Field guide / sub-domain
10
sources in this field
Updated September 4, 2026
Current thesis
The shortest path to orientation.
This synthesis records claims and practices from the cited sources; reported outcomes and product capabilities have not been independently verified.
Voice input preserves the texture of unpolished thinking—uncertainty, emphasis, half-formed ideas—making raw transcripts and dictation superior to polished summaries as Claude source material. The model's strength lies in reconstructing meaning from messy input rather than processing already-compressed text. Monologue or WhisperFlow pipes speech into focused apps; a gooseneck microphone is practical. Mac Mini with Telegram integration enables Claude Code access from anywhere via commands like /ce:plan fix the timeout issue, with tmux sessions persisting through connection drops. Voice modeling infers individual communication patterns from weeks of substantive, audience-separated Slack and email, identifying what a person challenges, notices, and ignores. Claude Sonnet 4.5 replicates writing voices with 94% accuracy in blind tests across literary, essay, and professional styles, enabling delegated communication that preserves authenticity. Reusable skills like $tibo-voice codify these patterns. Voice's advantage is fidelity over speed: unedited, messy thinking gives the model richer context than carefully engineered typed prompts. Ironically, high-value results often come from unstructured dictated rambles rather than polished prompts—suggesting context completeness matters more than prompt engineering when the model has full access to work history.
Evidence board
Claims worth carrying forward01Aggregating full business context (email, Slack, texts, Notion, meeting notes across 20+ projects/teams) into GPT-6 Astra produced the single most useful AI output the author has experienced—more valuable than the model's visual generation features.
02The high-value prompt was not carefully engineered—it was an unstructured, dictated (Wispr Flow) ramble. This suggests prompt polish matters less than context completeness when the model has full access to a person's work history.
03Effective prompt pattern for high-context analytical requests: explicitly instruct the model to avoid filler ('never fill space for the sake of it... every graphic and word should matter') and let it choose freely between text and charts/visuals based on need.
04Cross-tool context ingestion (previously siloed email, Slack, texts, Notion, meetings) is what surfaces cross-cutting business insights—wasted-time activities, team dependability gaps, skill priorities—that no single tool's data could reveal in isolation.
05Pinned megathreads (one per workstream: Chief of Staff, Agents SDK, Twitter monitor, etc.) accumulate history and preferences across months. Access via Command-1 through Command-9. Tradeoff: long threads likely fall out of cache, incurring higher cost than fresh short threads—continuity is worth it for important workstreams.
06Heartbeats are thread-local automations that schedule recurring checks without human presence. Example: Chief of Staff thread runs every 30 min to scan Slack and Gmail, drafts replies but never sends them. A single loop can cross tool boundaries—Slack feedback → Remotion render → @computer for file upload—without manual intervention between steps.
07Agent memory should live as files in an Obsidian vault (kept as a GitHub repo), not just as conversation history. AGENTS.md at vault root instructs agents to update people/, projects/, and notes/ pages as they learn. GitHub diffs become a review surface showing what the agent judged important enough to persist—preventing silent accumulation of 'vibes' in chat history.
08Voice input's value is not speed but fidelity: the agent receives the unedited, messy version of your thinking. Combining Wispr Flow (system-wide dictation) with Codex's built-in voice, and piping call transcripts via Granola, gives the model richer context than polished typed prompts ever would.
Adjacent fields
Latest evidence
Riley Brown
Riley Brown found that feeding GPT-6 Astra complete context across email, Slack, texts, Notion, and meeting notes for 20+ projects—then asking an unstructured, dictated prompt—produced the most useful AI output he's received, outperforming Astra's visual generation capabilities.
jason
Jason Liu's workflow guide for getting maximum leverage from OpenAI Codex by treating it as a persistent work OS rather than a one-shot chat tool. Key primitives: durable pinned threads (Command-1 through Command-9), voice input for unedited thinking, steering to queue intent mid-execution, an Obsidian vault as shared agent memory, Heartbeats for recurring loops, and the side panel for artifact inspection and annotation.
jason
Codex has matured from a coding assistant into a general work OS. Core patterns: durable pinned threads (Cmd+1–9 shortcuts), voice input for vague prompts, steering (mid-task interruption) vs. queuing (next-task scheduling), tool layers ($browser/$chrome/@computer), thread automations on a schedule, Goals with explicit verifiers (test suites, benchmarks), side panel for in-place artifact review, and shared memory via Obsidian vault with AGENTS.md routing rules.
Samantha Trimble
> another codex hack: for internal facing comms, make it read the last 3 weeks of slacks from someone at your company you trust and admire. ask it to understand what he/she pushes back on, what piques their interest, what they ignore, how they communicate with their team, etc. create a skill that yo
Nick Spisak
> https://t.co/ykuoaf5dhH - Use the [[claude/workflow]] capability of the Claude AI agent to streamline your coding processes and boost productivity — leverages [[claude]], [[vibe-coding]] - Integrate the [[claude/voice]] feature of Claude to narrate your coding steps, providing hands-free assistanc
rLLM
> https://t.co/Dl67Q7wMgx - The rLLM project has released a new version, which includes updates to the [[claude]] architecture, design, and ecosystem - The new release introduces support for [[voice-tools]] and [[physical-ai]] integrations, enabling new use cases for the [[claude]] language model
Nick Khami
> https://t.co/eSZGpkEGU4 - Use the [[claude]] plugin for Obsidian to seamlessly integrate with the Claude AI agent, enabling natural language interactions and advanced AI-powered capabilities within your Obsidian workflow - Configure the [[claude/settings]] to customize the Claude agent's behavior,
Griffin Hilly
> https://t.co/HWyMFZK7Ob - Leveraging [[claude/workflow]] to automate research, writing, and ideation within the [[.obsidian]] note-taking environment - Integrating [[claude/voice]] for hands-free note capture and command execution during the research process
Manthan Gupta
> https://t.co/em8mMn8bhj - The tweet provides a link to a detailed overview of Claude, an AI agent with a diverse set of capabilities including [[claude/architecture]], [[claude/design]], [[claude/ecosystem]], [[claude/settings]], [[claude/voice]], and [[claude/workflow]]. - The overview discusses
Shiv
> Lots of companies are now building primitives for an economy where AI agents are the primary users instead of humans. > > They're betting on an economy of AI coworkers.