#agents

Tobi Lütke: AI Agents, Better Decisions, and the Future of Work

Shopify founder and CEO Tobi Lütke joins Shane Parrish to discuss AI agents, better decision-making, and the future of work. He explains how he uses an AI council to examine his hardest decisions and why taste, judgment, and responsibility become more valuable as AI becomes more capable. They go inside Shopify’s work with River, an … The post Tobi Lütke: AI Agents, Better Decisions, and the Future of Work appeared first on Farnam Street .

Farnam Street · EN

Stageshow

Create better faux UI with agents. Avoid results often look sloppy and heavy-handed.

Sidebar · EN

OpenAI Adds iCloud Calendar and Mail Plugins and Dot Texting

OpenAI continues to add features to its ChatGPT app on a regular basis, but there are a couple of recent Apple-specific updates worth mentioning. First, OpenAI created plugins for Calendar and Mail a couple of days ago. Both features use iCloud and require you to set up an app-specific password to use them. Here’s what […]

MacStories · EN

You Own the Outcome: Product Engineering in the Age of AI

Agents are great at producing code. The valuable work left for you is deciding what should exist, how it should behave, and what you're willing to trade for it.

Kent C. Dodds · EN

How Dropbox uses MCP and Dash to close the design-to-code security gap

Using an agentic AI system to surface threat models during code review and spot gaps between security requirements and implementation.

Dropbox Tech · EN

How we used DSPy to turn AI evaluations into better responses in Dash chat

We used DSPy to improve LLM judges and optimize our chat experience, creating an evaluation-driven feedback loop that produced better outputs.

Dropbox Tech · EN

Evolving our calendar assistant Reclaim to be AI-native without starting over

How we redesigned Reclaim for AI and natural-language requests while preserving the scheduling experience people rely on.

Dropbox Tech · EN

Import AI 472: DeepMind's cheating math agents; populist AI policies; and Forethought theorizes a nightwatchman

Plus, a machine hermeneutics story

Import AI · EN

Architecting Governed, Self-Evolving AI Agents on Google Cloud

Learn how Project Chrysalis combines Google Cloud's Gemini Enterprise Agent Platform, Agent Development Kit (ADK), BigQuery, and a four-gate defense-in-depth security stack (Model Armor, Cloud KMS, Binary Authorization, and OPA) to build governed, self-evolving AI agents that remediate live production outages in 1.8 seconds.

Google Developers Blog · EN

Hill-Climbing Agent Quality with Agents CLI Evaluation

This post walks through the Agents CLI evaluation loop for systematically improving agent performance through continuous testing and grading. It demonstrates how to catch prompt regressions, evaluate model backend swaps using side-by-side trace comparisons, and automate evaluation passes. Developers will also learn how to integrate nightly scheduled runs with threshold-based alerting to track quality over time.

Google Developers Blog · EN

How well do agents use test and verification techniques?

We previously noted that, while it's easier than ever to hit a particular quality bar by having coding agents use effective test techniques, software quality seems to be getting worse , indicating that whatever defaults developers are using may not work very well. Here, we test if simple instructions to agents to use particular techniques or libraries improve implementation correctness, as a kind of test to see how effective agents are when guided by someone with no expertise in testing who's maybe heard that you should apply certain techniques or use certain libraries. We'll re-use the Zstd i

Dan Luu · EN

WorkOS: Let Agents Sign Up for Your App Without a Browser

My thanks to WorkOS for sponsoring last week at DF. An agent can’t click through a signup page built for humans, so give it something it can read instead. Publish an auth.md file and agents register themselves without ever touching a browser login, and the user never gets pulled out of what they were doing. With WorkOS auth.md, enroll in the dashboard and AuthKit publishes the file. Agents read it, register, and get scoped, short-lived credentials you control. Make your app agent-ready today . ★

Daring Fireball · EN