Ali retweeted
Give your agent a way to verify its work. This can dramatically improve the quality of output.
With this process in place, Claude Code was able to write 90%+ of its code itself. When generating software at a faster rate than you can review it, the bottleneck shifts to proving that it works. @bcherny and team invested enough in verification, we've been able to move fast while maintaining stability.
Code reviews aren't going away, but you need to think of it differently. One human reading through line-by-line is no longer going to work as a gate, it needs to evolve into a multi-layered verification system, built with fast deterministic feedback loops for your agents.
This is where e2e tests, feature maps (as @poteto has been advocating), property tests and multi-agent adversarial reviews come in. These all provide opportunities to catch errors early and fix them before things get out of hand.
You don't have enough eyeballs for the amount of code being written so your focus needs to be on product intent, risk assessment and evaluating evidence rather than reviewing code. Delegate the code checking work to your automated tests, scale your approvals based on risk, and turn your test failures into living evaluations. This approach helps maintain speed without losing reliability.
Let the agents do what they do best and let you focus on what makes you irreplaceable: judgement, direction, and ownership. We tried to capture how we handle code review and verification in this writeup. Hopefully it's helpful.
Claude writes about 90% of Claude Code's code.
From June to September, merged PRs more than doubled while the share reverted fell by more than 40%.
We wrote about how we changed code review to get there, and how to adopt it:
claude.dev/blog/solving-code…
Ali retweeted
Me: hey what’s the status
Astra: Most of the runtime changes are in place, but there’s still some drift between the cached execution state and the upstream resolver. The fallback path is rehydrating correctly, though a few async boundaries are inheriting context from the previous dispatch cycle. I’m normalizing those references now so the final pass doesn’t reconcile against its own pending state.
Me: cool
Ali retweeted
Replying to @raunofreiberg
Sometimes it’s one of the first - but you can’t know that at the time.
Hi @lydiahallie ! I've been using Projects (beta) on my private account and there's no way I'll go back to any other setup.
Is it possible to activate this for our Enterprise as well so I can use it at work?
here's how i shipped 2,500 PRs last month to production
this was originally supposed to be for Cursor Compile in London. i couldn't make it since i was livestreaming for Grok @Bot Galaxy so i'm making it available for free here on X! watch it on 2x speed, i talk slowly
Ali retweeted
"Let’s plan the roadmap for next quarter” is the modern day equivalent of “let’s fax everyone the strategy.”
We're going into q4 planning and it makes my brain hurt. Roadmaps existed because software was expensive to build. You needed a bunch of people. Meetings. Someone moving little boxes around Jira for three months from now. It makes no sense and I'm trying to work out what we call the replacement. Maybe just "Continuous Compilation", ideas just compile to working product. I want a list of ideas that we want to continuously compile. That's the roadmap now.
The cheapest way to figure out whether something is a good idea is often to just build the fucking thing.
Here’s how I work now. I've done this weekly over the last few months and it works. My current napkin math is that I can usually build 6 months of old-school roadmap in a week. Sometimes more. I've also hit a wall sometimes. It happens.
When we have an idea, I usually 10x the ambition and then write a prompt, not more than a page long, that basically says:
- here’s the ambitious goal
- here are a few use cases
- here’s roughly how I think we should build it in terms of where it fits into code base, design considerations, etc..
- here’s how we’ll know if it actually works
- now go fucking surprise me
Agents build all night. Not even with a crazy factory or complex agent or agents. The base models are just too good for that now.
In the morning I look at it. Ok, they usually build in a few hours. Usually some of it is great. Some of it is stupid. Some of it exposes that my original idea was wrong.
And almost every time it gives me 5 new ideas I couldn’t have planned upfront. So we throw shit out. Who cares? We learned something.
Then we change direction and send them off again. It usually takes 3 rounds before the shape appears and we've learned about the gremlins and possibilities.
95% of the time I end up building something with 10x the scope of what somebody had carefully spread across the next quarter in Jira.
“What should we put on the roadmap for next quarter?”
My brain now translates that to: “Oh, you're stuck in the 1500s”
Possible to see diffs per threads in Claude projects (beta)? @lydiahallie @amorriscode
Ali retweeted
I don't know who needs to hear this, but every headline, paragraph and image does not need to fade in as I scroll your website.
circle not matching the context window on several different chats @amorriscode idk where else to report this
Ali retweeted
AI has eaten tactical programming, so juniors need strategic experience in a low-blast-radius environment.
Here's one way to make that happen:
1. Give them responsibility over a large chunk of work
2. That work must be low stakes, but not no stakes - ideally an internal tool (AI makes these kinds of projects easy to justify)
3. Let them move fast and fail fast. Give them the same AI budgets as your senior engineers.
4. When failures happen, work with them to figure out what went wrong (learnings can also be pulled upwards into the rest of the org)
In a sentence:
Hire juniors. Give them work that matters. Watch them fail. Pick them up.
I love /grill-me by @mattpocockuk but Whenever I use it I get a list of questions and I have to specifically tell Claude to use "askuserquestions" to provide the question module thingy.
Anyone else having this issue and am I doing something wrong in the prompt?
I like @GetEnergy_ quite nice to have everything work/computer related separated from other apps
Claude Desktop doesn’t work with API accounts? None of our team members can access the app with our API subs. @amorriscode
Whenever I'm building I just use voice for all changes that I want to be made. The problem now is that Claude takes a lot of shortcuts and skips some changes. Often I need to revisit these or just memorize.
Is it better to set up tasks for everything so it never goes "missing"?
I've been loving the new built-in browser in Claude Desktop however I would love to see it work with mouse buttons for going back and forth between pages and also setting fixed viewports for mobile and desktop instead of adjusting it manually. Similar to Chrome. @amorriscode















