Tenderly

Tenderly is an AI-powered tender-management platform that turns the painful, paperwork-heavy process of finding, analysing, and bidding on Malaysian government projects into a few guided clicks.

Comment

Introduction

Our team is three students on three different timetables who still believe Malaysia can run clean, transparent procurement:

  • Harjeet – 3rd-year Information Engineering student, HAW Hamburg
  • Henry – 1st-year Computer Science student, Universität Hamburg
  • Bhanu – fresh OSSD graduate heading for ETH Zürich CS

We see the same pattern everywhere, especially in Malaysia, where winning a tender is still a “who-you-know” game. We want the best contractor, not the best connection, to win. Even while juggling work, classes, and side projects, we knew this had to exist, so we built Tenderly.

Inspiration

We set out to make public tenders radically more accessible for Malaysian and ASEAN SMEs. Today, winning a government contract still comes down to who deciphers a maze of Malay-only PDFs fastest—or who knows the procurement officer. Existing Malaysian services like Tender2u (Petaling Jaya, 2003) and TenderDB (2014) do little more than email filtered tender notices; newer players such as TenderDirect and TenderPanel charge for the same alerts. None of them use AI to read the fine print, flag hidden eligibility traps, draft compliant proposals, or predict win probability.

Tenderly was born to fill that gap. We’re building a bidder-first AI web platform that scrapes every tender pack, translates it, scores a company’s eligibility in real time, auto-drafts the proposal, and even records the submission’s hash on Algorand—removing the opacity and connection-driven bias that stifle honest SMEs across Southeast Asia.

We don't just help you find proposals.. We help you WIN them

What it does

  • Scrape → Structure – pulls tender bundles, stores files in Supabase Storage, writes clean JSON metadata to Postgres. (Not implemented. Only pulled 7 Official tenders from website)
  • Translate – seamless Malay ↔ English via Lingo.dev.
  • AI Summary & Eligibility – GPT-4o with RAG explains each tender and scores your company profile against every requirement.
  • Proposal Wizard – one-click draft (cover letter, pricing sheet, Gantt chart).
  • Algorand Attestation – hashes each submitted PDF and records the tx-id, creating a tamper-proof supplier reputation.

How we built it

  • Frontend – Next.js 15, TailwindCSS, shadcn/ui, SWR hooks, React Context, all inside Bolt.new.
  • Backend – Supabase Auth, Postgres (RLS), Storage, Edge Functions for heavy PDF parsing.
  • AI / Translation – OpenAI GPT-4o for RAG tasks; Lingo.dev for bilingual accuracy.
  • Blockchain – Algorand via Nodely endpoints for immutable attestations.
  • Dev tooling – seed-tenders.js for demo data, CI + snapshot tests to catch React import mishaps.

Challenges we ran into

  • Balancing time to work on studies and time to work on this hackathon since we all had different schedules.
  • Browser sandbox blocked pdf-parse; fixed by off-loading to a Supabase Edge Function.
  • Duplicate filenames in tender packs; solved with deterministic keys scraper//.
  • A single mis-export of TenderCard crashed the feed minutes before demo; CI now enforces import sanity.
  • Prompt-tuning to stop GPT hallucinations across bilingual procurement jargon.
  • Algorand mainnet deployment didnt work, and we had to revert to our previous build

Accomplishments we’re proud of

  • Turned raw tender folders into structured, AI-ready JSON in under a week.
  • Building an industry-ready web app within a month!
  • Live eligibility scoring that updates the moment a supplier uploads a new cert.
  • Polished multi-page UI that loads on 3 G—and built entirely in Bolt.

What we learned

Grounding prompts with exact snippets kills hallucinations, procurement Malay needs a curated translation corpus, and robust testing saves launches. Most SMEs care less about AI magic than about a verifiable audit trail proving fair evaluation.

What’s next for Tenderly

  1. Instead of using a scraper, we plan to partner with the official platform; ePerolahan to integrate their API into our system
  2. Fixing Algorand problems
  3. Evaluator dashboard for side-by-side bid comparison.
  4. Mobile push alerts for tenders that match saved profiles.
  5. Public API so ERP tools can pull tender status and on-chain attestations.

Built With

Share this project:

Updates