---
type: "post"
id: "a-new-feature-for-my-blog-built-using-95f6ec"
slug: "a-new-feature-for-my-blog-built-using-95f6ec"
title: "A new feature for my blog, built using my voice"
description: "The case shows voice as an additional interaction channel for coding work, not a replacement for the full development loop."
retrieval_nugget: "The case shows voice as an additional interaction channel for coding work, not a replacement for the full development loop."
published_at: "2026-10-09"
updated_at: "2026-10-09"
record_date: "2026-10-09"
date_kind: "published_at"
topics: []
source_urls: ["https://simonwillison.net/2026/Oct/9/built-using-my-voice"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:a-new-feature-for-my-blog-built-using-95f6ec"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:508f99131fedb50031f2b924bae11cda0e0e85c2cd79216821fef3ba0f572aa7","reviewed_at":"2026-10-09T21:00:46.624Z","source_evidence_count":1,"verified_claim_count":3,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":3,"implication_count":1,"watch_condition_count":1,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"voice input can widen when coding work fits into a user's day, while review and precise correction remain separate interaction tasks.","observed_facts":[{"text":"Willison says he built a newsletters feature using Codex voice mode in the ChatGPT desktop app against a local development environment.","source_urls":["https://simonwillison.net/2026/Oct/9/built-using-my-voice"]},{"text":"The work included a Django model and migration, import functions, archive pages, and search integration.","source_urls":["https://simonwillison.net/2026/Oct/9/built-using-my-voice"]},{"text":"He reviewed a GitHub pull request, changed one import to use an API rather than Git in a subprocess, and spent about another half-hour prompting by keyboard.","source_urls":["https://simonwillison.net/2026/Oct/9/built-using-my-voice"]}],"mechanism":"spoken direction, local visual feedback, and typed review formed a complementary loop rather than a voice-only workflow.","why_now":"the account demonstrates a shipped use of voice coding connected to a real local project, rather than a voice-only demo.","implications":["voice may make coding agent work compatible with multitasking, but it does not remove the need for review and precise edits."],"evidence_boundary":"this is one developer's account of one feature, not a controlled comparison of speed, quality, or general usability. It does not show that the agent independently deployed production-ready software.","watch_conditions":["look for additional documented projects that report both the voice-driven work and the subsequent review and correction effort."],"related_records":[],"new_branch_reason":"No prior New Runtime record is supplied for this specific voice-driven feature build; it begins a distinct case record."}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/a-new-feature-for-my-blog-built-using-95f6ec/","markdown":"https://newruntime.com/posts/a-new-feature-for-my-blog-built-using-95f6ec.md","json":"https://newruntime.com/posts/a-new-feature-for-my-blog-built-using-95f6ec.json"}
---

# A new feature for my blog, built using my voice

## Retrieval answer

The case shows voice as an additional interaction channel for coding work, not a replacement for the full development loop.

The case shows voice as an additional interaction channel for coding work, not a replacement for the full development loop. The thesis is: voice input can widen when coding work fits into a user's day, while review and precise correction remain separate interaction tasks. Willison says he built a newsletters feature for his blog using Codex voice mode in the ChatGPT desktop app against a local development environment. The work included a Django model and migration, import functions, archive pages, and search integration.

The mechanism was a loop across modalities: spoken requirements and clarifying questions drove implementation; a local browser preview made the changing result inspectable; then a GitHub pull request supported review and correction. The mechanism is: spoken direction, local visual feedback, and typed review formed a complementary loop rather than a voice-only workflow. He replaced a Git-subprocess import with an API-based approach and spent another half-hour prompting by keyboard. Why now: the account demonstrates a shipped use of voice coding connected to a real local project, rather than a voice-only demo. Its implication is: voice may make coding agent work compatible with multitasking, but it does not remove the need for review and precise edits.

The evidence boundary is: this is one developer's account of one feature, not a controlled comparison of speed, quality, or general usability. It does not show that the agent independently deployed production-ready software. Watch whether later examples document fewer modality handoffs, or instead continue to show human review and typed corrections as necessary stages. The first watch condition is: look for additional documented projects that report both the voice-driven work and the subsequent review and correction effort.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)