AI productivity platform
Montlify
One workspace holding 33+ AI tools for writing, research and chat, with the accounts, subscriptions and infrastructure needed to keep them all running.
- React
- LLM APIs
- Streaming
- Authentication
A voice agent built for three people in the room rather than two on a call. It tracks who is speaking, warns the professional privately in their earpiece when a rule is crossed, and stays silent the rest of the time.
Product design, real-time audio pipeline and full-stack build
Built for a room, not a two-person call
Private warning in the earpiece, public answer in the room
Every warning names the rule that triggered it
Every voice agent on the market assumes two participants: a user and an assistant. A compliance conversation has three — the professional, the client, and whoever came with them. That breaks the usual design in three places at once: the agent has to know who is speaking, it has to warn one person without the other hearing, and it has to stay quiet through a conversation it is not part of.
Speaker diarization in real time, because a compliance rule applies to the professional and not to the client. Attributing a sentence to the wrong person turns a useful warning into noise, and noise is what gets an assistant switched off.
Guidance is whispered to the professional on a separate audio path while answers to the room go out loud. The dual-channel design is the product: a warning the client can hear is worse than no warning at all.
The rules that must fire immediately are evaluated deterministically rather than waiting on a language model. Model-based evaluation handles the judgement calls; anything that has to be instant never queues behind a token stream.
It answers when addressed by name and otherwise says nothing. Most of the engineering in a live-listening agent goes into deciding when not to speak, which is the opposite of how these systems are usually demoed.
Account numbers and identifying details are stripped before a transcript is written. The audit record has to survive a compliance review of its own, so the safest transcript is the one that never held the number.
AI productivity platform
One workspace holding 33+ AI tools for writing, research and chat, with the accounts, subscriptions and infrastructure needed to keep them all running.
E-commerce platform
A production storefront built from nothing: catalogue, guest checkout, payments, order processing, automated email and an admin dashboard the owner runs without an engineer on call.
A short call, then a written scope with a fixed price and a date. Scoping costs nothing and the document is yours either way.