Andrew Munn

API @ Anthropic

[Andrew Munn @AndrewMunn]

"Grapefruit" is the stupidest word in the English language. It's like if steak was called "chicken meat". I petition we adopt pamplemousse as a replacement.

[Claude @claudeai]

Introducing Claude Managed Agents: everything you need to build and deploy agents at scale.

It pairs an agent harness tuned for performance with production infrastructure, so you can go from prototype to launch in days.

Now in public beta on the Claude Platform.

[Andrew Munn @AndrewMunn]

Code execution is the future of tool calling

[Lance Martin @RLanceMartin]

claude opus 4.6 + its web search tool is now #1 on @arena's search arena. the web search tool is available in the API, and uses code execution to process intermediate search results (saves tokens / improves performance). docs:
https://t.co/Wp3STfyT9j
https://t.co/5rM9RDIUhL

[Anthropic @AnthropicAI]

A statement on the comments from Secretary of War Pete Hegseth.

https://t.co/Gg7Zb09IMR

[Lance Martin @RLanceMartin]

https://t.co/U5jwqltf6Q

[Alex Albert @alexalbert__]

Huge quality of life upgrade for devs:

We've added automatic prompt caching to the API which means you no longer have to set cache points in your requests!

[Brad Abrams @brada]

Not only is Opus 4.5 great at agentic coding, but with Tool Search tool and Programmatic Tool Calling, agents will get a lot better. Try this them out and watch Claude escape the room with these new tools! https://t.co/yCvKU6SwK6

[Katelyn Lesse @katelyn_lesse]

if you’re building an agent, check out the tool loop that ships in the anthropic sdk. it’s a very minimal scaffold that helps you take advantage of claude’s excellent tool calling ability. let us know what you think!

https://t.co/6ubpfRO1XG

[Andrew Munn @AndrewMunn]

We’re dropping Sonnet 4.5 today, the strongest coding, agentic, and computer-use model in the world. Sonnet 4.5 is the first model I’ve helped ship at Anthropic, and I’m psyched to get it in developer’s hands!

[Claude @claudeai]

Introducing Claude Sonnet 4.5—the best coding model in the world.

It's the strongest model for building complex agents. It's the best model at using computers. And it shows substantial gains on tests of reasoning and math.

[Andrew Munn @AndrewMunn]

@SathTweet Bruh it was a public works program and Salesforce just bought the naming rights.

[Andrew Munn @AndrewMunn]

@norbusonam Can I come over for steak

[Flo Crivello @Altimor]

Announcing a new chapter for AI agents: Lindy 3.0.

Our vision has always been the "Al employee": as capable as humans (can do anything on a computer) and as easy to use (just ask).

3.0 takes 3 giant steps in this direction, with Agent Builder, Autopilot, and Team Collaboration.

[Flo Crivello @Altimor]

Super excited for our first hackathon on August 9th in San Francisco! Already expecting 300 attendees and UNLIMITED MCDONALDS

[Flo Crivello @Altimor]

Normal day at Lindy

[Andrew Munn @AndrewMunn]

@Altimor Yeah the sticker is just vandalism insurance, I will remove it once the Elon-hate is no longer the current thing.

[Lindy @getlindy]

I built your email subscription tracker in ~10mins @jordienr

[Flo Crivello @Altimor]

Excited to announce Lindy's biggest update yet:
* Agent swarms let Lindy AI agents duplicate themselves and do 100s of things at once
* Integration supremacy: we are now the #1 agent in the world with the most integrations, with 5,000+ integrations and 4,000+ web scrapers

[Andrew Munn @AndrewMunn]

@andrew_n_carr Try @getlindy! Easy.

[Andrew Munn @AndrewMunn]

I'm gonna take credit for this.

[Andrew Munn @AndrewMunn]

Google Photos lacks the ability to flip a mirrored selfie. It's such a glaring omission it's honestly hard to believe it.