Getting Started & Technical Docs
Everything your technical team needs to deploy, configure, and run Sidekick. Covers infrastructure requirements, Azure setup, LLM configuration, data source connections, and security architecture.
How Sidekick classifies sensitive data: the four-tier model for PII and PHI
Sidekick automatically detects and classifies sensitive fields across every connected source using a four-tier model — Restricted, Confidential, Internal, and Public. This article explains what falls into each tier, how masking and audit logging work, and why this matters for GDPR, HIPAA, and POPIA readiness.
Deploying Sidekick in Azure: a step-by-step setup guide
A practical reference for the technical team responsible for getting Sidekick live. Covers the two deployment options, VM sizing, networking requirements, LLM configuration in Microsoft AI Foundry, and the access provisioning your team will need to support a Sidekick engagement.
Inside the Sidekick architecture: "Our code, your cloud" explained
Sidekick runs entirely inside your environment, with no data ever leaving your boundary. A walkthrough of the core components — the Windows VM, the Linux containers, the LLMs in your AI Foundry — and how they fit together to deliver enterprise-grade discovery without enterprise-grade risk.
What is Sidekick? An introduction to AI-powered data discovery
Most enterprises have far more data than they realise — and far less understanding of it than they need. Sidekick changes that.