Relay is an agent for the weeks after a storm, when volunteers rotate out and the people who were reported once are forgotten. It listens across 311 calls, volunteer visit notes and utility updates, remembers every household for six weeks in MongoDB, and tracks every promise made to them. When a promise lapses or a household goes quiet, it proposes a follow-up with cited evidence for a coordinator to approve, and calls opted-in residents in their own language with hard-coded safety checks. It learns from its own outcomes, adjusting how often it checks in and carrying measured lessons into the next storm.
More from The Harness Engineering & Model Wrangling Hackathon
Ripple designs circuit boards from plain English, grades them against hidden checks, and evolves its own harness from the failures, going from 0/4 to 3/4 on…

Offload learns the work you repeat, so next time you can hand it over. Its engine, REM (Replay · Evolve · Merge), is an agent harness with a day/night cycle…
Recursive Computer Use is a local-first desktop automation harness that enables AI agents to execute tasks on your computer, verify outcomes locally, and…

Da Vinci is a recursive improvement CAD harness designed to support physical engineering tasks through specialized AI agents, programmatic CAD and automated…

CyclopsDiary gives factory workers wearing Meta AI glasses a shared memory of the floor. Every worker's glasses feed one MongoDB memory that keeps what was…

A harness that teaches itself what context to show Jev, TypeSafe's fast decision model, proves the result on a storm it never saw, and can't cheat because…