A Production Platform for a Self-Hosted AI Product — at Startup Speed (Mimrr)
Austin, TX · remote
Executive Summary
The Client
Mimrr is an AI code-intelligence startup: their self-hosted AI, Rune, helps engineering teams understand, document, and maintain their codebases. THNKBIG met the team at SXSW in Austin.
The Engagement
A seed-stage startup needs the same platform discipline as an enterprise — without the enterprise timeline or bill. THNKBIG designed and built Mimrr's production Kubernetes platform on Azure AKS: the cluster, the ingress and TLS automation, the data layer, the observability stack, and the deployment of six production services — including the self-hosted AI at the heart of their product.
Key Scope Items
Solution Implemented
✔ AKS cluster with real access control — Azure AD integration and Kubernetes RBAC from day one, not bolted on later.
✔ Ingress + TLS, fully automated — ingress-nginx behind Azure Application Gateway with Key Vault-managed certificates via managed identity, and cert-manager doing DNS-01 issuance with automated rotation. Nobody at Mimrr renews a certificate by hand.
✔ A three-store data layer — Neo4j for the code knowledge graph, Elasticsearch (ECK operator, with Kibana and APM) for search, RabbitMQ for messaging — all operated in-cluster.
✔ Observability from day one — OpenTelemetry collectors at app and cluster level feeding Grafana dashboards and Elastic APM.
✔ Six production services shipped — API, web app, identity, the Rune AI service, and supporting services — deployed via Kustomize with images in Azure ACR and AWS ECR for multi-cloud portability.
✔ Self-hosted AI, sovereign by design — Mimrr's product promise is that customer code never leaves the deployment; the platform THNKBIG built is what makes that promise operational.
Outcomes Expected
▸ Six production services live on a hardened AKS platform — including the self-hosted Rune AI
▸ Zero manual TLS — certificates issued, stored, and rotated automatically end to end
▸ Enterprise platform patterns at seed-stage cost — AAD/RBAC, GitOps-ready manifests, multi-cloud registries
▸ Owned by Mimrr's team — runbook-style docs for every component, in their own repo
The Customer's Situation
Mimrr's product is a self-hosted AI — Rune — that helps engineering teams understand and document their codebases. A product whose pitch is 'your code never leaves your environment' needs production infrastructure that lives up to it, and a seed-stage team can't spend two quarters building a platform before shipping. THNKBIG met the founders at SXSW in Austin and took on the build.
The Platform
THNKBIG stood up an Azure AKS cluster with Azure AD integration and Kubernetes RBAC, put ingress-nginx behind an Azure Application Gateway with Key Vault-managed certificates, and wired cert-manager for DNS-01 issuance with automated rotation. The data layer runs in-cluster: Neo4j for the code knowledge graph, Elasticsearch via the ECK operator with Kibana and APM, and RabbitMQ for messaging. OpenTelemetry collectors at both application and cluster level feed Grafana.
Six Services to Production
On that foundation THNKBIG deployed Mimrr's six production services — API, web app, identity, the Rune AI service, and supporting applications — with Kustomize-managed manifests and container images in both Azure ACR and AWS ECR, keeping the platform portable rather than welded to one cloud. Every component shipped with runbook-style documentation in Mimrr's own repository.
Why It Matters
This is the same platform discipline THNKBIG delivers to mid-market and enterprise clients — access control, automated TLS, observability, documented handover — scaled to startup speed and budget. And it's the sovereignty story in miniature: a self-hosted AI product, running on infrastructure built so that customer data never has to leave.
About THNKBIG
THNKBIG is an Austin, TX-based Platform Engineering consultancy specializing in Kubernetes, cloud-native, and production AI infrastructure — on-prem and cloud, vendor-neutral, with ownership transferred to your team. Specialties: platform builds and assessments, GPU/on-prem AI, sovereign AI infrastructure, software supply-chain security, and compliance readiness (FedRAMP, HIPAA, SOC 2, PCI, ATO).
Frequently Asked Questions
How do you approach client engagements?
Every engagement begins with a thorough discovery phase to understand your current state, business objectives, and constraints. We develop tailored recommendations rather than applying one-size-fits-all solutions. Our consultants work alongside your team to transfer knowledge and build sustainable capabilities. We measure success by business outcomes, not just technical deliverables.
What ROI can we expect from this type of engagement?
Organizations typically see significant improvements across multiple dimensions. Common outcomes include 50-80% reduction in deployment time, 30-50% decrease in infrastructure costs, 60-90% reduction in incident resolution time, and substantial improvements in developer productivity. The specific ROI depends on your starting point and investment level, which we help quantify during the assessment phase.
Related Solutions
This case study demonstrates our expertise in the following service areas. Learn more about how we can help your organization achieve similar results.
Cloud Complexity is a Problem —
Until You Have the Right Team
From compliance automation to Kubernetes optimization, we help enterprises transform infrastructure into a competitive advantage.
Talk to a Cloud Expert
