optionOS optionOS

I produce everything by speaking — these pages included

How do I work?
Tags
  • WORKFLOWRepeatable working flow.
  • VOICEVoice-driven production.
  • ACTIVE-USECurrently in use.

I produce this site without typing a single line. I record my own voice conversations, tag the useful ones in the panel, then have agents produce from those conversations. The marketing copy, these guide pages, the what’s-new entries — all of it comes out of this loop.

The visual below is the very conversation that asked for this page: guide-tagged raw speeches sit in the panel with the production prompt placed on top as it is. The agent receives the speeches and the prompt as one packet.

Guide-tagged conversations in the Dictation panel with the production prompt placed on top Conversation rowGuide-tagged conversationsPanel view
·
Conversation row

The prompt goes on top of the conversations as it is; the agent receives speeches and prompt as one packet.

Even the conversation that asked for this page is a row here: raw speeches with the prompt placed on top.
The conversation that asked for this page at 1; guide-tagged raw speeches at 2; step 3 continues to the full panel view.

Two nested visuals: the final step takes you to the complete panel — list, detail, audio and search in one place.

The whole cost is the up-front speeches. The raw conversations behind this page took 3, 5, 2, 3 minutes and 18 seconds. The total cost is that speaking time spent up front; from there it proceeds by resolving on the agent side. The panel counter showed 49 hours 37 minutes of accumulated speech while these lines were written — the whole system was built with those conversations.

The task reaches the agent by speech too. Below is a Ghostty terminal: the entire input is a speech transcript, not a single hand-typed line inside. The transcript is pasted with its markup; the agent resolves rectangles, images and timing from that text.

A task handed to the agent in a Ghostty terminal as a speech transcript only; not a single typed line Agent tabSpeech transcript
·
Agent tab

Every production task goes to an agent running in a terminal tab.

One conversation, one agent tab: this is how a task reaches the agent inside Ghostty.
The task tab at 1; the pasted speech transcript at 2 — this is the entire input.

What if the transcript comes out wrong? That is the first question people get stuck on. The answer is simple: in a 20-minute conversation, even with typos — even if I say something wrong — it causes no problem, because I can recover it later. The rest of the speech corrects the mistake; the model separates the confusing part from the whole.

There is a small trick too. I add this sentence to the end of the speech: “I don’t know if I should do it this way — find whatever is right.” My thinking shifts mid-speech — first I say A, then B, then C. With this sentence I hand the decision to the model: I collect my feelings and the options, the model picks what is right.

The same speech packet can be given to more than one agent. This page was written in a Claude Fable 5 session; the same packet was handed, in the same form, to a Codex agent running GPT 5.6 Sol xhigh. The packet is agent-independent: intent, evidence and references travel inside the conversation, so which agent produced it stays an implementation detail.

The tool side of this loop is told on its own pages; the cards below are the interactive visuals of the same release.

Recording bar with the context list, waveform, background transcription and pending speech row marked Growing context listActive context trackingWaveformBackground transcriptionPending speech row
·
Context list

Every capture and note joins the conversation context; the list updates itself while you keep talking.

As you speak and capture, this list grows; the system actively tracks the context.
Growing context list and live tracking at 1–2; waveform at 3; background transcription at 4; pending speech row at 5.
Cockpit agent grid with terminal filters, the wide agent card and the change summary marked Terminal filtersWide agent cardAgent index numberAgent infoAgent goalTerminal it runs inChange trackingChange summaryYour messagesAgent messagesSub-agent conversationsEdited filesUncommitted changesCommitted changesConversation operationsOnly your messagesMessages plus file summariesLast run durationForkOur own compact mechanism
·
Terminal filters

Your terminals live on the same surface as your agents; this reads how many sessions each tool has open.

Terminals now show up inside Cockpit; Claude, Codex and terminal counts in one filter.
Terminal filters at 1; identity, goal, change and compact layers of the wide agent card across 2–9.