NavoX logoFounder & Product Lead

NavoX.

Plan the week. Talk it through. Keep control of every action.

A voice-first assistant for student planning, coursework, and interactive whiteboard lessons, with source-linked memory and reviewable calendar actions.

NAVOX / CURRENT DEVELOPMENT BUILD
5,985 API/web testsRECORDED CHECKPOINT
THE IDEA

What NavoX does.

As Founder & Product Lead, I am building NavoX, a voice-first AI assistant for college students. It connects weekly planning, calendar scheduling, coursework, and interactive whiteboard lessons through a persistent conversation, with encrypted source-linked memory and explicit approval before consequential actions.

Real-time voice and whiteboard lessons

LiveKit and OpenAI support streaming speech-to-text and text-to-speech, barge-in, and reconnect recovery. Interactive whiteboard lessons connect spoken tutoring with visual explanations.

Memory with controls

Encrypted, source-linked memory preserves useful context while giving students retention, off-record, and deletion controls.

Calendars across providers

Google Calendar, Microsoft Graph through OAuth 2.0, and iCloud CalDAV adapters feed constraint-aware planning and scheduling.

Exact approval and supported Undo

Students review the exact proposed action before a calendar write. Supported Undo checks the resource version so a later edit cannot be silently overwritten.

Durable background work

An async FastAPI and PostgreSQL backend uses Temporal workflows for syncs, reminders, and briefings.

BUILT WITH

The technology.

FROM INPUT TO OUTCOME

How it works.

Student commitments are scattered across calendars, classes, and conversations. An assistant needs to recover from interrupted voice sessions, retain only the context a student chooses to keep, and distinguish a suggested schedule from an approved calendar write.

Connect and remember

Authorize calendar providers and retain source-linked context under the student’s memory and privacy controls.

ENGINEERING DECISIONS

Why it’s built this way.

A streaming voice runtime

LiveKit manages real-time sessions while OpenAI powers speech and model interactions. Barge-in and reconnect handling make interruptions part of the interaction design.

Durable work with bounded authority

Temporal coordinates syncs, reminders, and briefings. Approval state remains separate from background execution, and a materially changed action requires fresh approval.

Owned, source-linked state

PostgreSQL stores application state and source references with ownership boundaries. Encrypted memory has explicit retention, off-record, and deletion controls.

RECORDED CHECKPOINTS

What the evidence shows.

The recorded API/web regression checkpoint contains 5,985 tests, alongside strict mypy and Ruff checks. LLM evaluations cover schema validity and prompt-injection rejection. These validate the recorded source checkpoint rather than establish production accuracy or availability.

5,985API & web tests
LiveKitStreaming, interruptible voice
TemporalDurable background workflows

Watch the spoken product demo for a scripted student–Vox conversation and reviewed task/planning flow.

SCOPE & LIMITS

The workspace screenshot shows the development build with sample data. The spoken product demo is a scripted illustration with generated student and Vox voices and illustrated task/planning actions. Live account connections and voice behavior depend on configured providers. Undo is supported for specified calendar writes and checks the resource version before applying a change.

Read the earlier architecture brief (October 4)
OPEN THE WORK

Code, documents & proof.

Current source code and supporting design records, alongside an earlier architecture snapshot.

ENGINEERING BRIEFNavoXMichael Baffour Awuah · 2026

Earlier architecture brief · October 4

An October 4 architecture snapshot. It predates the current LiveKit voice runtime and 5,985-test checkpoint described above.