Cases

Proof: agents and systems we built

Systems we have built for clients.

In-house product

Call n Book

An AI voice receptionist and booking platform, built and run by our team.

Challenge: Small businesses miss calls while they work. Missed calls are lost bookings.
What we built: A voice agent that answers calls in natural Greek, checks live availability and books straight into the calendar. Every call gets a customer record and a transcript.
How it works: It checks calendar availability, follows the business’s booking rules and keeps a record of the call.

Enterprise software · Life sciences tendering

AI agents inside Tender Central, Cube RM's tender management platform for pharma and medtech companies.

Cube RM (Zurich), enterprise software for public tenders in life sciences.

Challenge: Public tenders mean long documents in many languages, strict rules and tight deadlines. Bid teams spend most of their time reading, checking and filling in forms.
What we built: A team of agents, each with one job across the tender lifecycle. Nova finds tenders. Valerio shapes value-based strategy. Redia checks readiness and maps products to lots. Clara drafts questionnaire answers from the company knowledge base. Victor runs pricing simulations. Tess reads every document and builds the bid dossier. Cuber coordinates the team. Clara, Valerio and Tess are live; the others roll out in stages.
How it works: LLM agents trained on real tender workflows, embedded in the software the team already uses. Every output cites its sources and shows a confidence level. People make the final decisions.

Manufacturing software · Print and packaging

AI agents on Overprint Cloud, BEL's cloud MIS and MRP for print and packaging manufacturers.

BEL (Greece), management software for label, carton, flexible packaging and commercial printers.

Challenge: In print, quotes take days, delays surface too late and answers sit in spreadsheets. Better dashboards alone do not reduce the workload.
What we built: Agents, one job each, from quote to delivery. Valdo drafts quotes and cost trees. Primo spots material shortages and drafts purchase orders. Fabrice re-plans the production schedule. Vera tracks machines and maintenance. Quinn raises nonconformities and corrective actions. Travis gets finished jobs out the door. Tracey keeps customers informed. Claire answers business questions in plain language.
How it works: Every agent runs the same loop: read the live MIS data, draft the action, wait for a person's approval, then act and inform the rest of the fleet. The agents run on top of a full Print MIS and MRP.

Enterprise AI · Governance and decisions

Specialised AI agents on Signal Prime, an enterprise reasoning platform that turns AI-era decisions into governed Decision Packs.

Signal Prime (Switzerland), enterprise software for large organisations and regulated industries.

Challenge: Large organisations struggle to answer the board's questions about their AI portfolio: what to scale, what to pause, what duplicates existing capabilities and what adds risk. Agents working in isolation drift and cannot be defended in a boardroom.
What we built: A team of specialised agents coordinated by Prime, the executive orchestrator. Atlas covers architecture, Helix M&A integration, Hermes data governance, Aegis risk and resiliency, Lex compliance, Flow process intelligence, Orion portfolio and finance, and Nova strategy and investment. Prime brings their work into one Decision Pack: options with evidence, cost and risk, and a named approver.
How it works: The agents reason across the Signal Twin, a governed, living model of the enterprise, connected read-only to existing systems of record. Every question opens a tracked Decision Case: sense, analyse, reason, decide, act, learn. Nothing acts on its own. A named person approves every step, with a tamper-evident record.

AI platform · Business discovery for SMEs

An AI operating system for small and mid-sized businesses. It maps how a company works, spots AI opportunities and turns them into a phased roadmap.

AIOS (aios.tech), a platform for founders and leadership teams of small and mid-sized businesses.

Challenge: Leaders know AI matters but not where to start. Mapping operations and finding the right opportunities usually takes long consulting work and technical know-how.
What we built: A guided AI interview, by voice or text, that asks the CEO about vision, challenges and goals and adapts its questions to the answers. An onboarding step reads the company website and documents, builds a business profile and detects departments. Optional role-specific interviews with finance, technology and operations leads add depth. The output is a report with prioritised opportunities, an impact-versus-effort view, matched AI tools and a phased roadmap.
How it works: Interview transcripts are analysed to extract tasks and patterns. A confidence check decides whether there is enough information for the report, or whether to ask follow-up questions or bring in more executives. Each recommendation comes with suggested timelines and resources.

Tell us the work you want them to take on. Together, we find the first agents worth building.

[Add Calendly link]

A 30-minute call with us.