TIMELINE
weeks, brief to production
SCOPE
Brand + Platform
End-to-end build
CLIENT
IntelliFunnel Labs
techshorts.io
DELIVERABLES
8 major outputs
Brand to deployment
THE BRIEF
An AI-powered news platform.
No human editorial step.
Rishabh needed more than a website. He needed a complete brand identity and a production-ready platform — one that could aggregate tech news from multiple premium sources, generate concise AI summaries for each article, and present them through a clean mobile-first card interface, without any manual editorial work in between.
The platform also needed a whitepaper lead capture system and a full admin dashboard for content management and analytics. The target: brand, design system, and production platform — all delivered in 4 weeks.
WHAT WE DELIVERED
BRAND IDENTITY
A brand built for decision-makers.
TechShorts needed an identity that would earn the trust of CTOs, VPs of Engineering, and technology decision-makers at B2B companies. The brand had to feel premium and data-forward — not another generic tech startup aesthetic.
We built the full brand system from scratch: logo, colour palette, typography scale, component library, voice guidelines, and a complete brand guidelines document that the client's team could use independently.
Primary wordmark and icon variations
Dark and light background variants
Complete colour system with usage rules
Typography scale (display to caption)
Component library (buttons, cards, badges)
Brand voice and messaging guidelines
9-section brand guidelines document
BRAND COLOURS
TechShorts Red
#EF4444
Deep Navy
#0F172A
Slate 800
#1E293B
Electric Blue
#3B82F6
Purple
#A855F7
Inter — Primary typeface, weights 300–900
THE CHALLENGE
Four hard problems. Four weeks to solve them.
Brand identity from zero
No existing brand assets, no style guide, no visual direction. We built the complete identity system — logo, colours, type scale, and component library — before writing a single line of code.
Multi-source aggregation without duplication
Pulling from PRNewswire, NewsData.io, Currents, and GNews every 30 minutes — with hash-based and semantic deduplication so the same story never appears twice regardless of source.
AI summaries at exactly 60 words
Groq (Llama 3.1 70B) generates summaries that are exactly 60 words — not approximately. Cached permanently after first generation so AI cost does not scale with traffic.
Admin dashboard + production in 4 weeks
A full role-based admin panel covering article review, approval, lead management, and live analytics — built alongside the consumer product, not after it. Plus CI/CD, monitoring, documentation, and a full training session.
THE PLATFORM
What we shipped.
The main feed — InShorts-style cards with 60-word AI summaries, source badges, and category filtering across HR Tech, MarTech, FinTech, AI Tech, and more.
Gated whitepaper downloads with automated email delivery via Resend.
Mobile-first InShorts-style interface — designed for one-thumb navigation.
THE ARCHITECTURE
How 4 sources become one clean feed.
NEWS SOURCES
4 APIs
AGGREGATION
Every 30 min
DEDUPLICATION
Hash + Semantic
GROQ AI
Llama 3.1 70B
60 words exactly
PUBLISHED FEED
50-100/day · Cached
The pipeline runs automatically. Once an article is summarised, the result is cached permanently — meaning AI costs stay flat regardless of how many people read the same story.
THE ADMIN DASHBOARD
Full control. No developers required.
Article review, lead management, whitepaper publishing, and real-time analytics — built for non-technical users. Zero support requests after the handover training session.
WHAT WE BUILT IT WITH
Every choice was deliberate.
Next.js 14
React framework for the full stack — frontend, API routes, and serverless functions in one codebase.
Supabase
PostgreSQL with real-time subscriptions, full-text search, and built-in authentication for the admin panel.
Groq (Llama 3.1 70B)
AI summarisation at speed. Exactly 60-word summaries, cached permanently after first generation.
Resend
Transactional email for lead notifications and automated whitepaper delivery.
Vercel
Edge deployment with GitHub CI/CD. Every push to main deploys automatically.
Sentry
Error tracking and performance monitoring in production from day one.
THE OUTCOME
Delivered on time.
Every feature shipped.
The platform launched on schedule at the end of Week 4 — fully functional, production-deployed, and handed over with complete brand guidelines, technical documentation, a training session, and 30 days of post-launch support included.
The AI pipeline was processing articles from all four sources within 48 hours of the cron job going live. The admin dashboard was adopted without any support requests after the training session.
“I came to Utathya with a brief, a budget, and a 4-week deadline. Most agencies would have told me to be realistic. He told me what was possible and then delivered exactly that: brand, platform, and a working AI pipeline, all production-ready. I have not had to touch the codebase since launch.”
— Rishabh Shetty, Founder · IntelliFunnel Labs
HONEST REFLECTION
Four weeks is a tight window for a platform of this complexity. We delivered everything in scope — but with more runway, we would have invested more time in the relevance scoring algorithm and built a more sophisticated categorisation system from the start. The architecture supports it. We just did not have the time to build it properly in Version 2.