We keep hearing about giving agents the right context - that’s our job now.

But how do you actually give it instruction files to write/design/code/whatever like YOU want it to?

A pattern I see a lot is getting your agent to interview you.

Your task is to interview me and get all the information you need to [your task].

Then add a specific ask based on your goals…

Come up with a number of interview questions for me about landing page designs I like, why I like them and what I don’t like.

Ask me a number of questions on how I think about sales copy, ask me for some examples I like and dislike and why.

Interview me about writers I like, which books/posts I love from that author and why.

I recently did this with the course I’m working on.

I hate courses. I don’t think the majority of them do all that much teaching. They walk you through steps to mimic getting you to the end goal. But once you ‘graduate’ (not many people do), you’re on your own.

But real life is never that straight forward, you’ll always hit bumps in the road and courses don’t give you the knowledge to navigate them.

I get stuck with blank page syndrome. I need something, anything, to start me off - even if it’s AI slop.

So I asked my agent

I am writing a course on 'Becoming a builder'. A helpful guide for non-coders to learn how to work with and steer agents, understand systems of code projects (not specifics of how to code) and learn whilst building.

I want you to interview me so we can flesh out the course content map - a hierarchical overview of the topics to cover, with some bullets on the points to cover.

Ask me one question at a time, I may disregard questions but I will say why I don't think its relevant. 

Feel free to probe further if you dont have enough context for any section.

Really try to understand what and how I'm teaching based on the end outcomes I've specified.

The agent asked me 20 questions and I spoke my rambling thoughts back. I was genuinely surprised how often it would remember to probe me, or ask clarifications like ‘do you actually mean to go down this route or this one’.

All in all a very helpful exercise in getting off the blank page. I now have a number of sections with ‘what this covers’. Even if on first glance I know I’m going to remove/merge/edit a lot, I’m moving forward.

What am I building this week?

• I’m furiously working away on the course I mentioned above, named Fork Off.

• I want to revisit my OpenClaw/personal agent memory system - has anyone found one that they absolutely love and swear by?

• I really want to make a YouTube wrapper for my kids where I can pre-approve channels I let them watch. Fuck CocoMelon, ASMR, cutting coloured sand and all that crap. YT’s algo just constantly surfaces these. Also if you make a YT video for kids, please put the thumbnail scene at the start of the video - or you get meltdowns 🙃

Ben’s Bites is brought to you by Reevo

Go stackless and get back to selling. Remember when selling meant talking to people? Before the tab-switching and endless sync errors. Reevo¹¹³ brings it all back to one platform. Prospecting, calls, pipeline, and reporting all in a single tab. From prospect to close. Go Stackless. reevo.ai¹¹³*

Headlines

• You can schedule recurring cloud-based²⁵⁸ tasks²⁵⁸ on Claude Code, and you can now enable Claude to use your computer to complete tasks¹⁵⁸. It uses your connectors first, but if there's no connector, it’ll use your computer to open the app (but your computer must be on!) Plus projects are now available in Cowork.

• Long-running agents designed to automate large software tasks³⁸⁴ like building applications from scratch with Factory Missions. This is genuinely the closest feeling of AGI I’ve ever had. You spend decent time planning your mission but then it just does everything end to end.

• ChatGPT now has a library of the files you upload¹⁴⁷, making it easier to reference them. OpenAI is also planning to simplify its product experience and launch one “superapp” - much like Claude has done with their Desktop product.

• Cursor launched Composer 2⁸¹ as their latest ‘in-house’ coding model. It came to light that the model was a tuned version of Kimi’s 2.5 open-source model (which they failed to mention, which caused some rumblings on X.) They boasted about their high scores on their own benchmark, CursorBench - but only compared their scores against Claude Code/Codex (not any other harnesses which outperform them), which feels weird considering they are a harness themselves. They also released ‘Glass’, which is their new interface that follows the 3-column layout that lots of apps are using.

• SpaceX, Tesla and XAI launched TERAFAB¹¹⁶, the largest chip manufacturing facility ever (1TW/year). This post²⁰⁸ from Sequoia Partner Shaun Maguire puts forward the idea that everyone is sleeping on XAI, and how it will win in AI.

• New model, worse benchmark. Plot twist: the truth files were wrong. AssemblyAI found their AI penalized for transcribing things correctly that human labelers missed. Live workshop March 31 on why WER breaks and how to fix your eval pipeline⁸².*

⁸²

My feed

• Speechmatics¹²⁴ – STT for voice agents. <300ms latency, high accuracy at conversational speed, 55+ languages. BB readers get $200 free credits¹²⁴.*

• Codebase to Course²¹² - a skill to make learning codebases more visual and interactive.

• Luma Labs has a new image generation model: Uni-1.⁹⁵ Think Nano Banana with a canvas and multiple outputs per turn. It’s good but slow because of the many outputs (sometimes 10+ for a single message).

• GPT 5.4 is awful at frontend design - but this guide¹⁸² apparently makes it better. And they’ve added a frontend-skill to use in Codex. I’ve not yet tested it - mixed reviews on X.

• ~99% SOTA memory system²⁵⁸ for agents.

• ‘The Minimalist Entrepreneur’ is a great book for founders, and now Sahil’s turned it into a set of agent skills⁴³⁵.

• A podcast with Simon Willison: Engineering practices that make coding agents work²¹⁹.

• Must read/listen: The End of Coding⁴²⁶: Andrej Karpathy on agents, autoresearch, and the loopy era of AI.

• How to use Claude Code to design⁴⁶⁷, by one of the Tailwind founders.

• Ghost Pepper²⁸⁰ - 100% local hold-to-talk speech-to-text for macOS.

• Deploy a team of OpenClaw agents²⁶⁶ securely.

• Lovable is kinda pivoting²⁵⁵ from an app-making tool to a general agent.

• AI style guides: How to help AI write like you³⁶⁹

Afters

There is a tremendous amount of progress happening in World Models. Multiple labs have raised more than $1B. WMs were the star of GTC. They are a real path to embodied AI. So @PimDeWitte &amp; I wrote a comprehensive 19k word overview of World Models.

@packyM¹⁵²

Introducing the Music Marketplace in @ElevenCreative. Creators, artists, and musicians can now publish and earn from their tracks created with our music model.

@ElevenLabs¹³³

Wow. Jeff Bezos is raising a $100B fund to buy manufacturing companies and automate with AI.

@pitdesi¹¹³

spent last night organizing swiftui docs so that I can pass them to an agent easily 50k words narrowed down to &lt;1k words to find the exact webpage from apple docs your agent needs. just point it to this repo:

@Keshavatearth¹¹⁵

Hermes Agent wrote a novel. "The Second Son of the House of Bells" runs 79,456 words across 19 chapters. The agent built its own pipeline to do it, using the ame modify-evaluate-keep/discard loop as @karpathy's Autoresearch but applied to fiction: world-building, chapter

@NousResearch¹⁷⁴

Browserbase now has a CLI. Browse the web, deploy serverless automations, debug sessions, and manage your entire project — all from the terminal. Just tell your agent: "Read browserbase.com/SKILL.md and set up Browserbase" Or try it yourself: npm i -g @browserbasehq/cli

@browserbase¹³⁸

T3 Code now supports Claude. If you have the Claude Code CLI installed and signed in, you can use it with T3 Code. Hopefully the lawyers won't make us remove this 🙃

@theo¹⁰⁴

vibe coding in AI Studio just got a major upgrade 🚀 • multiplayer: build real-time games &amp; tools • real services: connect live data • persistent builds: close the tab, it keeps working • pro UI: shadcn, Framer Motion &amp; npm support we can't wait to see what you build!

@GoogleAIStudio⁹⁸

• Find me on X⁴⁰, Linkedin³⁷, or YouTube³³

• Read about me³⁸ and Ben’s Bites

• 📷 thumbnail by @keshavatearth³²

* sponsors who make this newsletter possible :)

Wanna partner with us for the next quarter?

Email us at shanice@bensbites.com²⁷ or k@bensbites.com³³