Citizen technologies and open source for the public good
Voir tous les tags
Today we completed a major architectural milestone: modular prompt management for Forseti461. Each feature now has its own versioned prompt in Opik, enabling independent optimization and A/B testing.
From a single monolithic prompt to a clean separation of concerns — each Forseti feature can now evolve independently while sharing a common persona.
Forseti461 est un agent IA qui modère automatiquement les contributions citoyennes sur les plateformes de démocratie participative — approuvant uniquement les idées concrètes, constructives et localement pertinentes, tout en rejetant les attaques personnelles, le spam, les hors-sujets ou la désinformation, et en expliquant toujours ses décisions avec des retours respectueux et actionnables.
Ce week-end, Facebook nous a rappelé que la démocratie est fragile. Commentaires toxiques, attaques personnelles et diatribes hors-sujet ont envahi les discussions sur les enjeux locaux. Le signal se perd dans le bruit. Les citoyens se désengagent. Les voix constructives abandonnent.
Et si nous pouvions protéger le débat civique à grande échelle ?
Goal: Create a systematic approach to test and improve our AI-powered charter validation system.
For the Encode Hackathon first submission, we focused on building the infrastructure to ensure Forseti 461 (our charter validation agent) catches all violations reliably. The key insight: you can't improve what you can't measure.
Here is the assessment of the catch-up call between @jnxmas and Victor regarding the Ò Capistaine project status and immediate priorities.
@jnxmas and Victor discussed the immediate roadmap for the Opik/Commit to Change Hackathon MVP submission (deadline: ~1 day, 14 hours). Victor has successfully downloaded approximately 4,000 PDFs (including ~3,965 deliberation documents), though he noted some potential duplicates and that the download process was synchronous and could be optimized later. He has committed changes to a development branch but not yet merged them, preferring to use GitHub as a medium to exchange the code while keeping the large PDF dataset local (or shared via a specific sub-directory).
The team agreed on a strategy for the Hackathon demo deployment. Instead of using Vercel, which complicates environment variable management for their specific security setup (ngrok, multiple API keys for Opik, Firecrawl, Gemini, etc.), @jnxmas will run the demo from his local machine using a secure, paid ngrok tunnel (ocapistaine.ngrok.app). This setup allows the jury to interact with the Streamlit UI (restricted to Ollama for the external demo) while the team can continue testing other models (Gemini) locally. The architecture involves Locki.io -> Vaettir Orchestration -> Local Machine (Ocapistaine Agent).
Context: Audierne 2026 Election Platform
This document outlines how we will leverage the Google Gemini ecosystem (AI Studio, Flash models, and Agentic workflows) to accelerate the development of the Locki project. By utilizing these tools, we aim to bridge the gap between human ideation and automated N8N workflows, specifically for the Commit to Change hackathon and the subsequent election period.
This document summarizes key insights from the recent team sync following Jean-Noël's attendance at the Google Gemini workshop. The focus is on accelerating the Locki / Ò Capistaine project by transitioning from manual human analysis to automated agent workflows.
Project: Locki / Ò Capistaine (audierne2026) - AI-powered civic transparency & participatory democracy platform for Audierne 2026 local elections (France) Core Mission: Build a neutral, source-based RAG chatbot to answer citizen questions about 4 municipal programs, automate contribution validation against charter rules, crawl/process municipal data (150+ links, 4,000+ PDFs), and showcase Opik integration for the "Commit to Change" Hackathon. Critical Timeline:
AI-Powered Civic Transparency for Local Democracy
This year, I will finally understand my local elections and get involved as a citizen.
Sound familiar? Every election cycle, millions of citizens want to participate but face the same wall: scattered documents, administrative jargon, and no time to dig through years of municipal decisions.
This January, I stopped just wishing — and started building.
This lecture, led by Abby Morgan, an AI Research Engineer, introduces AI evaluation as a systematic feedback loop for transitioning prototypes to production-ready systems. It outlines the four key components of a useful evaluation: a target capability, a test set, a scoring method, and decision rules. The session differentiates between general benchmarks and specific product evaluations, emphasizing the need for observability in agent evaluation. It demonstrates using OPIK, an open-source tool, to track, debug, and evaluate LLM agents through features like traces, spans, 'LM as a judge', and regression testing datasets.