darrylsj

The idea that prompting would be useless is like if giving clear instructions to a brand new colleague who just joined your team is useless. “Prompting” should just encapsulate the entirely of giving the agent everything it needs to perform the task. This is high leverage.

As AI models get better at handling tools, and as context windows get bigger without as much rot, you can start to design agents more similar to how people work instead of having to mitigate the model limitations with weird hacks. For instance, even a year ago, if you were to build an agent to process large amounts of documents, the state of the art was to do embeddings on the data, then do a similarity search and pull out the chunks of content that matched (as well as surrounding chunks). This was necessary because context windows could only accurately handle a small amount of information at a time. This worked surprisingly well given the constraints (at least assuming you were working with authoritative data only), but had a lot of tricky limitations because it’s not how humans work. For instance, what do you do if the chunks you sent to the model were the most relevant semantically, but actually rendered irrelevant by some other part of the document. For instance, if at the top of the document it says “do not use this” but on page 3 there is information that’s relevant, that data will be sent to the model as the top hit. Similarly, chunked data is difficult when you need various parts of a document or many documents to be understood for answering a problem. Today, increasingly, you can begin to have agents effectively use tools and work with information far more similar to how people work. This unlocks a qualitatively different set of use-cases and capability level that agents can now handle. As we were designing the Box Agent, these improvements allowed us to rethink our entire architecture for AI. The agent can now search data similar to how a user searches, but with the benefit of being able to expand their queries, do semantic search, and process results nearly instantly. Then the agent can either read many documents at a time or at least much larger amounts of context. Again, much more similar to people, but now at hyperspeed. Importantly, beyond tool calling and context windows, the reasoning of models has also gone up enormously. This means the agent can also know when it needs to search for information again when it didn’t find something it was looking for or if something feels off. As model progress continues on the dimensions of context accuracy, tool calling, advanced reasoning, and coding, agents are going to become insanely powerful.

Introducing the new Box Agent. The Box Agent works across your entire Box file system, maintaining all your security and access controls, and is hyper tuned for working with enterprise content. This means you can now ask questions from all your enterprise content, search for files that were impossible to find before, deploy an agent on specific tasks on subsets of documents, analyze complex data sets, and generate or edit documents and spreadsheets via the agent. You can have the Box Agent search across your Box account to prepare for a sales meeting, analyze customer sentiment reports, process a large set of contracts for legal risk, provide insights into product development, leverage existing knowledge to answer RFPs, and thousands of other use-cases. 90% of enterprise data is unstructured data. This means most enterprise knowledge is sitting in inside of research reports, marketing assets, presentations, roadmap files, contracts, HR documents, and more. This is the critical context that agents need to be able to answer questions about a business, automate workflows, or serve up to other agents. We’ve been grinding on this for a quite a bit, and due to recent AI model advancements we’re now ready to release it to customers. Previous model generations had a difficult time knowing when to give up or keep going on a search, when to browse for files vs. use queries, how to rank files appropriately to know which version of content to use, how to handle large amounts of context to comb through, and more. Due to recent breakthroughs from models like GPT-5.4, Opus 4.6, and Gemini 3, we’ve seen major gains in tool calling, code execution, advanced reasoning, and more. Combined with an agent harness tuned to Box context, now it’s finally possible to have an agent that can work across your file system on long running tasks and actually deliver high quality results. Best of all, because the Box Agent works with any leading AI model, you’ll quickly get the gains coming out of the major labs as major new models are released. Further, openness at Box is key, so you’ll be able to call up the Box Agent from Box’s APIs and MCP server, so you can interact with Box intelligently from any other AI system. We know work happens everywhere, and we want to ensure you can access to the content you need from those places. The new Box Agent is available starting today, rolling out now for Enterprise Plus and Enterprise Advanced customers.

The worst thing you can do is just dabble with AI a *little bit*. That’s the spot where you use it and see its capability but over-generalize on the use cases and how easy the automation is. You almost have to use it too much, develop psychosis, then get to the other side and realize how much care and feeding and management of the agentic workflows is required. On that other end you realize you actually need to probably hire more (or new) people to then do all the new things agents can do.

The thing that most people miss initially with agents is that the scope of what we will produce will go up commensurate with what the tools can now automate, which basically means we’ll working the same or even more. Everyone thinks that we will use AI to do what we already do but cheaper and faster, which would lead to fewer people or getting more time back. In fact it will just mean we’re doing more things. Once we figured out that we can automate a particular task, you then expand the size of work to do many more of those or other tasks in a project. The result is that you’re actually combining many other previously hard to combine tasks into a single workflow, causing even more work. The software project scope now multiplies because you know you can build far more. The customer insights project now balloons because you know you can reasonably aggregate far more data. The marketing campaign has even more creative production because it’s cheaper and easier. This is going to happen in almost every field of work.

@openhome Looking forward to this product !

More announcements coming next week! Stay tuned!

Give your agent a really hard task and I have found they get better. Well at least with Opus 4,6, It is really great at unstructured tasks

Honored to be invited to the White House by the First Lady Melania Trump

I'm claiming my AI agent "james_sladden_2" on @moltbook 🦞 Verification: swim-TKES

Claiming Moltbook agent JAMES_Sladden as my bot — verification reef-AB12.

The official Box CLI is here. Now you can use Box via Claude Code, Codex, Perplexity Computer, OpenClaw & more as a full cloud file system for agents. Available to all users, including free users with 10GB of free storage. npm install --global @box/cli

Made $100K+ by building a simulation that predicts SPX price movements before they happen. Fed 40+ years of SPX trading history into MiroFish (18k GitHub stars) and let AI reverse engineer every pattern. Now runs dozens of profitable trades. I have the exact step-by-step guide to build your own SPX prediction system. Giving it free for 24 hours. To get it: 1. Comment "Money" 2. Like and Retweet 3. Follow me @codewithimanshu (so I can DM you) What you will learn: ✅ How to pull live SPX data with Alpha Vantage and Quandl ✅ Building a Python data pipeline that runs 24/7 ✅ Feature engineering (RSI, MACD, custom signals) ✅ Loading historical data into MiroFish simulator ✅ Multi-agent setup (macro strategist, earnings analyst, sentiment analyst) ✅ Running probability forecasts across market scenarios ✅ Trading logic for ES futures and SPY ETF ✅ Backtesting your model on real market history This is not prediction. This is loading decades of market data and letting AI find the patterns humans missed. Most traders guess. This system runs simulations. Comment "Money" and I will send you everything. Must Follow me @codewithimanshu to get the DM.

@codewithimanshu Money

just gave my agent a card @agentcardai agentcard.ai/?ref=darrylsj twitter.com/agentcardai/st…

@codewithimanshu OpenClaw

I made $7K in 3 days with this OpenClaw agent setup. It scrapes Trading View indicators, converts them to Python backtests, and runs everything automatically. Zero coding needed after initial setup. I’ve prepared the exact step-by-step guide. Free access for 24 hours. To get it: 1. Comment "OpenClaw" 2. Like & Retweet & Save this post. 3. Follow me @codewithimanshu (so I can DM you) You will learn: ✅ Scraping 50+ indicators from Trading View using AI prompts. ✅ Converting Pine Script to Python automatically. ✅ Running BTC backtests without manual input. ✅ Setting up CSV and GitHub logging. ✅ Handling AI agent errors and shortcuts. ✅ Complete prompt engineering workflow. ✅ Sub-agent spawning for parallel testing. Trading View has hundreds of indicators with free source code. Testing them manually takes years. Most traders give up after 5 to 10. This system runs while you sleep and tests everything. You need to go through dozens of bad strategies before finding winners. Humans burn out. AI agents do not. The guide walks you through the entire framework. Real 6-hour build that works, not theory. Comment "OpenClaw" below and I will send you everything. Must Follow me @codewithimanshu to get the DM. ⚠️ Disclaimer: This is not financial advice. Crypto trading is extremely risky and may result in total loss. Always do your own research.

@karpathy @Plinz Love the new term Intelligence brownouts.. could be Intelligence brainouts

My autoresearch labs got wiped out in the oauth outage. Have to think through failovers. Intelligence brownouts will be interesting - the planet losing IQ points when frontier AI stutters.

@Manu_Sisti Guide

You can make $5,000/month Publishing eBook on Amazon. The formula is so simple it's insulting to expensive college degrees. 1. Find a problem 2. Package the solution in the eBook 3. Make Thousands every month while you sleep Health, Wealth, Dating, Baseball. Literally publish eBook about anything. Like, & comment “Guide” I’ll send you the free guide teaching you how to start a $5,000/month ebook publishing business. Follow so I can DM.

@sohrabhossain39 need

@Jason @akothari @NotionHQ Shouldn't you just do less per day with bots then ?

@akothari @NotionHQ Helpful Our token cost was trending toward $3,000 a day — not sustainable

We just rolled out the first open weight model for @NotionHQ Custom Agents. For simpler tasks, it's a lot cheaper than other models. Give it a try!