Applied AI · UX · systems integration
Voice-to-knowledge pipeline
Speak a thought on a phone and have it arrive as a structured, linked note. The interesting part is not the pipeline that works — it is the one before it, which could never have worked, and took a read of the platform's own rules to diagnose.
The first design was broken by architecture, not code. Finding that out was worth more than patching it would have been.
The problem
Capture is where most note systems die. Not retrieval, not organisation — capture. If recording a thought takes more than a few seconds, the thought does not get recorded, and the system quietly stops existing.
So the constraint was absolute: the act of recording had to be the same act as having it filed. Say it, and it is organised. No inbox to clear, no triage pass, no discipline required later — because discipline required later is a system with a failure date on it.
The one that works
Dictation on the phone, a local service on the tailnet, an agent turn in the middle, and a structured note out the other end.
The one that could never work — and why that was the useful part
The first version of this routed the whole thing through a chat bot. The phone would send the question as a message, the agent would answer into the chat, and the phone would read the reply back. It looked reasonable. It was impossible, and no amount of debugging would have fixed it, because it was wrong about how the platform works.
The lesson generalises: when a design is impossible, the impossibility is usually about ownership — who authors a thing, who consumes it, who is allowed to see it. Reading the platform's own rules and finding the two places where the plan contradicted them took less time than another round of debugging would have, and it produced a design that is simpler than the one it replaced.
Two pipelines, two jobs
The system deliberately keeps recording and answering apart, because they are different promises. One is a note filed for later; the other is an answer you hear out loud.
Facts, in a form you can check
| Capture | A phone dictation shortcut — nine actions, no app to open |
|---|---|
| Transport | HTTP over a private tailnet; the service is not exposed publicly |
| Output shape | Frontmatter plus four enforced sections: summary, key points, action items, links |
| Typical latency | Around 6 seconds for a direct answer, around 13 when the agent needs a tool call |
| Ceiling | 180 seconds, after which the request is abandoned rather than left hanging |
| Failure handling | A failed agent run returns an error rather than an empty answer |
| Scheduling | Note processing runs on a timer, so a backlog drains without being watched |
Outcome.
What I would change next
Three things, and none of them are cosmetic. The service currently listens on every interface rather than the private one, which is fine on this machine and wrong the moment it joins a network I do not trust. There is no shared secret on the answering endpoint, so any device on the network can spend model credits. And each question is a fresh turn with no memory of the last one — a session handle would fix that, and is the first thing I would add if the thing turns conversational.