The Well of Kvasir: When the RAG Pipeline Learned to Listen
· 9 min read
How a single email from a candidate revealed four distinct failures in four distinct layers — and why Separation of Concerns was the only way to fix them
9 posts tagged with "Opik"
Articles on Opik LLM observability and prompt optimization
View All TagsClean the Windshield: Enhancing RAG Without Upgrading the Engine
· 8 min read
Three near-zero-cost interventions that improved our civic RAG pipeline more than any model change could
The Conversation Loop: When Citizens Teach the AI What Matters
· 6 min read
How streaming, threads, and two small buttons turned a Q&A tool into a learning system
The RAG Adventure Begins: When Documents Learn to Speak
· 5 min read
How 60 social media screenshots became a searchable civic memory in one afternoon
The Impossible Sprint: Building Civic AI in 4 Weeks
· 5 min read
"It looks impossible - but it's a hackathon. Cheers!"
This is the story of OCapistaine, a civic transparency AI built during the Encode "Commit to Change" Hackathon. It's a story of blocked pipelines, strategic pivots, 4,000 municipal PDFs, and the belief that AI can help citizens understand their local democracy.
Spoiler: We shipped it. Barely.
Sprint Planning: Mistral Document AI RAG Prototype
· 5 min read
Sprint planning call between Johnny (@jnxmas) and Victor (@zcbtvag) to align on the Sunday midnight deadline. Key decision: pivot to Mistral Document AI + Batch + Agent for a rapid RAG prototype.
Call Goals
- Align on immediate priorities before Sunday midnight
- Decide RAG approach and OCR path
- Clarify repo/branch workflow and submodule handling
- Assign ownership for Mistral Document AI setup
- Coordinate API keys and cost management
Project Sync: Opik Progress & OCR Blockers
· 3 min read
Quick catch-up between Johnny (@jnxmas) and Victor (@zcbtvag) covering Opik integration progress and OCR pipeline challenges.
Summary
Johnny showcased recent progress on Opik prompt optimization. A new architecture is in place where prompts are no longer hardcoded but managed via an Opik Prompt Library. The "Charter Validation" prompt has already been optimized using this system.
A new mock-up feature can automatically generate contributions (even with violations) from existing meeting reports. The goal is to create a robust dataset to test and improve the validation agent. However, this auto-generation currently produces repetitive content - a challenge that will need addressing by identifying and aggregating duplicate contributions.
Forseti461 Feature Architecture: Modular Prompts with Opik Versioning
· 4 min read
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.
tip
From a single monolithic prompt to a clean separation of concerns — each Forseti feature can now evolve independently while sharing a common persona.
Forseti461 Prompt v1: Charter-Proofing AI Moderation for Audierne2026
· 7 min read
Forseti461 is an AI agent that automatically moderates citizen contributions to participatory democracy platforms — approving only concrete, constructive, locally relevant ideas while rejecting personal attacks, spam, off-topic posts, or misinformation, and always explaining decisions with respectful, actionable feedback.
tip
This weekend, Facebook reminded us that democracy is fragile. Toxic comments, personal attacks, and off-topic rants flooded discussions about local issues. The signal gets lost in the noise. Citizens disengage. Constructive voices give up.
What if we could protect civic discourse at scale?