CasaSol · Architecture & Design
A model with full access to your private context outperforms a more powerful model that lacks it. CasaSol is the operational instantiation of that thesis — on hardware you own, in a building you control, with no data leaving the perimeter.
§ i — The Asymmetry
A frontier cloud model reasoning about a Marbella property has zero access to the agency's listing histories, viewer-aggregate patterns, comparable-sale deltas, and authored neighbourhood context. The local Reducer has all of it.
This is the version of the claim that survives sceptical engineering scrutiny. "A smaller model wins" is a weak claim. "A smaller model with full context beats a bigger model with no context" is the claim. The corollary: a Mac Mini with all of an agency's lawfully-held context will out-answer Claude Opus 5 on questions about that agency's market — because Claude Opus 5 cannot see the data.
General intelligence is commoditised at the API level. The portals own flat data — price, beds, baths, postcode. The only remaining moat is hyper-local context: which streets flood, which schools have waitlists, which sub-areas turned over in Q1 and at what discount to asking. Today that context is wasted.
§ ii — The Real Constraint
Most property data is the same property data. The villa on Idealista is the villa on the agency's own site is the villa in three aggregators' feeds — the same copy, re-scraped, often wrong, sometimes for a listing that sold months ago. Volume was never the problem. Trust is.
Each listing enters as a photograph, a GPS coordinate, and a timestamp — that triple is the provenance. The database does not hold "a listing found online." It holds "an offer observed to exist — here, then." The machine extracts the facts; the image stays as proof; the GPS and timestamp make the record auditable.
That combination cannot be reconstructed by a competitor with a scraper, because it was never on the wire. The portals see a listing when an agency uploads it. CasaSol sees it when the sign goes up on the wall — days or weeks earlier, and sometimes for offers that never reach a portal at all.
CAPTURE UNIT photo + GPS + timestamp [+ optional voice note] ↓ (Shortcuts / Tailscale / iCloud drop — device choice) INBOX seed/field/inbox/ (inside perimeter, never egress) ↓ vision pass — Gemma 4 via Ollama EXTRACTED sign_type: se_vende | se_alquila | obra_nueva | agency_board contact_raw: phone / agency name as printed building_state: free text (crane up, façade done, occupied) ↓ merge GPS → sub_area (offline reverse-geocode table, no API) OUTPUT enriched .md → load_db.py → SQLite + ChromaDB
§ iii — The Engine
CasaSol is the architect of the boundary between what the agency lawfully holds internally and what the cloud is allowed to see. The boundary is enforced by hardware and filesystem permissions — not by prompt instructions.
agent_intel.json (private) and public_listings.json (MCP-readable) are the two outputs. A misconfigured prompt cannot leak the private layer because the private layer is not in the MCP process's filesystem view.search_properties, get_property, market_summary to Claude Desktop. Reads only from the public output directory. The filesystem boundary is OS-enforced. Live and tested since 2026-03-29.§ iv — Hardware
All inference runs on-device. No cloud API calls. No data leaves the physical hardware.
Ollama — system daemongemma4:26bgemma4:e4b§ v — Open Stack
No proprietary inference. No vendor lock-in. Every layer is auditable and replaceable.
| Component | Role | License |
|---|---|---|
gemma4:26b | Reducer — enrichment + redaction | Apache 2.0 |
gemma4:e4b | Router — edge classifier | Apache 2.0 |
| Ollama | Inference runtime + model server | MIT |
| SQLite | Structured listing store | Public domain |
| ChromaDB | Vector store for semantic search | Apache 2.0 |
| mlx-whisper | Audio transcription (field capture) | MIT |
| MCP (Model Context Protocol) | Claude Desktop ↔ local server bridge | Open spec |
§ vi — Regulatory
The Cloud and AI Development Act (proposed June 2026) defines four assurance levels for sovereign cloud computing services. CasaSol delivers no cloud computing service. There is nothing to certify — because there is nothing to regulate.
CADA's highest tier (Level 4) requires zero third-country control — a standard AWS, Azure, and Google cannot meet while subject to US law. OVHcloud and Hetzner reach Level 2 at best. CasaSol is structurally outside the entire framework: on-premise inference, no remote access model, no network traversal to audit.
The answer for any agency asking about compliance: "CADA certifies cloud services. CasaSol has no cloud service. Your data never leaves your hardware."
§ vii — GDPR Pack
In Marbella luxury real estate, the lawyer is in the room before the IT director. CasaSol ships with a compliance binder the agency hands to its DPO on day one — written by an EU GDPR practitioner, bilingual EN/ES.
| Artifact | Purpose |
|---|---|
| Records of Processing Activities | Pre-filled RoPA template, Article 30 aligned |
| Data Processing Agreement | Vendor ↔ controller DPA, ready to sign |
| Legitimate Interests Assessment | Article 6(1)(f) basis for the Reducer layer |
| Privacy Notice Template | For agencies surfacing queries to public buyers |
| Data Subject Request Procedure | Access, erasure, portability — with CLI commands |
| Breach Notification Procedure | 72-hour template aligned with AEPD requirements |
| Retention Schedule | Documented schedule; raw CRM never imported |
| Audit Log Specification | What logs exist, where, for how long — bounded to device |
No personal data crosses any boundary. Article 22 (automated individual decision-making) is out of scope by construction — the output is a property report, not a decision about a natural person.