Rivac LabsOur Work
What we're actually building
Real client work, each shown at whatever stage it's actually at — not a portfolio of finished projects yet, but the real thing as it happens.
Real Client Work
Surplyst — Surplus Lines Market Intelligence
A data-intelligence platform that automates market-share tracking for the surplus lines insurance industry, replacing manual PDF analysis with a continuously updated feed of carrier performance data.
See what we're buildingRevalex — Agent Action-Safety Platform
An evaluation platform built around a genuinely different question than existing tools: not "did the agent say the right thing," but "did the agent's actions — refunds, writes, deploys — happen safely." Grades agent behavior, not agent text, and blocks a risky deploy in CI before it reaches production.
See what we're buildingMore Client Engagements
Velatir — AI Governance & Shadow-AI Oversight Platform
A platform giving enterprises visibility and control over how employees actually use AI day to day, closing the "shadow AI" gap with real-time policy enforcement and compliance evidence.
See what we built
Visiby — AI Citation Intelligence for Brand Visibility
Tracks whether and how brands get cited inside AI-generated answers across ChatGPT, Perplexity, and Gemini, turning citation gaps into specific, prioritized content fixes.
See what we built
Wisry — AI Ad Generation for Ecommerce
Analyzes a brand's highest-performing ads and automatically generates new, high-ROAS ad campaigns across image and video.
See what we built
Nexcade — AI Agents for Freight-Forwarding Desks
A suite of AI agents that quote, tender, and book freight-forwarding work automatically, consolidating rates and requests scattered across email, portals, and TMS systems.
See what we built
Marmot Data — Open-Source Data Catalog & Lineage
A self-hostable data catalog that indexes an organization's data infrastructure and serves that context to both people and AI agents via MCP.
See what we builtPage 1 of 4 — 19 engagements
Illustrative Process Walkthroughs
How a project like this runs with Rivac Labs
8 walkthroughs of our six-step process, one for each common kind of engagement — not write-ups of completed client work.
1-2 weeks
Startup MVP
Idea to a live, user-tested product in roughly 1-2 weeks.
See how it runs2-4 weeks
Enterprise Feature
Adding a major feature to an existing complex system without breaking compliance or stakeholder alignment, roughly 2-4 weeks.
See how it runs1-2 weeks
Multi-Channel Marketing Campaign
Coordinated launch across several platforms with one brand voice, roughly 1-2 weeks.
See how it runsHours to days
Production Incident Response
A minutes-to-hours support engagement when something's broken in production, with a written post-mortem afterward.
See how it runs1-3 weeks
Customer-Facing AI Agent
A human-supervised AI agent that handles real customer conversations, live in roughly 1-3 weeks.
See how it runs1-2 weeks
Back-Office Workflow Automation
Turning a slow, manual internal process into an automated pipeline a human still signs off on, roughly 1-2 weeks.
See how it runs2-3 weeks
Data & Reporting Infrastructure
Replacing scattered spreadsheets with a live data pipeline and a dashboard leadership trusts, roughly 2-3 weeks.
See how it runs2-4 weeks
AI Search Visibility (AEO/GEO)
Making a brand the answer ChatGPT, Perplexity, and Gemini give, with first measurable movement in roughly 2-4 weeks.
See how it runs