// edition · 2026-04-15
31 stories on AI dev tools, agents, and the coding stack — curated from the day's RSS haul by Agentic Dev's pipeline.
Anthropic launched "routines" for Claude Code, allowing automated tasks to run on schedules, via API calls, or GitHub webhooks on Anthropic's cloud infrastructure, replacing manual GitHub Actions setups for tasks like issue triage and smoke testing.
Anthropic released a redesign of its Claude Code desktop app featuring a sidebar for multi-project session management, an integrated terminal pane, a side chat function (Ctrl+;) for context-aware queries, and consolidated model and effort controls.
Anthropic released a redesigned Claude Code desktop app with an integrated terminal, improved diff viewer, side chat functionality, and rearrangeable interface panes for managing multiple coding sessions simultaneously.
HTTP 529 "overloaded_error" responses from Claude's API indicate insufficient model capacity rather than per-key rate limits; developers should respect retry-after headers and implement exponential backoff rather than immediate retries, which can worsen fleet overload.
Claude's agentic loop operates as a repeated cycle where the model reads the conversation and tool definitions, then decides whether to call a tool or respond; the model selects tools via a forward pass based on tool descriptions and conversation context, not rules or decision trees.
An article describes five workflow patterns for Claude Code: Sequential (human-verified step-by-step), Operator (single agent with defined permissions), Parallel (multiple independent tasks), Teams (role-separated agents), and Autonomous (minimal human involvement). Each pattern trades control fo...
A developer outlined four practices to reduce technical debt when using AI coding assistants: defining completion criteria before prompting, performing independent code verification, documenting implicit project knowledge, and breaking work into small well-defined units.
MemoryLake launched a persistent memory layer for AI agents that retains information across sessions and works with multiple AI platforms, featuring multimodal document parsing, conflict resolution, and three-party encryption for data privacy.
A developer using Claude as a coding agent observed patterns of shallow reasoning and contradictory suggestions that matched documented performance declines in a 6,852-session analysis. They addressed the issue by converting their project wiki from a knowledge base into behavioral constraints for...
A developer described a workflow that uses AI to generate product requirements and issues from detailed plans, emphasizing upfront thinking and explicit specification over rapid implementation to maintain code clarity and maintainability.
Observability platforms are evolving into AI auditing tools to monitor autonomous AI workloads in production, as traditional monitoring systems fail to track AI agent decisions and code generation at enterprise scale.
Anthropic released documentation for Claude Code Routines, a feature within its Claude coding platform available at code.claude.com.
GitHub launched Season 4 of its free Secure Code Game, focusing on security vulnerabilities in autonomous AI agents that can browse the web, call APIs, and act independently. Over 10,000 developers have participated in previous seasons as OWASP identifies agent-specific risks like goal hijacking ...
A developer built a trading signal API that charges AI agents per-call micropayments in USDC via the x402 protocol, eliminating the need for traditional API key signup; signals are generated using RSI, ADX, MACD, and volume indicators with prices ranging from $0.005 to $0.01 per request.
A developer used Claude AI with SiteAudit MCP to audit five major Spanish websites and identified technical issues including slow load times at El Corte Inglés (LCP 4.2s), missing security headers at Banco Santander, render-blocking resources at El País, accessibility gaps at Zara, and mixed resu...
Suga switched from last-write-wins conflict resolution to Zero, a real-time sync engine from Rocicorp, after developers lost work when simultaneous edits overwrote each other. The system uses local SQLite databases on clients that synchronize with a PostgreSQL server, with server-side conflict re...
A beginner guide instructs ChatGPT users how to set up Claude, including downloading the desktop app, creating a free account, importing chat history, organizing work into Projects, and using features like Chat mode and Cowork for file-based tasks.
Google introduced Skills, a Chrome feature that allows users to discover, save, and reuse AI workflows with one click.
Google launched a Chrome feature called "Skills" that lets users save AI prompts and reuse them across multiple webpages with a single click, eliminating the need to re-enter the same Gemini commands repeatedly.
Agent-dispatch is an MCP server that allows Claude Code agents to delegate tasks to specialized agents in other project directories while maintaining isolation of credentials, configs, and context. The tool provides multiple dispatch methods including one-shot tasks, multi-turn conversations, par...
MCP servers require more setup but enable advanced features like code execution and multi-tool reasoning chains, while custom GPTs are simpler to create and distribute to consumers but limited to basic API calls and file operations. MCP servers offer better monetization potential but require deve...
Rod Johnson, creator of the Spring Framework, launched Embabel, an Apache-licensed agentic AI framework for Java built on Spring Boot, at Microsoft's JDConf conference to address enterprise predictability challenges in large language model applications.
The UK's AI Security Institute evaluated Anthropic's Claude Mythos Preview and found it autonomously completed a 32-step corporate network takeover simulation, marking the first AI model to execute such a full multi-stage cyberattack simulation. The model showed improved performance in capture-th...
The Pragmatic Engineer surveyed 900+ software engineers on AI tool usage and found that companies typically pay $100-200/month per engineer for AI coding tools, with 30% hitting usage limits; impacts vary by engineer type, with "builders" dealing with more low-quality output while "shippers" see ...
GitHub introduced Code Security Risk Assessment, a free tool that scans up to 20 repositories using CodeQL to identify vulnerabilities by severity and language, available to organization admins and security managers at no cost.
Kumo announced KumoRFM-2, a foundation model for relational databases that accepts plain-English queries and outperformed supervised machine learning models by 5% on Stanford's RelBench benchmark and beats AWS AutoGluon on enterprise benchmarks, scaling to over 500 billion rows of data.
The UK's AI Safety Institute found that Claude Mythos discovers more security vulnerabilities with increased computational spending, creating an economic model where system security depends on outspending attackers on vulnerability analysis.
Vercel made anomaly alerts generally available for Observability Plus users, enabling real-time detection and alerts for unusual application metrics and error patterns. The feature integrates with Vercel Agent for automated investigation and supports notifications via dashboard, email, Slack, or ...
Cloudflare launched Mesh, a private networking service that connects internal resources across multiple cloud environments without exposing them to the public internet. The service targets AI agents that require secure access to company databases and internal APIs.
Datasette pull request #2689 replaces token-based CSRF protection with Sec-Fetch-Site header protection, removing the need for hidden CSRF token form inputs and simplifying the security implementation based on research by Filippo Valsorda and Go 1.25.
OpenAI released GPT-5.4-Cyber, a model variant fine-tuned for defensive cybersecurity work, and expanded its Trusted Access for Cyber program allowing identity-verified users reduced-friction access to security tools via government ID verification through Persona.
Free daily email. Every story you just read, in your inbox at 6 AM ET.