lookingfortone

[Los Angeles Lakers @Lakers]

Thank you, LeBron 💜💛

[Andrew Ng @AndrewYNg]

“Loop engineering” is a hot buzzphrase after mentions of it by Boris Cherny (Claude Code’s creator) and Peter Steinberger (OpenClaw's creator) went viral on social media. Loops are now a key part of how we get AI agents to iterate at length to build software. In this letter, I’d like to share my 3 key loops, shown in the image below, for building 0-to-1 products. These loops guide not just how I build software, but also how I decide what software to build.

Agentic coding loop: Given a product specification and optionally a set of evals (that is, a dataset against which to measure performance), we can have an AI agent write code, test its work, and keep iterating until the code is bug-free and meets its specification. This idea of closing the loop took off around the end of last year, and it has been a game changer in enabling coding agents to work longer productively without human intervention. For example, over the weekend, I was building an app for my daughter to practice typing, and my coding agent could easily work for around an hour, using a web browser to check what it had built multiple times before getting back to me, without needing my intervention.

The engineering loop executes quickly. Every few minutes, the coding agent might build and test a new version of the software. I hear frequently from developers who are finding new ways to engineer more effective engineering loops. This is an active area of invention!

Developer feedback loop: In this loop, a developer examines the current product and steers the coding agent to improve it. Last year, a lot of developers (including me) were acting as the QA (quality assurance) function for our coding agents, manually finding bugs and then asking the agent to fix them. But with coding agents much more able to test their own code, the amount of time we need to spend on this function has decreased significantly. This allows us to make higher-level product decisions, such as what key features to offer, where the UI needs improvement, and so on.

The developer-feedback loop operates over time intervals between tens of minutes and hours — that's how frequently a developer might review a product and give feedback. In the case of the typing app, I changed my mind a few times about the visual design, what cat costumes she can unlock as she learns (she loves cats), and the user flow for a grown-up to log in and steer the child's learning experience.

When a developer has a clear vision for what to build, it is still a lot of work to translate that vision into a specification for a coding agent to implement. Further, after the developer has seen an implementation, they might update (or perhaps clarify) the spec to steer it toward what they want. If you find that the system repeatedly runs into certain problems, building a set of evals for the agent becomes useful.

AI-native teams are increasingly using AI to help shape product direction, for example, automating the gathering and analysis of usage data, summarizing written and verbal customer feedback, or carrying out competitive analysis. However, for pretty much all the products I’m involved in, I see humans as having a significant context advantage over current AI systems — we know a lot more than the AI system about the users and the context the product has to operate in — and thus humans play a critical role. Many people describe this human contribution as “taste,” but I prefer to think of it as humans having a context advantage, since that gives us a clearer path to helping AI systems get better. This also speaks to why this step can’t be automated: So long as the human knows something the AI does not, human-in-the-loop is needed to to inject that knowledge into the system.

External feedback loop: This includes a wide range of tactics like asking a few friends for feedback, launching to alpha testers, or putting the code into production with A/B testing. These tactics are usually slow, rarely taking less than hours and sometimes taking days or even weeks. This data informs the developer vision, which in turn continues to drive the detailed product spec, which in turn drives the coding agent.

With coding agents speeding up software development, more engineers are starting to play a partial product management role. For many engineers who are growing into this role, the hardest part is shaping the product vision and striking a balance between building (bridging the gap between vision and spec) and getting user feedback to evolve the vision. It is important to do both!

I will write more about how to do this in future posts, but for now, I find it encouraging that engineers are playing an expanded role (just as product managers and designers now do more engineering).

[Original text: The Batch]

[Anatoli Kopadze @AnatoliKopadze]

Spotify Chief Architect, Niklas Gustavsson:

"Once we implemented loops in our workflow, our agent success rate went from 20-30% to 80%."

26 minutes with Claude Code creator Boris Cherny on how Spotify runs AI agents across 20 million lines of code.

Today 73% of their code is written by AI, most merged without a human ever seeing it.

The model matters less than the loop you build around it.

Watch it, then read the full guide on building loops below.

[Codez @0xCodez]

https://t.co/eJB3TgyJwV

[Movez @0xMovez]

Ex-Google engineer explained AI agent loops, harness, evals in 20 minutes - better than 500$ courses.

trace every run → judge it with an LLM → diagnose → fix → ship.

That loop is how agents self-improve over time.

Agent loops + memory + harness + evals - thats the stack.

Watch it, then save the framework below.

[lookingfortone @lookingfortone]

@RainInAshes_x 你回来了

[lookingfortone @lookingfortone]

@RainInAshes_x 巧了，我也有

[lookingfortone @lookingfortone]

@toni_tonirl @Echinanews Actually, at that time, our Han race also thought of the Mongolians as invaders too; they conquered not only mainland China but also Central Asia and almost arrived at Europe.

[lookingfortone @lookingfortone]

@konsolitus @harukaawake Japan commits tens of millions deaths in China, but you as a japanese school staff still think China is evil, so you mean chinese derserve death? that is the how japan apologize way? You never think Japan made wrong

[lookingfortone @lookingfortone]

@liarminjoo @harukaawake If some Germans do this for Israel flag? This is how the Japanese apologize.

[lookingfortone @lookingfortone]

@unityEA108 I think most Chinese empathize with the separation in Korea. And I know one tenth of Chinese Korean work and live in south korea too

[lookingfortone @lookingfortone]

@alakebythesea @CollinSLKoh Wiki: The population in Tibet in 1945 was around 1 million.

[lookingfortone @lookingfortone]

@ViewsOfChris How Japan and Germany apologize

[lookingfortone @lookingfortone]

@anaknipajaglas @OopsGuess What do you mean? Japan invaded China in 1937. This picture was taken in 1989; Do you mean Chinese deserve the punishment for die more than 10 millions people?

[lookingfortone @lookingfortone]

Why Chinese and Koreans say Japan never officially apologized for WWII

[lookingfortone @lookingfortone]

@lulumain2025 @BeijingDai America being No.1, Singaporeans have benefited from it for decades, and so has China in the beginning. But the Chinese have the right to live a better life like you, Singaporean. China is a country with 1.4 billion people; we have to develop to promise a better life.

[lookingfortone @lookingfortone]

@lulumain2025 @BeijingDai China had been No.1 for thousands of years, way more than America exists. Do you really know history? Do you know that in the past, surrounding countries donated tributes, getting back times more than their tributes?

[lookingfortone @lookingfortone]

@russianblue2009 @MsMelChen It's an invader's arrogant accent. What you mean is that though I have bullied you, it has been passed long time, so let's go. But, for mainland Chinese and the government, though 80years passed, China never recovered from the outcome of the war, there is still one foot left.

[lookingfortone @lookingfortone]

@thewaitsmusic @ShangguanJiewen @hunterstyler I'm from Changsha, I think Changsha is tier 2 city, and we only classified cities into tier 1, 2, 3 ect

[lookingfortone @lookingfortone]

Network Earth https://t.co/yBcFgwhcTP via @YouTube

such research is not only meaningful but more beautiful too.