I built an opinionated AI agent to respond to EU consultations

Name: I built an opinionated AI agent to respond to EU consultations
Availability: InStock
Author: whp_wessel

by whp_wessel·Mar 9, 2026·1 point·0 comments

Visit Project View on HN

AI Analysis

●MidBold BetZero to One

AI lobbyist auto-submits policy responses, but lacks proof of impact or traction.

Strengths

•Novel framing of AI agents as democratized lobbying—genuine conceptual freshness.
•Multi-stage LLM pipeline (draft, critique, rewrite) shows thoughtful prompt engineering.
•Public dashboard transparency prevents black-box advocacy, ethical guardrail.

Weaknesses

•No evidence of submissions actually working or gaining traction with policymakers.
•Twitter/dashboard only—no functioning portal link, making claims unverifiable.

Post Description

I built Commento, an AI agent that acts as an automated lobbyist. It tracks open public policy consultations in the EU and the Netherlands, and automatically drafts and submits responses advocating for pro-growth, pro-creative destruction policies.

The positions are grounded in frameworks like the Draghi Report, the Wennink Report, and the Dutch National AI Deltaplan.

The pipeline consists of 4 steps:

Discover: Crawling government portals for open consultations. Draft: A 3-pass LLM pipeline (draft, critique, rewrite). Submit: Automated browser submission to the portal. Publish: A public dashboard for full transparency on what the agent submits.

I see this project as an exploration of how AI agents can interact with government policy and "democratise" lobbying.