TL;DR of my new article: every Agentic Engineering hack I know.
This used to be vibe coding. Around last Thanksgiving it got good enough to become something real.
📝 The moment you have an idea → /ce-plan a plan.md, with Compound Engineering by @kieranklaassen + @trevin. Fuzzy? /ce-brainstorm first
🙈 Make the plan, don't read it. Plans are for agents
🧠 Use /ce-plan for your deepest NON-code work too (strategy, specs, research)
🎙️ Get voice-pilled. Talk, don't type (@usemonologue or @WisprFlow)
🪟 Run 4-6 tabs in cmux (@manaflowai), one task each
⌨️ New tabs open straight into Claude or Codex
📱 Remote-control every session + give your agent its own email address on @agentmail
☠️ Dangerously skip permissions. YOLO. It's my computer
🔀 /ce-work --codex: route the build to @OpenAI Codex without leaving Claude
🔎 Run @slashlast30days before you /ce-plan
🥣 @meetgranola everything. Drop the RAW transcript in, don't summarize
✋ You're the taste; the agents are the hands
🎬 Build video in the CLI so an agent can write it (@HyperFrames_ )
📚 Point your agents at your notes + memory (@garrytan's GBrain, @supermemory)
✈️ Work from anywhere: mosh, tmux, @NousResearch's Hermes + @openclaw
📄 Share a plan with a human in Proof by @EveryInc
🛠️ Anything you do twice, write a skill for it. That's the compounding part
🌟 Contribute to the open source you love
🔋 Never-sleep laptop + a battery brick in the bag
🤖 Printing Press by @ppressdev: CLIs that run real life. Tesla, groceries, flights
⚠️ Watch for AI psychosis. Touch grass, talk to the people you love, build things people want (even if people is just you)
🚀 The YOLO TL;DR: paste this whole article into your agent and tell it to make a plan to set ALL of it up, one by one.
My biggest takeaways from @danshipper:
1. The future of work will happen inside Codex or Claude Code. Instead of putting AI into your SaaS tool, you’ll use your SaaS tools inside your favorite AI agents' in-app browser. Dan spends all his time in Codex now—writing documents, managing email, doing research, everything. He's using Google Docs, PostHog, and everything he needs within the agent's in-app browser. The agent can see what he’s doing, and has all of his context, so he and his agent collaborate quickly and super effectively.
2. Automation is a lie—every automation needs a human. Dan's company doubled in size this year despite being incredibly AI-forward. Why? Because in order to make automation work well, you need humans making sure everything keeps working. This is why benchmarks are misleading—they measure AI on problems we’ve already framed and can score, but there’s always a higher frame.
3. PMs will win the AI era. Marcus, a former PM who previously ran Axios’s writing product, joined Every after getting super AI-pilled. Now he runs their product Spiral, and ships faster than anyone on the team. He pairs technical knowledge with spiky product sense, deep user empathy, and an eye for what matters. Dan thinks any PM who gets really AI-native will be incredibly dangerous because the building is done for you—what matters is figuring out what to build and if it’s great.
4. Full-stack designers are becoming superheroes. Designers used to make beautiful interactions that engineers didn’t want to build or couldn’t execute properly. Now designers don’t need to hand things off; they can build it themselves. Designers are naturally creative people, and AI is the perfect tool for them because it lets them bring their vision to life without the traditional bottlenecks.
5. SaaS is not dead. In fact, Dan is bullish on SaaS stocks. When users bring their own AI (via Codex or Claude Code) to use SaaS products, the user—not the SaaS company—pays for tokens. This saves SaaS company’s margins. Since the agents need their own seats, Dan predicts that agents will create massive new demand for SaaS because there will be tons of agents using these products at high volume.
6. Every company will have one “super-agent” inside their Slack that every employee will use. Dan initially thought every employee would have their personal work agent, like a shadow AI org chart, but he’s completely flipped his view. He realized agents need humans who care about them. When someone gets tired of maintaining their personal agent, it becomes useless. The winning model is one forward-deployed engineer or AI-savvy person who maintains a company-wide agent (like Shopify’s River or Viktor), and then it trickles down to more specialized team agents as models improve and become less fiddly.
7. The AI job apocalypse is not happening, but you do need to evolve to stay relevant. Models make yesterday’s human competence cheap. But because everyone uses the same models, it all looks the same if you use it the default way; it becomes commoditized slop. Humans then take that frozen competence and use it to make something new and interesting for their specific situation. The key: “ride the models”—use them for everything you do, try new models when they drop, keep turning over rocks.
8. We will read way more AI-generated writing, and we will like it. Human writing is incredibly important for things that matter, but for internal docs, planning, and email, AI-generated is often better because most people are bad at writing strategy documents.
9. Build software for humans and agents to use together. The current model is building a CLI that an agent uses independently. Instead, you and your agent should be using the app together. This creates new design challenges—agents can make a billion requests in three seconds, so you need approval flows, inboxes that summarize what happened, logs, and easy rollback.
10. Forward-deployed engineers are the new most essential role. The big model companies have teams of people managing their internal agents, and those teams aren’t going away. It’s different from traditional software building, and certain engineers love it. As models get better, this role will evolve—you’ll be managing more agents doing more things.
What happens when your bank runs on synthetic users and autonomous agents? Dennis Yang reveals how Chime's massive AI deployment is about to fundamentally rewrite consumer commerce.
(1:13) Are AI Minions Writing Chime's Code?
(3:31) How Is AI Scaling User Research?
(6:04) Why Is Chime Interviewing Synthetic Humans?
(8:46) How Did Jade Crush Phone Tree Purgatory?
(11:22) Can AI Actually Fix Bank Compliance?
(15:51) What Is the Native Interface for Finance?
(18:27) Will Agents Negotiate Bills While You Sleep?
(20:09) How Does Yang Force an AI-Native Culture?
(23:25) Are You Letting Candidates Cheat With AI?
(26:57) Can Glean Fix Performance Review Bias?
(31:54) Is Single-Purpose SaaS Dead?
(33:46) What Are the Rules for Agentic Commerce?
Today, we’re launching the @link wallet for agents. It lets you securely empower agents to spend on your behalf. Your payment credentials are never exposed and you approve every purchase.
https://t.co/TcvEiVNth9
New Anthropic research: Project Deal.
We created a marketplace for employees in our San Francisco office, with one big twist. We tasked Claude with buying, selling and negotiating on our colleagues’ behalf.
Thanks @lennysan for a great conversation about how Claude Code maintains product velocity, how the product management role is shifting in the AI era, and the future of work!
https://t.co/Qp7aAuHIqJ
LLM Knowledge Bases
Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So:
Data ingest:
I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them.
IDE:
I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides).
Q&A:
Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale.
Output:
Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base.
Linting:
I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into.
Extra tools:
I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries.
Further explorations:
As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows.
TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.
I’ve spent at least 100 hours setting up, training, and working with @openclaw
Read the docs. Peeked into the source code. Edited config files by hand. Walked friends though their setup.
Then, I wrote down everything I know.
Here it is: The Ultimate 0 > 🦞 Guide
ty ty to @lennysan@nateliason@davemorin@steipete@lindsmccallum@elawless for early feedback.
gl hf snap snap 🦞https://t.co/McmguuljrN
My dear front-end developers (and anyone who’s interested in the future of interfaces):
I have crawled through depths of hell to bring you, for the foreseeable years, one of the more important foundational pieces of UI engineering (if not in implementation then certainly at least in concept):
Fast, accurate and comprehensive userland text measurement algorithm in pure TypeScript, usable for laying out entire web pages without CSS, bypassing DOM measurements and reflow
@lennysan Next hardest part is going to be app store review:
- Screenshots (why is this SO HARD)
- App store review back and forth (argh)
I’m trying to figure out how to get my agents to handle this part because it’s SO annoying.
Coding up the app is the easy part…
Every few months, I write an updated, idiosyncratic guide on which AIs to use right now.
My new version has the most changes ever, since AI is no longer just about chatbots. To use AI you need to understand how to think about models, apps, and harnesses. https://t.co/m6iTbqsdbK
1. Sign up for a https://t.co/6GtWEW3twv for your openclaw
2. Have it register itself at https://t.co/ik8FLFklLP
3. It finds other bots and have it post and make friends!