One flagship project: Lucid. Nine months of building, breaking and rebuilding a production AI system under daily live load. Every pattern in our voice agent builds was pressure-tested here first.
Start: September 2025. One developer. No co-founder, no team, no external funding. A full-stack AI productivity companion built to the same standard we apply to every client build, because it was the testing ground for that standard.
A full conversational agent in daily production. Not a prototype, scheduled tasks, habit tracking and neural memory, all integrated into one productive AI model with real users.
A pgvector-backed neural memory that retrieves relevant context across sessions. We use the same retrieval architecture for clinic knowledge bases in every voice agent build.
Not just answers, Lucid executes: creates tasks, updates calendars, fires notifications, manages state across sessions. The same tool-use pattern underpins voice agent booking flows.
Every Lina deployment ships with four safeguards baked into the request pipeline. Not as a configuration option, not as a premium tier. Architectural defaults that pass every call through identity disclosure, a confidence gate, scope enforcement and full transparency logging, in that exact order.
The bot announces itself in the first sentence of every conversation. "Hi, you are speaking with Lina, the digital assistant from [Practice]." Not in the small print, not buried, not optional. The pattern is architectural, not policy.
Every model response is scored against a calibrated confidence threshold. Below 0.75: clean decline + handoff path, not hedged speculation. The bot never guesses on medical-adjacent questions because the model cannot bypass the gate.
Scope is defined explicitly at build time per practice. Out-of-scope requests trigger a clear decline ("That is outside what I can help with, let me transfer you") rather than confidently-wrong hedging. Endless hold-loop patterns are architecturally ruled out.
Every conversation turn writes to the admin dashboard with timestamps, confidence scores, and handoff reasons. You and the caller can request the log at any time. No black-box decisions, no plausible deniability either way.
The safeguards are non-toggleable. A clinic owner cannot accidentally disable them in setup. A junior operator cannot turn them off to "make something work." Architectural enforcement is the only kind that survives operational reality on day 90.
The confidence gating and handoff logic were tested under daily production load in Lucid (case study 01) before they shipped to any client build. The numbers (0.75 threshold, <2s transfer ceiling) are calibrated against real failure modes, not invented.
Bot identity disclosure satisfies the German transparency requirement on automated decision making. Full transcript logging satisfies the data-portability obligation under Art. 20 DSGVO. Both are infrastructural, not policy-document promises.
Case studies are not written first and built after. They are the output of a process that runs before a single line of production code ships. The gates below are non-negotiable for every Lina deployment, in this exact order.
One structured intake brief, by email, before any contract. We audit your current phone setup, call volume and booking system in writing. If the fit is wrong, we say so here, not after the build starts. No scheduled phone calls in this process.
A written scope document covering voice persona, escalation rules, booking integrations and explicit out-of-scope topics. You review and sign before build begins. No ambiguity enters the codebase.
RAG knowledge base ingestion, safeguard layer wiring, booking-system integration and voice persona configuration. Each is tested in isolation before the pipeline is assembled. Average build window: 10 to 14 days.
A structured adversarial call session: off-topic probes, confidence-floor triggers, handoff edge cases. We run these before you hear the voice. Failure here delays launch; failure at a live caller does not happen.
Two weeks of parallel routing: a portion of real calls go to Lina while your existing line stays active. Transcript review with you every 48 hours. Full cutover only after both sides are satisfied with the numbers.
Monthly knowledge-base updates, confidence-threshold tuning as call patterns shift and admin-dashboard access so you see every conversation without needing to ask. The case study gets written here, once the numbers are real.
The voice-agent product is new. The architecture isn't, Lucid above is the proof. As each founding clinic goes live, they appear here with deployment details and outcomes. No padded logo grid, no faked quotes. This is the current state, in writing.
If Lina doesn't meet the agreed call-handling and booking targets in the first 60 days, you cancel and get the founding fee back. Terms in the contract.
No minimum term, no annual lock-in. The €449/month founding price is locked for 12 months once you sign.
No ticket system, no SDR funnel, no offshore support. Direct email and phone to Fabi with a 4h SLA. You talk to the person who built it.
The retrieval, agent-action and safeguard layers in your voice agent ran first under daily load in Lucid. Case study 01 above is the receipt.
€449/month in year 1, €0 setup. Case study posts here when this clinic is live.
Same terms. Reserved as soon as the first slot signs.
Last seat at founding pricing. After this, Professional pricing applies to new sign-ups.
Demo projects prove you can follow a tutorial. Production projects prove you can ship, maintain and debug at 2am, and build systems that hold up under real users. Lucid is the latter.
Every RAG pattern, every safeguard, every escalation trigger in our voice agent builds ran first under real load in Lucid. Failure scenarios get found before they reach your callers.
No framework generated Lucid's architecture. No team made decisions on a developer's behalf. Every design decision has a name and a reason behind it, we bring the same accountability to client builds.
Hetzner Falkenstein, Supabase pgvector, n8n orchestration, Lucid runs on the same stack we deploy for clients. We do not show demo infrastructure in the portfolio and hand you something different.
Tell me your current phone setup and call volume. I come back with a scope document, a timeline and an honest assessment of what is feasible for your configuration in 7 days.