I built an AI travel agent for India's hidden destinations — here's the tech stack

KRISH — Wed, 26 Aug 2026 11:51:34 +0000

I spent 5 months building almanacindia.com — an editorial platform documenting India's genuinely hidden destinations. Not "offbeat" places that show up on every listicle. Places like Bara Bhangal (a permanently inhabited village with no road, reachable only by a 5-day trek over a 4,700m Himalayan pass) and Hunderman (a village that was Pakistani territory until 1971, 8km from Kargil).

Here's everything I built and how.

The Stack

Framework: Next.js 15 App Router with TypeScript, deployed on Cloudflare Pages via OpenNext. Static generation for 1,500+ pages at build time. No Git — Proton Drive with AES-256 encrypted backups.

Maps: Mapbox GL v3 Standard style. 96 Indian cities, 3D cinematic dusk lighting, destination pins, routing between places, satellite toggle, live rain/snow overlay from Open-Meteo (15-min cache). Night mode activates automatically after 7pm local time.

Expedition Books: Each destination gets a full book — About, History, What Nobody Tells You, The Moment, Before You Go. Books paginate using DOM-height measurement via Range.getClientRects() — not character count. Fonts load before pagination runs via document.fonts.ready. 32 books live.

Media: Cloudinary for all destination cover photos. g_auto crop handles landscape-to-portrait conversion for book covers. f_auto,q_auto across the board.

Auth: Firebase Auth with OAuth. Community chat via Firebase Realtime Database with admin moderation and 48hr auto-delete.

Email: Resend for the Inner Circle newsletter. Rotates 100 cities every 2 weeks.

AI Chat: The most interesting piece.

The AI Travel Agent

Built an editorial chat agent that opens with "Where do you want to disappear to?" — three starter chips, streams word by word, right-side push sidebar.

Provider: Ofox.ai (official Anthropic partner gateway) — solved the India payment problem after Anthropic's Stripe integration blocked all Indian cards.

Model: Claude Sonnet via Ofox.

Architecture:

Dynamic context loading — max 2 expedition books per question, under 7,000 token budget
Prompt caching — 71.6% cache hit rate on day one
Retrieval logic — books only attach when the question names a specific destination or region, not on departure intent words
Postgres Q&A cache — 80% word-match threshold, 7-day expiry
[ALMANAC_GAP] logs — every unanswered region query goes to a content roadmap

Gap rule: When a user asks about a place we haven't documented, the agent acknowledges the gap and redirects to the closest documented region. Never halluccinates.

SEO/GEO Architecture

Built specifically for AI citation:

llms.txt at root with all 58 destination URLs and descriptions
robots.txt explicitly allows GPTBot, ClaudeBot, PerplexityBot, OAI-SearchBot, Google-Extended
Cloudflare AI Crawl Control — all crawlers set to Allow
IndexNow — 1,531 pages submitted on first run
FAQ schema (153 Q&A pairs) for AI answer engine visibility
Canonical URLs enforced across all 1,500+ pages
Attraction descriptions server-trimmed to 120 chars on city pages so full text only lives on attraction pages — fixes the duplicate content problem Google penalises
The Hardest Problem

Distribution. The product works. Getting the first 1,000 people to see it is the actual problem.

If you've solved this for a research-heavy content product — I want to hear how.

almanacindia.com — The India nobody shows you.

How I built a Next.js travel discovery platform using AI as my junior dev

KRISH — Tue, 26 May 2026 18:22:52 +0000

I’ve been working on Almanac, a travel discovery platform focused on uncharted Indian destinations, heritage sites, and regions like Leh-Ladakh. I know system architecture and data, but I wanted to move fast. So, I used AI to write the core frontend code.

The Stack:

Frontend: Next.js & Tailwind CSS
Hosting: Cloudflare
Visuals: Mapbox integration for 3D renderings of palaces and statues
Auth: GitHub OAuth

The Process:

I acted as the tech lead. I handled compiling the custom destination databases, sorting the image addresses, and managing the architecture. I used AI as my junior developer to pump out the boilerplate components, wire up the routing, and handle the responsive Tailwind layouts. It cut my development time in half.

The Hurdle (Where I need your help):

Because this project relies entirely on an outbound affiliate model, my Conversion Rate Optimization (CRO) has to be flawless. The UI needs to build immediate visual trust so users actually feel comfortable clicking the partner links.

I need this community to tear down my frontend.

Does the layout feel premium?
Are the image loads and transitions snappy on your end?
Where is the friction?

Live Site: https://manzil.online/

Roast the UI/UX in the comments. I'll be reading them and implementing fixes to the codebase.

DEV Community: KRISH

I built an AI travel agent for India's hidden destinations — here's the tech stack

How I built a Next.js travel discovery platform using AI as my junior dev

The Stack:

The Process:

The Hurdle (Where I need your help):