressively
FAQPage schema + 8–12 FAQ items per pillar topic. Perplexity and Claude lift FAQ answers verbatim 40%+ of the time when schema is clean.
- Step 05
Monitor LLM-driven traffic
GA4 referral source filter for 'chat.openai.com', 'perplexity.ai', 'claude.ai', 'gemini.google.com', 'copilot.microsoft.com'. Tag in BigQuery as 'llm_referral' for cohort analysis.
What goes wrong in Kolkata
- Trying to skip stages — playbooks compound; out-of-order execution leaves earlier-stage work undone and the later steps don't catch.
- Optimising the wrong leading indicator — picking a vanity metric (impressions, reach, follower count) instead of the playbook's actual primary KPI.
- Running the playbook against a broken funnel — the playbook ships traffic / leads / activity to a leaky landing page or onboarding, amplifying the leak.
- Hiring junior-only execution and expecting senior judgement — the playbook lists tactics; the calls between tactics need a senior operator.
- Cutting the playbook on a single bad month — compounding plays need quarterly review windows; monthly noise will kill the program prematurely.
What to track for Kolkata
- Time-to-first-signal — how long until you see the leading indicator move (typically 2-4 weeks for paid, 4-9 months for organic).
- Step-completion rate — what percentage of the playbook is actually shipped vs documented.
- Cost per primary outcome — CAC for acquisition playbooks, CPL for lead-gen, revenue-per-customer for retention.
- Velocity — how many full playbook cycles you complete per quarter.
Tools + channels we use here
- Notion / LinearSource-of-truth for the playbook; track step ownership + due dates.
- GA4 + GTM Server-SideServer-side attribution for the playbook's outcome KPIs.
- Meta Business / Google AdsPaid execution surfaces if the playbook is acquisition-led.
- Klaviyo / WebEngage / Customer.ioLifecycle + nurture execution layer.
- Looker Studio / MixpanelDashboards for the leading + lagging indicators.
- Slack + weekly stand-upsCross-team coordination on the playbook.
Terms used on this page
Want this scoped to Kolkata?
30 minutes, no slides. We'll review your setup against Kolkata-specific search demand, competitor density, and channel mix — and hand you the three highest-leverage moves.
Frequently asked questions
Do LLMs respect robots.txt and llms.txt?
OpenAI (GPTBot), Anthropic (ClaudeBot), and Google-Extended respect robots.txt. The llms.txt convention is voluntary but increasingly honored by Perplexity and Anthropic. Block training, allow inference if you want citations.
How long until GEO efforts show citations?
LLM index refresh cycles run 2–8 weeks depending on the model. Expect first citations from Perplexity in 4–6 weeks, ChatGPT in 6–10 weeks, Claude in 8–12 weeks after publishing.
Do LLMs respect robots.txt and llms.txt?
OpenAI (GPTBot), Anthropic (ClaudeBot), and Google-Extended respect robots.txt. The llms.txt convention is voluntary but increasingly honored by Perplexity and Anthropic. Block training, allow inference if you want citations.
How long until GEO efforts show citations?
LLM index refresh cycles run 2–8 weeks depending on the model. Expect first citations from Perplexity in 4–6 weeks, ChatGPT in 6–10 weeks, Claude in 8–12 weeks after publishing.
How long does this playbook take end-to-end?
The named-step durations are listed inline; total elapsed time depends on how many steps run in parallel. A typical sequential execution takes 20-30 weeks; parallel execution compresses that by 30-50%.
Can we run this in-house or do we need an agency?
In-house works when you have the seniority + bandwidth on the named-step disciplines. Most teams that try in-house solo end up doing 60-70% of the work and missing the cross-step optimisation. An agency or fractional senior compresses time-to-result by 30-50% on average.
What's the minimum budget to start?
Budget breaks into three lines: agency fee (if applicable), media spend, and tools. The combined minimum to make data-driven decisions in 2026 is ₹1L/month for paid-heavy playbooks. Below that, manual optimisation in-house is more honest than an agency retainer.
When do we stop and reassess?
Quarterly. Each quarter, review the leading indicator (movement) and the lagging indicator (outcome). If both are positive: scale. If leading is positive but lagging isn't: wait one more quarter. If leading is negative: change the playbook, not just the spend.
Does this playbook work outside India / outside the listed market?
The framework transfers; the specifics (CPCs, channels, compliance, language overlays) need adapting. The named steps are universal; the within-step tactics adapt to the local market.
Long-form guides on related topics
Other guides for Kolkata
- How to launch a D2C brand in India in 90 days — Kolkata
- How to validate a D2C product before manufacturing — Kolkata
- How to reduce CAC by 30% without lowering ad spend — Kolkata
- How to calculate true CAC for an Indian D2C brand — Kolkata
- How to optimise for Google AI Overviews in 2026 — Kolkata
- How to write a direct answer for Google AI Overviews — Kolkata
This guide for other cities
- How to optimise for ChatGPT, Claude, and Perplexity (GEO) — Mumbai
- How to optimise for ChatGPT, Claude, and Perplexity (GEO) — Bangalore
- How to optimise for ChatGPT, Claude, and Perplexity (GEO) — Delhi NCR
- How to optimise for ChatGPT, Claude, and Perplexity (GEO) — Chennai
- How to optimise for ChatGPT, Claude, and Perplexity (GEO) — Hyderabad
- How to optimise for ChatGPT, Claude, and Perplexity (GEO) — Pune
Sources & references
Cited primary and analyst sources. Independent of Frameleads' own data.
- IBEF — India Brand Equity Foundation: Indian Industry Reports — IBEF (Ministry of Commerce & Industry)
Sector-level market size, growth, and policy context for Indian industries.
- IAMAI — Internet & Mobile Association of India — IAMAI
Digital advertising industry body; reports on India internet user base, ad spend, and platform shares.
- MoSPI — Ministry of Statistics and Programme Implementation — Government of India
Primary source for India macro-economic indicators (CPI, GDP, household consumption).
- ASCI Code for Self-Regulation of Advertising in India — Advertising Standards Council of India
Mandatory baseline for all advertising claims in India — including digital, influencer, and comparative ads.
Run growth marketing in Kolkata with a senior team.
Book a free 30-minute audit. We'll review your current marketing against the Kolkata benchmarks above and tell you the three highest-leverage moves.