Hey folks,

Results from the poll are in. 996 total votes.

‘Do you use a personal agent?’

Not interested folks, r u ok? Just kidding.

Personal agent’s aren’t much more than a number of files and tools connected to any agentic tool you choose.

I’ll do a walkthrough of a session I had to setup a new (clean) personal agent for myself in tomorrow’s post. It really is just a bunch of files and tools. I shared my messy folder last week and I realised I must clean my desk before I start any work 😬.

Files give it context in the session - even memory is just a file it reads at the start of the session to seem-like it has memories, but it hasn’t. It’s just read those things (like me last-minute cramming for a test).

There’s so many tools out there with a bunch of features but ultimately if you have a folder with these pieces, you can have a personal agent. And that agent can use whichever tool you want - don’t like Claude’s latest writing style (pfft who does)? then point ChatGPT Work at the folder and work from there.

It also doesn’t matter if it’s the cowork or code versions of the agents.

-results in tomorrow’s post.

btw the latest best line I added in my AGENTS.md (agent instructions), from my agent spring clean:

questions are requests for an answer, not changes.

Agents actually just answer the damn question now instead of changing a bunch of shit and then answering!

Ben’s Bites is brought to you by Name.com¹⁶⁵

Ship domain integrations in hours with the name.com API¹⁶⁵. Use the API that powers Vercel, Lovable, and Netlify’s domain services.Built for agents and developers with OpenAPI spec and MCP support.Integrate search, registration, and management. Start building¹⁶⁵.

Headlines

Two new Mac apps today:

• Meta AI²⁵⁴ - ChatGPT-like Mac app, not built for coding. It also bundles in Wispr Flow like universal dictation in the app. I tried it for a minute, but currently no reason to go back to it.

• Berd³⁰² by Block - It combines the folders as project approach (codex/cc) with characters as agent (grok bot) with a board where you can pin these projects, agents, checklists and sticky notes. You can use your codex/claude code subscriptions for the tokens. Here’s a demo³¹³.

OpenAI paused improving their models for two weeks²²⁰ after the Hugging Face incident and signs that Astra may cross its critical-cyber threshold.

Ramp launched router.com³¹⁵ - it picks the best model for your task automatically. They claim 40% lower cost for the same outputs. Interesting timing: Stripe bought OpenRouter the same day, and their letter to investors explaining the acquisition got leaked²⁷¹. Oh, and Stripe co-led Ramp’s $115M Series B in April 2021.

Anthropic’s new research put Claude on duty to help life scientists¹⁸⁷ across two tasks: design protein binders from scratch and accelerate chemical analysis. Claude passed both. Reminder: Dario’s latest tweets had one clear message: “labs can’t just say AI will cure diseases, they need to show results.”

Slack is the new IDE... Slack now lets you multi-player code/build/agent from within Slack³⁶⁷. Say Slack one more time…Anyway, it’s interesting because you (humans) can collaborate but also with agents like Claude. And when Shopify posted about their Slack agent, they said it helped so many other team members learn how to use agents. This is a pretty good direction for Slack, I think.

My feed

• All of your company’s code and context belongs in a monorepo⁴⁰⁴. A monorepo is just one big folder with mini sub-folders.

• Can Grok Bot grow a newsletter to 20k subs and $20k MRR⁴²⁸?

• Replit is giving away GPT-5.6-Luna for free¹⁸⁵ (on its paid plans) in partnership with OpenAI. Keshav predicted their future²¹⁸…

• Vercel built its own version of Pi²⁷⁷ - a minimal coding agent harness.

• A moat is just one of 80 ways to win⁴⁷⁵.

• Stop letting your agents ship ugly UIs⁵³⁰.

• ElevenLabs’s new conversational model²²⁷ can help you create apps like ChatGPT’s updated voice mode.

• There’s a new AI lab for “better writing”²⁸⁰ that fools Pangram¹⁷⁸. But is that the measure of good writing? Tons of ways to fool Pangram and other AI detection tools btw…

• Notion’s solution for shared memory for agents²³² is to create a lore²⁵² based on your past conversations.

• Turn your codebase into an isometric city³²⁷ and explore its architecture.

• Matt Pocock’s skills have 200k+ GitHub stars²⁸⁹. Theo walked through the select few he uses³⁵¹.

• A Mac app for transcribing multi-hour recordings²⁸⁵, with a CLI for agents.

• Long read from Cursor on how they built Origin²⁸⁷ as if it were a database. Really good visually interactive post.

• Another code-storage startup²⁶⁹ nipping at GitHub’s heels. This one I’ve been eagerly awaiting, signed up yesterday and already started a paid plan. The Pierre Computer company put out awesome tools, and they’ve got a lotta taste.

• GPT-3 moment for teaching robots tasks²⁴².

• Lease a factory from Warp²³⁸ for your agents to build your product.

• An open-source version²⁸⁵ of Grok Bot.

• An open-source Mac app that automatically tracks your entire workday³⁸⁴.

Afters

We've raised $700M at a $21B valuation from Jane Street, Kleiner Perkins, Sequoia, A16Z, Peter Thiel, BCV, and Blackstone. We're also excited to share that we've shipped our first rack to Jane Street.

@Etched²²⁷

*disclaimer - I’m an early investor 😉

Currently I’m really into markdown graphs with one vibrant accent color

@emilkowalski²⁰⁹

We're continuing to improve cloud agents in Cursor. They pick up work from events, hold a goal until it's met, and stay on course through long sessions.

@cursor_ai¹⁹⁹

Introducing 1kpapers.com! I took the top 1k research papers of the last year, summarized them, and visualized them. Fun fact: all 1,000 papers cost a total of $4 to summarize with DeepSeek V4 Flash.

@nutlope²⁵⁷

My life has become boring All I do is asking coding agents to write a PLAN.md, then /grill-me on it to improve the plan, then spin up an agent to implement it I'm just a markdown manager now😭😭

@NielsRogge²¹³

I've been tinkering with an AI to increase my “luck surface area” (basically, to find interesting opportunities that exist across my entire network) and the results are ... pretty interesting. Built on my corpus of personal & professional data - everyone I’ve met with, emailed,

@edleonklinger³⁴¹

the models have no moat (OpenAI, Anthropic, XAI) the IDEs have no moat (Cursor, Windsurf) the harnesses have no moat (Cognition, Factory, LangChain) the app builders have no moat (Replit, Lovable, Bolt) the wrappers have no moat (Harvey, Abridge, OpenEvidence) the inference

@nikunj²³⁶

I'll be going on TBPN today. I'm at the MTS Live studio. I just announced a new $2.42B round on Sourcery. I'm on a redeye to London for 20 Minute VC. Just did the MOTS Pod pushup challenge. I'm whiteboarding with Dwarkesh. Just did Senra. I'm on Invest Like The Best.

@TurnerNovak¹⁹⁴

• Find me on X¹³⁶, Linkedin¹²¹, or YouTube¹²⁰

• Read about me¹⁴⁷ and Ben’s Bites

• 📷 thumbnail via @keshavatearth¹³⁸

* sponsors who make this newsletter possible :)

Wanna partner with us for the next quarter?

Email us at shanice@bensbites.com¹⁴⁰ or k@bensbites.com¹²⁰