src/data/facts.json · 51 entries
Fact file
Every claim on this site, in one place. Site copy is written from this file, and therole-match agent may only state things that trace back to an entry here. That includes the gaps.
Person
on the home page →| p1 | Andrew Deighan. Based in Dubai. British and Irish citizen with full EU right to work. Available from mid-October 2026. |
| p2 | Co-founder and Product Lead (CEO) of AtlasOra, June 2024 to October 2026. Two-sided vacation rental marketplace. Team of thirteen. |
| p3 | Founder and builder of DUDsJobs, an AI job-hunting service, launched September 2026. |
| p4 | Head of Marketing at Qubic, an AI-focused layer-1 network, August 2024 to May 2025. |
| p5 | Nine years in secondary education across the UK, Thailand, New Zealand and Jordan, finishing as Assistant Headteacher and Head of Year on a school senior leadership team. |
| p6 | MSc Fintech and Digital Banking (taught modules complete, 84% average, dissertation pending). PGCE. BSc Pharmaceutical Science. |
| p7 | Builds hands-on with AI coding tools, including Claude Code. Not a trained software engineer. |
Host acquisition agent pipeline
project page →| h1 | An orchestrated pipeline of 11 working agents and rule-based gates. Two further agents are registered but not yet built out, and are not counted. |
| h2 | It worked through all 117 property managers on the Costa del Sol: finding decision-makers, researching each company and drafting personalised outreach. |
| h3 | Around 20 managers agreed to list about 1,000 properties in under three weeks. These are agreements to list, not live listings. |
| h4 | Email outreach measured a 1% reply rate. Andrew moved the channel to WhatsApp and replies rose to 25%. |
| h5 | Models are tiered by task: Claude Haiku to sort, Sonnet to research, Opus to write. |
| h6 | Every draft passes an automated tone check (rules, then a model judgement). Failed drafts are rewritten up to three times. |
| h7 | A rule-based compliance gate checks throttling, GDPR lawful basis and consent before every send, and writes an audit record. |
| h8 | Nothing is sent without a person approving it. The agent that handles replies never replies by itself. |
| h9 | Failure handling: automatic fallback to a smaller model, an alert when fallback passes 10% in an hour, retries with backoff, a daily spend cap and kill switches by agent, channel and region. |
| h10 | Several agents use no model at all (prospect finding, sending, compliance, follow-up templates). That is deliberate. |
AI job matching engine
project page →| j1 | A five-model pipeline that routes each task to the cheapest model able to do it well: a low-cost gate model (Jev), Claude Haiku for extraction, Sonnet for matching, Opus for CV parsing and writing, with DeepSeek as a second provider. |
| j2 | Rules and the gate settle 82% of job assessments. The mid-tier model reads 18%. |
| j3 | The gate rejects 47% of candidates in under half a second. |
| j4 | Median AI cost is $0.09 per search run. |
| j5 | Failover to DeepSeek is automatic when the primary provider errors, times out or rate-limits, after three retries. It never triggers on a bad request or a refusal. Anything DeepSeek scores is re-scored by the primary model on the next run. |
| j6 | Each user has a hard monthly AI budget. When it is reached, matching continues on rule scores alone. |
| j7 | Live with paying users since September 2026. 74 of 78 production runs succeeded; all four failures were in the launch cut-over. |
| j8 | The job data feed costs more than the AI. |
Decision Intelligence
project page →| d1 | A guest-facing feature that weighs homes against a guest's priorities using measured map and listing data. |
| d2 | It runs only when the guest asks. It never books and never reorders results. |
| d3 | AI output is labelled as judgement, separately from measured fact. |
| d4 | If the model fails, it falls back to measured facts alone. This kept the feature working through a model outage in September 2026. |
| d5 | No measured results on guest behaviour are available yet. |
AI Help and host assistant
project page →| a1 | A guest help assistant grounded in a 497-entry knowledge base. For each question it retrieves the closest entries and answers from them. |
| a2 | It is barred from stating numbers, policies, dates or features that are not in its sources, and points unresolved issues to support. |
| a3 | This was built after the assistant was found inventing facts such as dates. |
| a4 | A separate host assistant drafts profile and listing text and can change only a fixed set of fields. |
| a5 | The safeguards on AI Help are instructions and grounding. There is no automated checker on its answers. |
Wider product and payments work
on the home page →| w1 | Took AtlasOra from zero to public launch in September 2026: a 198-feature requirements document and 98 features shipped with a CTO and four engineers. |
| w2 | In-person discovery with property managers across Malaga and Marbella. |
| w3 | Designed and specified trigger-released escrow contracts on Base. Guest funds were held in EURC and released at check-in, or automatically 24 hours later, with dispute freeze and admin settlement. It ran in production and is currently switched off for cost reasons. |
| w4 | Automatic cross-border host payouts by Revolut bank transfer once the on-chain release was recorded, so hosts never touched crypto. |
| w5 | Eleven live integrations, including a payment provider, KYC and seven property management systems. |
| w6 | Led a 13-person team and hired and developed three product designers. |
| w7 | Shipped on four model providers: Anthropic, OpenAI, DeepSeek and Jev. |
Qubic
on the home page →| q1 | Worked directly with the project's AI scientists, David Vivancos and Dr Jose Sanchez. |
| q2 | Hosted their public technical interviews and supported the launch of their research paper on Aigarth. |
Known gaps
7 entries| g1 | About two and a half years in product roles. |
| g2 | Has not fine-tuned or trained models. |
| g3 | Products have been early-stage, not high-volume consumer scale or enterprise software. |
| g4 | Has not managed a dedicated research team or a large engineering team. |
| g5 | Not a trained software engineer; builds with AI coding tools. |
| g6 | Works in English. Does not speak Spanish, German, Arabic, Russian or Mandarin. |
| g7 | No professional background in healthcare, life sciences or contact-centre operations. |