Case Study - Ground truth for AI agents acting in the physical world

Overview

A fluent model will confidently invent the weather at a place it has never queried. When that model is just chatting, the made-up fact is harmless. When it is an agent acting in the world, the same invented fact becomes a wrong action with a real cost. Pointmoon was built for that second case: it is the agent-callable trust layer for physical and environmental reality.

The idea is simple. Before a model speaks or acts about a place, it asks Pointmoon what is actually true there right now. Pointmoon reads live data from real sources, the weather, the turning season, rivers and tides, the shape of the land, the sun and the moon, and hands back a short, grounded read of the present moment. Three guarantees come with every answer. Each fact is sourced, with a timestamp and a confidence value. Freshness is tracked, so a stale reading is never passed off as current. And where the data will not hold, Pointmoon returns a typed silence with a reason, instead of a confident fabrication.

That refusal to guess is the product. There is no language model anywhere in the fact layer, so there is nothing in it that can drift or hallucinate. Pointmoon does not write sentences. Voice belongs to the model that calls it. Pointmoon brings the grounded fact, or the honest gap, and lets the agent decide what to do with it.

It ships as real infrastructure built for agent builders: a clean API, an MCP server so an agent can pull verified field-truth the same way it reaches for any other tool, a versioned contract so consumers can upgrade safely, and an open-source quickstart anyone can run. It is built for anything acting on the physical world, from location-aware assistants to outdoor, logistics, and agriculture systems. The first product standing on it is Rewyld, where every place-aware practice is grounded in Pointmoon before a single word is spoken.

What we built