InTune Get in touch
Development

The engineering diary.

Implementation notes, architecture, technical decisions and problems solved — recorded as the project goes rather than reconstructed afterwards.

Technical workspace

Areas of the system.

Architecture

The current system diagram and how the parts fit together. See flow

Frontend

Structure, technologies, components and the Supporter-side experience.

Backend

APIs, services, data flow, authentication and infrastructure.

Real-time

LiveKit architecture and the communication flow between participants.

Transcription

Speech-to-text architecture and speaker identification.

AI

Claude integration, context construction, prompts, outputs and evaluation.

Data

Transcript structure, storage, retention and access.

Infrastructure

Hosting, deployment, environments, monitoring and operational requirements.

Technical notes

A chronological log.

Each entry: date · problem · investigation · solution · result · next step.

The log starts with the prototype

Entries are added as real problems are hit and solved — real-time audio quality, speaker separation, context window construction, latency between transcription and assistance.

Technical decisions

Choices made, and why.

Architecture

The AI is downstream of the conversation

Transcription produces context; the model reads that context. The AI is never in the path of the audio between the two people, so a model failure degrades assistance rather than the session.

Scope

Prototype before platform

Real-time communication, transcription, storage and Claude integration first. Marketplace, billing and analytics deliberately deferred.

Product-level decisions are recorded separately under Product.

Version history

How InTune has evolved.