Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

Solving the ~95% legislative coverage gap using LLM's

Details

External ID
46289073
Source
HN
Company
—
Product
Solving the ~95% legislative coverage gap using LLM's
Website domain
lustra.news
Launched
Dec. 16, 2025
Cohort
—
Upvotes
41
Upvotes percentile
0.7891221374045801
Tags
—
Fetched at
Sept. 7, 2026, 9:25 p.m.
Updated at
Sept. 7, 2026, 9:25 p.m.

Description

Hi HN, I'm Jacek, the solo founder behind this project (Lustra).The Problem: 95% of legislation goes unnoticed because raw legal texts are unreadable. Media coverage is optimized for outrage, not insight.The Solution. I built a digital public infrastructure that:1. Ingests & Sterilizes: Parses raw bills (PDF/XML) from US & PL APIs. Uses LLMs (Vertex AI, temp=0, strict JSON) to strip political spin.2. Civic Algorithm: The main feed isn't sorted by an editorial board. It's sorted by user votes ("Shadow Parliament"). What the community cares about rises to the top.3. Civic Projects: An incubator for citizen legislation. Users submit drafts (like our Human Preservation Act), which are vetted by AI scoring and displayed with visual parity alongside government bills.Tech Stack:Frontend: Flutter (Web & Mobile Monorepo),Backend: Firebase + Google Cloud Run,AI: Vertex AI (Gemini 2.5 Flash),License: PolyForm Noncommercial — source is available for inspection, learning, and non-commercial civic use. Commercial use would require a separate agreement.I am looking for contributors. I have the US and Poland live. EU, UK, FR, DE in pipeline, partially available. I need help building Data Adapters for other parliaments (the core logic is country-agnostic). If you want to help audit the code or add a country, check the repo. The goal is to complete the database as much as possible with current funding.Live App: https://lustra.newsRepo: https://github.com/fokdelafons/lustraDev Log: https://lustrainitiative.substack.com

Enrichment

Theme
searchable public records and archives
Vertical
Government
Function
Agent / copilot
Audience
B2B
AI stance
AI-native
Project type
Commercial product
Normalized one-liner
llm-powered legislative analysis
Manually corrected
False

Could you build this?

Partial The front-end and basic LLM summarization pipeline are straightforward, but building a reliable, high-throughput ingestion and sterilization pipeline across disparate state and federal legislative bodies requires substantial domain-specific data scraping and parsing infrastructure.

What it would actually take: The system requires an orchestration pipeline (e.g., Temporal or Dagster) connecting scrapers for diverse government legislative portals, OCR/PDF text extraction engines, legal document chunking and cross-referencing systems, and an LLM evaluation framework to ensure legal accuracy without hallucination. Specialized legal engineering and continuous scraper maintenance are needed to manage irregular governmental data formats.

Discussion

20 comments analyzed.

Competitors mentioned: EU law adoption frameworks, Manual hand-review processes for legal conflicts

Concerns raised: LLM hallucinations and omissions in bill summaries, Innate model biases impossible to fully strip, Compression of information is inherent interpretation, Models choose what to mention/omit despite constraints, Low adult literacy makes LLM summaries ineffective

Feature requests: Automated diffing and traceability to source sections, Use 'Representatives' instead of 'MPs' terminology, Support for senators in addition to parliament members, Fix voting error on Civic Projects, Clarify license in description

Competitors

Other products that read as similar to this one — 27 launches clear the similarity bar, closest 8 shown.

Attention rank: #6 of 28 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 6 days after the earliest competitor.

Other launches for this product

Same idea, different domain

Nobody's really built a agent / copilot tool for Agriculture yet.