Lasse Hyldahl Jensen

I joined Avido as its Founding Engineer and third co-founder, after working with Avido’s CEO in Lunar’s AI Colony. Avido is a platform that lets banks and financial firms build, test, and monitor the AI they put in front of customers, and I’ve built most of the platform and the infrastructure it runs on.

The heart of it is a configurable conversational-AI engine that customers deploy and build their own LLM assistants on. It gives them self-service access to LLM capabilities through well-defined interfaces, coordinates a set of specialised agents, and hands them tools through Model Context Protocol (MCP) connectors. Moderation runs on the input and output as a guardrail, the whole thing is driven by per-customer config, and every request is traced back so it can be evaluated. RPM and TPM rate limiting in the inference layer keeps it within an LLM provider’s limits, which mattered when we ran inside a bank’s private cloud behind their AI gateway.

On top of that, the platform spins up test cases and simulated conversations to score the AI’s answers against evals like faithfulness and context recall, much of it driven by AI agents. Customers can stream their own production conversations in over OpenTelemetry and reuse them as test material, with Postgres and pgvector behind the semantic search.

I own the platform layer end to end, from the Next.js frontend and Node.js (Hono) backend down to managed Azure Kubernetes, with Pulumi for infrastructure as code, Flux for GitOps, GitHub Actions for CI, and the Grafana LGTM stack for observability. It deliberately mirrors the Talos Linux cluster I run at home.

Avido is now used by companies like Skatteguiden, Sydbank, Kamina, and ABN AMRO. To get one bank through procurement we ran the same container images inside their own private cloud, and as part of our SOC 2 work an external penetration test came back with zero findings.

In early 2024, two colleagues and I started Lunar’s AI Colony, a small team set up to find out how far generative AI could go across the bank’s products and internal work. The brief was simple: get hands-on and show value quickly.

We spent the first month on internal tooling, an assistant for staff and then a support chatbot wired into Lunar’s knowledge base. Those worked well enough to convince us, and the wider organisation, to put AI in front of real customers.

We launched the customer-facing assistant in April 2024 and tuned it on real usage. Once people trusted it, we built a full support system on top.

The support system connects to Intercom through its REST API and answers customers in seconds, where a reply used to take up to three days. It resolves 85% of Lunar’s support cases today; for the rest, it gathers what a human will need, screenshots of a bug and so on, and hands the case over.

Between them, the assistant and the support system handle over 40,000 customer interactions a month. It all ran on Lunar’s stack: Go microservices behind OpenAPI and GraphQL APIs, with retrieval over PostgreSQL and pgvector.

I also built Lunar’s internal GenAI platform, so other teams could reach LLMs through our APIs and build their own RAG pipelines on top, without standing up the plumbing themselves. On the data side, I built a pipeline that synced data from our warehouse back into production, so users could compare their own spending with others in their cohort.

I built backend microservices in Go, mostly services that exposed APIs to Lunar’s app and internal tools through OpenAPI and GraphQL.

As an intern I built an anti-corruption layer in front of one of Lunar’s partner integrations. API calls had been forwarded straight to the partner, which added latency and left little control over response times; the layer fixed that and let us move to event sourcing across the affected microservices. Those endpoints were hit every time one of Lunar’s million users opened the app, and we shipped changes to them continuously, sometimes several times a day.

Full-time, I took over Lunar’s card management system. It dated back to the 2019 banking licence and the rushed 2020 launch, so it carried real technical debt. I reworked the architecture that was holding back scalability and built an integration with Nets, Lunar’s card issuer, to keep the two systems in sync and reconcile any discrepancies automatically.

For my Bachelor’s project, I collaborated with IBM Denmark and Smukfest to develop the backend for Smukfest’s new mobile app. The backend was designed for scalability and maintainability, and it integrates various Content Management Systems (CMS) while enabling push notifications to all devices via Expo.

The app successfully launched for Smukfest 2023, supporting over 50,000 attendees, and was built to keep running even when parts of the backend failed.