Loop
We track 18 posts about Loop from 17 engineering blogs. Most active: Ray Wenderlich, Armin Ronacher, Expedia. Latest post: Oct 29, 2026.
Companies writing about Loop
Recent posts
Catching Bugs Before They Land: JiTTesting’s Human-on-the-Loop Approach at Full Scale (opens on the source site)
Facebook ·
Over the last year we’ve been sharing our work leveraging large language models to catch bugs on the fly — a novel approach we call Catching Just-in-Time Tests (JiTTests). Now, we’re sharing the results and positive impact we’ve seen with Catching JiTTests deployed into production. Our paper, “Just-in-Time Catching Test Generation at Meta,” fully details [...] Read More... The post Catching Bugs Before They Land: JiTTesting’s Human-on-the-Loop Approach at Full Scale appeared first on Engineering at Meta.
Beyond the Prompt: Engineering the Loop for Software Change at Scale (opens on the source site)
Expedia ·
Expedia Group Technology — EngineeringHow Expedia Group compressed an estimated two years of iOS modularization into about three months while shipping weeklyPhoto by Queensland, Australia on UnsplashThe first wave of coding assistants trained us to think in prompts: describe a task, generate code, review the result.Reusable skills made that interaction more repeatable. They packaged instructions, conventions, and tools so an agent could perform a familiar task more consistently.The hard part of large-scale engineering sits between code changes: hidden dependencies, incomplete context, build…
JavaScript Event Loop Explained: How to Trace Queues and Debug Async Code (opens on the source site)
Predict async execution order, identify microtask starvation, and compare browser and Node.js event loop behavior using step-by-step queue trace tables and annotated code snippets. Continue reading JavaScript Event Loop Explained: How to Trace Queues and Debug Async Code on SitePoint.
The Agentic Code Review Loop (opens on the source site)
An agentic code review loop where every developer fires their own AI review skill at a pull request, the author's agent answers, and a scorecard rates each.
From Training to Production, NVIDIA and CoreWeave Close the Loop on Agentic AI (opens on the source site)
Nvidia ·
Building on nearly a decade of co-engineering, CoreWeave has built NVIDIA compute, networking and software into a cloud purpose-built for AI that’s still returning on investment across multiple generations of deployment. Now, CoreWeave is bringing the next generation of NVIDIA infrastructure to production. At CoreWeave Fully Connected, running this week in San Francisco, CoreWeave announced […]
Is Your “Human-in-the-Loop” Actually Slowing You Down? Here’s What We Learned (opens on the source site)
In the rush to adopt AI and automation, many teams implement human-in-the-loop (HITL) frameworks. They believe that involving a person in the process solves the problems with reliability, quality, and trust. But as we’ve learned from real engineering workflows and integrations, the story isn’t that easy. In some contexts, humans-in-the-loop do improve outcomes, but in others, they can unintentionally become bottlenecks that limit speed, scalability, and innovation. In this post, we’ll analyze when human-in-the-loop is truly valuable, when it slows systems down, and how to strike the right…
Kodebits Day 97: Enumerated Loop [FREE] (opens on the source site)
What is the output? let items = ["A", "B", "C"] for (i, v) in items.enumerated() { print("\(i):\(v)") } Try it in the online Swift Playground → [spoiler title="Solution"] Answer: 0:A 1:B 2:C Explanation: enumerated provides both index and value when iterating collections. [/spoiler] Further Reading Swift Apprentice Fundamentals Swift Cookbook
Kodebits Day 92: Collection For Loop [FREE] (opens on the source site)
What is the output? void main() { final nums = [1, 2, 3]; final out = [ for (var n in nums) n * 2 ]; print(out.length + out[0]); } Try it in the online Dart Playground → [spoiler title="Solution"] Answer: 5 Explanation: A collection for builds a new list by transforming each source item. [/spoiler] Further Reading Programming in Dart: Fundamentals Programming in Dart: Control Flow & Collections
TDD inside the agent loop - theater or actual value? (opens on the source site)
My colleagues at Thoughtworks tend to be big fans of Test-Driven Development, and many people in the industry advocate telling LLM agents to use TDD when building software. Birgitta Böckeler was curious if this really makes a difference, so conducted a few experiments. more…
Beyond Human-in-the-Loop: Designing AI Oversight That Actually Scales (opens on the source site)
Haptik ·
As enterprises rapidly embrace AI Agents and Voice AI Agents, one question that consistently arises during customer evaluations, boardroom discussions, and compliance reviews is "Where is the human in the loop?" It’s a fair question. Human oversight has become a cornerstone of trustworthy AI, reinforced by emerging regulations, governance frameworks, and growing expectations around accountability. But there is a practical challenge that organizations rarely discuss. Imagine an enterprise AI Voice Agent handling hundreds of thousands of customer conversations every day. Each interaction…
Sidekick's continual learning loop (opens on the source site)
Shopify ·
How we compress production failures into model weights every day, beat frontier-model quality, and cut serving costs 96%.
Observations From Building a PR Review Loop (opens on the source site)
Building my own agent has been fun. Sure, I could have opted for an off-the-shelf solution, but I wanted control. The ironic part is that I'm using that control to offload more control to the agent. Recent experiments have included letting the agent work on itself. Super meta, but didn't quite go as planned considering the guardrails I have in place around the size of PRs. Agent work tends to be heavy lifting, whereas most project work is small and fits nicely inside the constraints. Part of the issue there is that the PR reviewer would constantly request changes on those larger PRs. Changes…
Claude Code Routines: A Third Way Beyond /goal and /loop (opens on the source site)
There's a third way to automate Claude Code, and unlike /goal and /loop, it doesn't need your laptop open at all. Anthropic just shipped routines: cloud-hosted automations triggered by a schedule, an API call, or a GitHub event. Read more
Own the Outer Loop (opens on the source site)
Engineers need to own the outer loop, the accountability for these systems. A written version of my AI Engineer World's Fair 2026 closing keynote: quality, verdict, and answerability, the three hidden costs of delegation, and building software factories you can stand behind.
Closing the loop: Evaluating and improving Replit Agent at scale (opens on the source site)
Replit ·
Most Replit Agent users start with an idea. They describe the goal in natural language — without a repo, test suite, or chosen framework — and expect the agent to turn it into a functioning app. The result might be a website, slide deck, mobile app, several connected artifacts, or something else entirely. Vibe coders are not usually checking diffs or test output. Success for Replit Agent is deceptively simple: the app should work when users click around. That changes the job of evaluation. A single score can help with a specific shipping decision, but it cannot tell us, week over week,…
The New Security Control Point: Governing AI Agents Inside the Execution Loop (opens on the source site)
Snyk ·
AI agents introduce security risk through the actions they take, not just the code they produce. Learn how agent behavior governance helps teams observe, steer, and block risky actions in real time.
The Coming Loop (opens on the source site)
I don’t prompt Claude anymore. I have loops running that prompt Claude and figuring out what to do. My job is to write loops. — Boris Cherny Over the last months I have watched more and more people build something on top of coding agents that feels meaningfully different from just using a coding agent. Some of this happens on top of Pi which is cool to see for sure! The pattern is the same everywhere though: work is put into a queue of sorts, a machine picks it up, attempts it, stops, and then some harness decides whether that was actually the end. If not, the harness continues the same…
Frequently Asked Questions from Strange Loop 2023 (opens on the source site)
Latacora ·
The last Strange Loop conference was held September 21-22, 2023 at St. Louis Union Station. The conference is targeted towards developers; the speakers are often sharing their knowledge on new and inventive ways to use technology. At our sponsor booth at Union Station, attendees asked two (okay, three) questions most often: What is Latacora? Your name is on the lanyards, and I’m curious to know what you do. Why sponsor Strange Loop? Can I take a plant? The first one isn’t hard for the folks from our team: Latacora is a consultancy that bootstraps security for startups. We have a team of…
Related topics
This page is generated automatically from the engineering blogs we follow. Every post links to its source, where it was published. See all sources.