Taking AI agents from visual design to production in one step
An agent framework and publishing service that turns a visually designed agent into a running, separately deployed service for each environment.
Read case studyOur work
Case studies and live products across platform engineering, AI, cloud, integration and security, described as they were built: the problem, the decisions and what was delivered.
Case studies
How we approached each engagement, the decisions we made and what was delivered.
One gateway to 45 models from six AI providers, with guardrails and tracing
A single model layer that lets teams choose and change models without rebuilding their workflows, with routing, policy and tracing handled in one place.
Read case study
Building a test suite that makes releases predictable for a growing AI and data platform
Unit, integration and end-to-end tests for a Python backend with no existing test suite, covering its databases, orchestration, storage and language model integrations.
Read case study
A booking and operations platform for sports facility owners in the UAE
Scheduling, staff roles, automated notifications and financial reporting in one platform, launched in four months ahead of peak season.
Read case study
Moving more than twelve applications from GCP to Azure with infrastructure as code
A two-month migration that introduced Pulumi, managed secrets with Doppler and Zero Trust access, and removed unused cloud resources along the way.
Read case study
One authorization service for many applications, built in Rust with Casbin
A central service that evaluates access rules for every application, chosen through framework benchmarks and integrated incrementally without disrupting operations.
Read case study
Applying LLMs row by row to business data, with structured and predictable output
A pipeline step that runs a chosen language model over every row of a table and returns typed fields that match a schema the user defines.
Read case study
Connecting AI workflows to Outlook and SharePoint through Microsoft Graph
Pipeline steps that read and write email, attachments and documents in Microsoft 365, acting with each user's own delegated access.
Read case study
A pipeline engine that runs, pauses and resumes data workflows
The orchestration core of a low-code platform, running visually connected steps in dependency order with breakpoints and resumable runs.
Read case study
Live run monitoring and cancellation across server instances
Step-by-step run logs streamed to the browser as they are written, and cancellation that reaches whichever server is running the pipeline.
Read case study
A controlled three-environment release pipeline on Azure
Branch-based releases to development, staging and production, with secrets applied at deploy time and security findings posted on every pull request.
Read case study
Workspace-level permissions that carry down to every project and asset
A hierarchical access model in which permissions granted on a workspace or project apply to everything inside it, checked on every request.
Read case study
Running user code and parsing documents in isolated services
Two separate services that let pipelines run user-written Python and turn documents into structured text, without putting the main platform at risk.
Read case studyLive projects
Products in production today that we helped build.
