🔥 TOP SIGNAL

Cursor’s big unlock this week is “demos, not diffs”: cloud agents can run the software they just built, test it end-to-end, and send you a video artifact as proof @cursor_ai +1. Practitioners are saying this flips async agents from “fun but hard to trust” to “mergeable”—Jediah Katz reports that in the last two months >50% of his PRs were written by cloud agents once they could self-test and send videos @jediahkatz.

🛠️ TOOLS & MODELS

• Cursor Cloud Agents — “computer use” + video demo artifacts (shipping)

  • Agents can onboard to your repo, use a cloud computer/remote desktop, and return video demos of the finished change @leerob +1.
  • Cursor: “A third of the PRs we merge now come from agents running in cloud sandboxes.” @cursor_ai
  • Cursor CEO Michael Truell: “Over a third of our PRs are now created autonomously with this feature.”@mntruell
  • Internal example: Cursor agents modifying Cursor (e.g., adding secret redaction to model tool calls) and returning a multi-chapter demo video after E2E verification @cursor_ai.
  • Try/read: http://cursor.com/onboard@cursor_ai · http://cursor.com/blog/agent-computer-use@cursor_ai

• Claude Code — Remote Control (rolled out to all Max users)

  • /remote-control lets you start a local terminal session, then continue it from your phone@_catwu +1.
  • Boris Cherny says he’s been using it daily @bcherny.

• Claude Code — Slack plugin (context + updates)

  • Install with /plugin install slack to connect Slack for search, messaging, doc creation, and pulling work context into Claude Code @_catwu +1.

• Claude Code — built-in git worktrees + tmux flags

  • New flags: -w, --worktree [name] and --tmux; each session runs in its own worktree to avoid branch-switching chaos @hqmank.

• Claude Code — notable performance datapoint

  • Reported: p99 memory usage dropped 40× in the last two weeks, and 6× since January, while shipping new features @jarredsumner.

• Devin (Cognition) — enterprise-first PMF story + self-serve UX catch-up

  • Scott (via @swyx): Devin didn’t have internal PMF at launch; first enterprise adoption took ~6 months; “async agents are the final boss of agent UX” @swyx.
  • Claimed growth: usage doubled every 2 months in 2025 per enterprise after landing; accelerated to every 6 weeks so far this year; internal usage now 4× 2025 peak@swyx.
  • Devin 2.2: sprint to pay down self-serve UX debt; omnibox; tighter “close the loop” integration with Devin Review @swyx.

💡 WORKFLOWS & TRICKS

• Close the agent loop with “proof artifacts,” not trust

  • Jediah Katz’s bottleneck framing: review/testing was the limiter (“you’re responsible… to deliver code you have proven to work”); video demos from agents shift what he can confidently merge without local checkout @jediahkatz.
  • Kent C. Dodds calls this “closing the agent loop” and credits Cursor’s computer-equipped cloud agents as a major step change for shipping from his phone @kentcdodds +1.

• “First run the tests” as your session opener (Simon Willison)

  • Prompt: “First run the tests” to force test-suite discovery and put the agent into a testing mindset simonwillison.
  • Willison’s claim: automated tests are no longer optional when working with coding agents; if code hasn’t been executed, it’s luck if it works in production simonwillison.
  • If you use uv in Python, he prompts: Run "uv run pytest"simonwillison.

• Generate a “linear walkthrough” doc for any repo (also Simon Willison)

  • Use an agent to read the source and produce a structured walkthrough—especially helpful if you “prompted the whole thing into existence” and now need to understand it simonwillison.
  • Willison’s implementation detail: use Showboat so the agent includes code snippets by running commands (showboat exec + sed|grep|cat) instead of manual copy/paste (reduces hallucination risk) simonwillison.
  • Example prompt (verbatim):

• Peter Steinberger’s “conversational agent” habit: always ask for questions

  • He treats coding with agents as a conversation and repeatedly asks: “Do you have any questions?” to surface hidden assumptions (models otherwise default to assumptions) OpenAI.

• PR review as intent review (not code review)

  • Steinberger’s PR loop: first ask the model if it understands the intent of the PR and whether it’s the optimal solution; often the right fix is architectural/systemic OpenAI.

• Rubric separation to reduce “context rot” and bias (Doug O’Laughlin)

  • He keeps task and rubric prompts separate because combining them can commingle information and increase bias/susceptibility; he also calls out sycophancy as a practical failure mode Latent Space.

👤 PEOPLE TO WATCH

• Jediah Katz (Cursor) — concrete practitioner stat: >50% of PRs written by cloud agents once agents could self-test and send video proof @jediahkatz.
• Michael Truell (Cursor CEO) — production signal: >⅓ of Cursor PRs now created autonomously with demos @mntruell.
• Boris Cherny (Anthropic) — on-the-record: Claude Code does 100% of his coding; he “doesn’t write any of it anymore” The Verge.
• Simon Willison — turning agent work into repeatable patterns: “First run the tests” + agent-generated linear walkthroughssimonwillison +1.
• Andrej Karpathy — pushing “build for agents”: CLI + Skills/MCP + exportable Markdown docs; argues CLIs are uniquely agent-friendly @karpathy.

🎬 WATCH & LISTEN

1) Cursor: “A computer for every agent” (video artifacts as proof) (≈ 0:10–0:35)

Hook: Cursor shows agents testing their changes on a real desktop and returning a video artifact that demonstrates the feature works—not just a diff Cursor.

2) Cursor demo: “paste GitHub issue → agent works → browser proof” (≈ 0:47–1:05)

Hook: A concrete flow: paste an issue link; agent works ~40 minutes; returns an artifact showing it navigated to the locally running app and verified the result in-browser Cursor.

3) Claude Code (Boris Cherny): what changed at Opus 4.5 (≈ 8:02–8:52)

Hook: The shift from “agent does first pass, human fixes” to “agent runs tests, opens the browser, clicks around, and fixes UI issues”—so he no longer opens a text editor The Verge.

📊 PROJECTS & REPOS

• Showboat (Simon Willison) — a tool designed so agents can build trustworthy walkthrough documents using executed commands + captured output (instead of pasted snippets): https://github.com/simonw/showboatsimonwillison
• “present” (Simon Willison’s SwiftUI app repo) + generated walkthrough
  • Repo: https://github.com/simonw/presentsimonwillison
  • Walkthrough doc: https://github.com/simonw/present/blob/main/walkthrough.mdsimonwillison
• Polymarket CLI — positioned as a terminal interface agents can use to query markets/place trades/pull data @SuhailKakar.

Editorial take: The day’s theme is verification as a first-class artifact—agents that can run, test, and demo their own work are the ones that actually scale async development.