// edition · 2026-05-05
21 stories on AI dev tools, agents, and the coding stack — curated from the day's RSS haul by Agentic Dev's pipeline.
A developer guide outlines 11 configuration rules for CLAUDE.md files used in multi-agent Claude Code setups, addressing file collision and coordination failures that occur when multiple Claude sessions write to the same repository simultaneously.
A Dev.to article outlines 14 rules for a CLAUDE.md configuration file placed at a Python project's root to direct AI coding assistants toward idiomatic Python 3.11+ conventions, including mandatory type hints, dataclasses over plain dicts, and pytest-based testing.
GitHub CTO Vlad Fedorov stated the company scrapped a 10x capacity expansion plan in favor of a 30x one by February 2026, citing AI coding agents driving unprecedented code volume. The article argues existing software development validation pipelines — test suites, staging environments, and code ...
A tutorial published on Dev.to details how to build an internal Slack chatbot using Anthropic's Claude 3.5 Sonnet model and Slack API 2.0 Socket Mode, with a self-hosted deployment cost of $0.18 per 1,000 queries and Redis-backed rate limiting supporting up to 1,200 queries per minute.
Anthropic released Claude Managed Agents on April 8, 2026, describing it as a meta-harness with architectural changes that reduced median response latency by 60% and the slowest-5% tail by over 90%. Early adopters include Notion, Rakuten, Asana, Sentry, and Vibecode.
A solo developer building a Calendly alternative called OneSlate shipped 14 features in one day using Claude for design and strategy and Anthropic's cowork coding agent for implementation, working across three sessions totaling roughly eight hours. The app filters calendar availability by `calend...
A developer building an AI dev harness called Codens found that a QA agent generated tests for outdated code because the orchestrator agent wasn't passing it the git diff of recent changes. Adding the implementation diff as a field in the HTTP handoff between the two agents caused test scope to t...
Google added webhook support to the Gemini API, providing a push-based notification system for long-running jobs. The feature eliminates the need for polling by sending event-driven notifications when jobs complete.
General Intelligence, an 8-person startup, built its AI agent platform "Cofounder" on Vercel after migrating from Render, using AI coding agents that generate 10 PRs and 70+ commits per engineer daily across 4,000+ active branches. The company's product lets founders run business functions via AI...
Arize AI announced a partnership with Google Cloud to promote standardized AI agent telemetry using OpenTelemetry and OpenInference protocols, following Google's launch of the Gemini Enterprise Agent Platform. The initiative aims to maintain consistent trace formats across enterprise AI agent dep...
Neuron AI, a PHP framework for AI integration, added parallel branch execution to its workflow system via a new `ParallelEvent` class. The feature allows independent pipeline tasks—such as text extraction, image analysis, and metadata classification—to run concurrently rather than sequentially, r...
OpenAI published a technical overview of the infrastructure and engineering methods it uses to deliver low-latency voice AI responses at scale, covering aspects of its real-time voice systems.
OpenAI rebuilt its WebRTC stack to support real-time voice AI at global scale, enabling low-latency audio delivery and conversational turn-taking across its voice AI products.
Developers released mcp-sync, an open-source tool that manages Model Context Protocol server configurations across multiple AI code editors including Claude Desktop, Cursor, Windsurf, and VS Code from a single .mcp.json file. The tool uses three commands—export, diff, and sync—to address incompat...
Vercel open sourced "deepsec," a security scanning tool that uses AI coding agents (Claude and Codex) to identify vulnerabilities in codebases, running locally or scaling to 1,000+ concurrent Vercel Sandboxes. The tool reports a 10-20% false positive rate and follows a five-step pipeline: scan, i...
A developer and their partner released Apra Fleet, an open-source MCP server on GitHub that allows a single Claude Code session to dispatch tasks to agents running on multiple machines or in isolated local workspaces. The tool supports doer-reviewer loops within a single machine using separate fo...
Simon Willison's April 2026 newsletter covers AI model releases including Opus 4.7 and GPT-5.5, both with price increases, as well as ChatGPT Images 2.0 and Claude Mythos, alongside LLM security research topics.
IBM released the Granite 4.1 LLM family under an Apache 2.0 license in 3B, 8B, and 30B sizes. Simon Willison tested 21 quantized GGUF variants of the 3B model on SVG image generation and found no consistent relationship between model size and output quality.
A technology commentator argues that organizations adopting AI to accelerate software delivery repeat a pattern seen with Agile and DevOps, where speed was treated as the primary goal rather than faster feedback loops. The piece cites Google Docs holding 9.6% market share versus Microsoft Word's ...
Palo Alto Networks announced plans to acquire AI gateway startup Portkey for approximately $700 million, intending to integrate it into its Prisma AIRS security platform. Portkey processes trillions of tokens per month for Fortune 500 clients and supports 3,000 LLMs, MCP servers, and agents.
Google Cloud Next '26 keynotes, held at the 12,000-seat Michelob ULTRA Arena in Las Vegas, centered on a shift from generative AI to an "Agentic Era" of autonomous AI agents. Google highlighted its end-to-end stack spanning Ironwood 8th-gen TPUs, Gemini models, cloud infrastructure, and Workspace...