A lot of people are asking how I pulled off these super long-horizon builds with Astra. Astra is extremely powerful, but by default it struggled with a task this difficult. I tested a bunch of approaches to get past this, and the one I landed on is something I'm calling the Manager Loop. It's basically a couple of tricks we used to use with much less capable models a couple of years ago, with a few new ideas layered on top. Turns out that when you put those together and apply them to Astra, its ability to do extremely difficult long-horizon tasks goes up dramatically. Here's how it works: 1. Launch an agent (I'm calling this one the "manager"). Chat with it about what you want to get done, and have it build a massive checklist of to-dos, then break that checklist into phases. 2. The manager then spawns a second Codex agent in a separate thread (the "implementer"). The two agents can message each other. 3. Put the manager in /goal mode, and tell it to run each phase on the implementer in /goal mode. 4. The manager messages the implementer: "/goal Complete phase one completely, extremely well." The implementer doesn't stop until that phase is done, then messages the manager back. The manager tells it to start phase two. They repeat until every phase is finished, completely autonomously. Why I think this works: over a long-horizon task, Astra tends to asymptote. It gets way further than previous models, but at a certain point it kind of just stops improving against the goal as quickly as it did before. It gets stuck in the minutiae, focusing way too much on small details, and overall progress stalls. The Manager Loop forces it to work piecemeal, one phase at a time. It's essentially how a human would steer a model, except the model is doing the steering for me. That's actually how this started. I was having the model write the checklist and break it into phases, and then I was doing the manager's job by hand. At some point I thought, "Wait, why can't I just get a separate AI to do this?" That's what unlocked full autonomy, which is super useful. A wording detail that seemed to matter: I ask for each phase to be done "extremely well," not "perfectly." Maybe I'm reading too much into it, but asking for "perfect" sent the model right back into the minutiae. "Extremely well" implies it's allowed to move on once it's good enough, and that worked better in my testing. One more trick that I think helps (this one is more of a hunch, but it was useful for me): have the implementer build a simple HTML page with the full checklist on it. The implementer checks boxes off as it goes and updates a counter, and the page has a chart of # of boxes ticked over time. Obviously the boxes aren't all equal, but it forces the model to notice things like "I haven't made progress in a while, time to move on." You can even put this in the prompt directly, like: "if you haven't ticked a box in X amount of time, move on". That helps a lot. I also ran 96 sub-agents at a time. You can change this in your Codex config (or just ask Codex to change it). This got me far better long-horizon performance than anything else I tried. I'll be sharing more in the coming days!

Your competitor isn’t your biggest threat. Your ability to abandon your SaaS for a shinier idea every 3 weeks is

Still wondering where to market your app outside the US? These are the top markets to focus on if you want to generate the highest LTV among 180 countries. Save this list and focus on these markets in next 30 days

Here's a prompt that runs Gary Klein's premortem on any decision before you commit to it. You're good at defending a plan and terrible at attacking it. Once you're attached to an idea, your brain hunts for reasons it'll work and quietly skips the reasons it won't. That's how obvious risks survive all the way to launch. This prompt forces the opposite. It runs a premortem, the method cognitive psychologist Gary Klein introduced in Harvard Business Review. The model assumes the plan already failed and reconstructs exactly how, so the weak points show up as a story you can read instead of a surprise you have to survive. Here's the prompt. "Assume the plan I'm about to describe has already failed completely, twelve months from now. Write the story of how it failed. Name the three or four most likely causes, the early warning signs I would have ignored, and the one decision that probably sank it. Then tell me what to change now to prevent each one." Run it on anything you're about to commit real time or money to: a launch, a hire, a big strategic bet. You get a list of failure modes while you can still do something about them, which is the whole point of thinking about the ending before you start. Save this one. It's the cheapest insurance you'll ever run on a decision.