Add "Never Touch the Laptop" phone-first cloud agents field survey#10
Draft
wschenk wants to merge 6 commits into
Draft
Add "Never Touch the Laptop" phone-first cloud agents field survey#10wschenk wants to merge 6 commits into
wschenk wants to merge 6 commits into
Conversation
Never Touch the Laptop: Codex Cloud, Cursor Cloud Agents, and Claude Code on the web mapped across 13 axes against the idealized phone-only, voice-driven project loop. Includes tool screenshots captured Jul 20, the supporting stack (Vercel MCP/previews, Neon, Cloudflare, Poke, GitHub Mobile), a phone-only project walkthrough, and gaps. Filed into Drive for 2026-Q3 with a new quarter discovery. Co-authored-by: Will Schenk <wschenk@gmail.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_018vDxfPeuHcGE89J6pDf25R
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
…urvey Amp shipped orbs (Jun 30), remote thread creation, OIDC-based orb identity, agent-to-agent spawning, Slack integration, and self-scheduling agents between Jun 30 and Jul 22, so the survey now compares four platforms: - Fourth scoreboard column covering all 13 axes - New Part III section on orbs: pricing/sizes, .agents/setup + resume, orb portal, OIDC secrets model, agents spawning agents, mobile-web-only phone surface - Two ampcode.com screenshots to match the other tool sections - Updated verdict, secrets and looping sections (three -> four philosophies), walkthrough chaining note, method note, cover stats, and Drive catalog summary Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01ENwqmTAxTmRhtj1116fqU2
The five-column markdown table was unreadable — narrow cells behind a horizontal scrollbar, hiding the densest information in the report. Each of the 13 axes is now a full-width block with four vendor cells, graded green/amber/red (strong / workable / missing) with a legend, four-across on desktop, stacking to two then one column on phones. Screenshots now break out wider than the text column. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01ENwqmTAxTmRhtj1116fqU2
…ng callout The setup agent discovers which secrets the environment needs and prompts with the Add Secrets dialog (runtime-redacted default, paste-your-.env, per-repo scoping) — the best secrets onboarding flow of the four vendors, now shown and called out in the Cursor section. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01ENwqmTAxTmRhtj1116fqU2
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Adds field survey FR-2026-07-PHONE — Never Touch the Laptop: Running a Whole Project from Your Phone at
/reports/phone-first-cloud-agents/, filed into Drive for 2026-Q3.The report answers: can you spec, build, preview, deploy, and iterate on a real project entirely from a phone, by voice — never touching a laptop?
Changes
src/content/reports/phone-first-cloud-agents.md— the report memosrc/pages/reports/phone-first-cloud-agents.astro+src/styles/reports/phone-first-cloud-agents.css— paper-theme report page rendering the memosrc/lib/reports.ts— Drive catalog entry (FR-2026-07-PHONE, 2026-07-20)src/content/quarters/2026-q3.json— new quarter discovery ("three seams")public/images/reports/phone-first/*.png— 10 tool screenshots (8 captured Jul 20, 2 Amp screenshots Jul 23)Verification
pnpm run buildpasses (221 pages). Manually verified via browser onastro preview: cover, scoreboard table (horizontally scrollable, no overflow), all 8 screenshots load, Drive listing shows the entry, homepage shows discovery note 05. After the Amp revision:pnpm run buildre-run and passing (221 pages).<img src="https://cursor.com/artifacts/c/art-9c00b4a1-c342-42d9-bed2-7980e214f5f5" alt="phone_first_report_walkthrough.mp4"/><img src="https://cursor.com/artifacts/c/art-a670d5c6-1e1c-4ce6-b3ea-909af33cebc4" alt="homepage_discovery_note_phone_first.mp4"/><img alt="Open in Web" width="114" height="28" src="https://cursor.com/assets/images/open-in-web-dark.png"><img alt="Open in Cursor" width="131" height="28" src="https://cursor.com/assets/images/open-in-cursor-dark.png">