Short-term rental welcome guide: write it from a video
Film one narrated walkthrough and get what a guest welcome guide needs: Wi-Fi, heating, trash, keys, appliances. Who sees the codes, and how to keep it current.
Blog
Context for AI agents about physical spaces
Notes on giving AI agents context about physical spaces: the API, the MCP server, the iPhone app, and what we learn building Space Context. RSS feed
Campervan and boat handover inventory from one video
What to film when a campervan or a boat changes hands, what the API records (VIN plate, gas, battery, seacocks) and how to compare the handover with the return.
RoomPlan alternative without LiDAR: what is in the room
Apple RoomPlan maps walls and furniture boxes on LiDAR devices. To know what is in a room, where and in what state, from any video, here is the other half.
Vision model hallucinations: check each claim on its photo
A vision model can name an object its photo does not show. How Space Context asks every record again on its own frames, and what 38 of 38 and 0 of 227 mean.
Check-in and check-out inventory: compare two video scans
How a video check-in/check-out comparison works: what counts as added, moved or gone, why "not seen" is not "gone", and how to run it on a real example.
Context layer for AI agents: knowledge of physical places
How to give an AI agent real knowledge of a physical place: what a Space Document is, the four ways in, evidence frames, and what it never invents.
Home inventory video for insurance: how to film it well
How to film a home inventory video room by room, what Space Context records from it (items, condition, timestamped frames) and how to keep it current.
How to give an AI agent access without sharing passwords
Least privilege for AI agents in practice: scoped API keys, redacted Wi-Fi passwords and door codes, read-only MCP connections, spending caps and revocation.
MCP server for physical spaces: connect Claude to your home
Connect Claude, ChatGPT, Claude Code, Codex, Cursor or VS Code to the spaces you filmed: exact setup per client, the 17 tools, access levels and real output.
Office and building knowledge base for AI assistants
Film a building once and let AI assistants answer "where is the water shut-off?" with cited records: key locations, coverage checklist, search and ask.
Prompt injection from the physical world: signs and speech
A sign or a sentence in a video can give orders to the AI agent that reads it later. How Space Context screens it, and what agent builders should still do.
Video to structured data API: turn a walkthrough into JSON
Turn a walkthrough video into structured JSON with one API: create, upload, start, follow. curl, CLI and SDK code, limits, the output fields and the price.
x402 example: how AI agents pay for an API with USDC
A working x402 example on Base and Solana: an AI agent pays USDC and gets an API key and credit in one HTTP call. The 402 flow, spend caps, rotation, errors.