Blaine Yeager

@awsdevelopers @grok why would I use this instead of the AWS CLI with coding agents like claude code

we just dropped an MCP server, have you set it up it yet? → full AWS API coverage → sandboxed script execution → real-time documentation access

Turn any website into an API with /browser-to-api. This skill analyzes network activity, CDP logs, and website behavior to generate a custom OpenAPI spec. Watch Codex one-shot a fully documented OpenTable API client from a single prompt 👀

Starting June 15, paid Claude plans can claim a dedicated monthly credit for programmatic usage. The credit covers usage of: - Claude Agent SDK - claude -p - Claude Code GitHub Actions - Third-party apps built on the Agent SDK

How do you keep Claude working until the job is done? Claude Code helps with this in a few ways, including one we shipped recently: /goal.

New in Claude Code: agent view. One list of all your sessions, available today as a research preview.

Introducing the Lovable aesthetics update, a new level of design in vibe coding. Ask for typography, layout, and color preferences. Preview design concepts before building, and create bolder landing pages, apps, and blogs.

/radio

The Product team at OIT has been busy! Numbers Management just shipped in MPP. Self-service ordering across 4 carriers, one inventory, no tickets. voipdocs.io/inventory-phon…

Pets. Now in Codex. Use /pet to wake your pet.

Last week, we released a preview of memories in Codex. Today, we’re expanding the experiment with Chronicle, which improves memories using recent screen context. Now, Codex can help with what you’ve been working on without you restating context.

Introducing Euphony, an open-source tool for visualizing chat data and Codex session logs. Paste in a public URL or upload a local file, and Euphony turns the raw data into an easy-to-browse view. It supports translation, filtering, editing, and more.

SpaceXAI and @cursor_ai are now working closely together to create the world’s best coding and knowledge work AI. The combination of Cursor’s leading product and distribution to expert software engineers with SpaceX’s million H100 equivalent Colossus training supercomputer will allow us to build the world’s most useful models. Cursor has also given SpaceX the right to acquire Cursor later this year for $60 billion or pay $10 billion for our work together.

Caching is critical for customers to lower both costs and TTFT. We’re launching a new dashboard in Claude Developer Console to increase visibility and help customers optimize their usage. Check it out here: platform.claude.com/usage/cache

opus 4.7 seems to have a much better time in claude code if you run without most of the system prompt (claude --system-prompt ".")

Claude Code in the terminal will now show recaps when you switch focus away from the session and then come back. This should help you stay more in flow while multi-clauding.

We’re adding more visibility into where your Claude Code usage goes. Run /usage to see a breakdown of what's driving it: parallel sessions, subagents, cache misses, long context, plus tips to optimize each.

Claude Code 2.1.88 has been released. 41 CLI changes, 3 system prompt changes Highlights: • Agent guidance adds 'never delegate understanding': agents must verify comprehension to avoid misdelegation • Fixed StructuredOutput schema cache bug causing ~50% failures in multi-schema workflows, restoring reliability • PermissionDenied hook fires after auto-mode classifier denials; returning {retry: true} lets the model retry Complete details in thread ↓

people to follow who are working on claude code (who else?) @_catwu: founding pm, coined antfooding (walked around the office and watched engineers using the product), former investor at index ventures! @bcherny: head of claude code, ex-principal eng at meta, author of an o'reilly book on typescript @trq212: built chime which was acquired by hubspot while an undergrad, cofounder of multiverse (yc) @noahzweben: pm, prev first pm at warp (the terminal), columbia eng valedictorian, painter @karan_sampath: engineer, applied ai. researched w Duncan Watts (computational social scientist, small world networks) @IsabellaKHe: ex-de shaw, stanford psychiatry research, founded a platform that makes therapy kits for kids with autism @lydiahallie: engineer, dx. popular js/ts instructor. dx at bun and vercel @amorriscode: ex-stripe. voice mode, desktop, office hours @alicelovescake1: engineer. moved her career path from sales to eng in 2020, ex-notion @OmidMogasemi: mts. auto-fix pr feature

Watching Jenny (Cowork's design lead) walk through her thinking behind all her past Claude Cowork iterations was fascinating. "It's this constant balance between how much do we tell people how to use [Cowork] versus leaving it really free form for them." "Over time, we stripped away alot of the really opinionated UI because it wasn't actually helpful to show all of these things." 📌 Watch Jenny talk about it here: youtube.com/watch?v=rlIy7b…

the more I've been digging into the new Figma MCP, the more excited I am about it something new I'm trying is starting with a very ugly sketch in Figma, and then having Claude Code flesh it out in Figma so I can tweak and edit before sending the final back to Claude Code