9 posts
Anthropic added webhooks to Claude Managed Agents. Long-running AI agents now proactively notify your app on key state changes β idle waiting for approval, outcome evaluation complete, errors. With HMAC signing, replay protection, and SDK helpers in 7 languages, this is the practical guide for developers running AI agents in production.
READ MOREAt Google I/O 2026, Gemini 2.5 Pro Deep Think mode went generally available. It scored impressively on the 2025 USAMO math competition and added MCP support to connect with the open-source tool ecosystem. Gemini 2.5 Pro now leads both the WebDev Arena and LM Arena leaderboards.
READ MOREIn May 2026, Claude Code's Hooks system received a significant upgrade. PostToolUse hooks can now intercept and replace output from any tool (not just MCP), hooks can read the current effort level via effort.level or $CLAUDE_EFFORT, and duration_ms tracks actual tool execution time. A new claude ultrareview subcommand also enables non-interactive code review from CI pipelines.
READ MOREIn May 2026, Claude Code received a massive update: Routines, /ultrareview, and Claude Opus 4.7 as the new default. Scheduled cloud agents, parallel multi-agent code review, and the xhigh effort level β an EdTech CEO analyzes what the finished form of a vibe coding tool looks like.
READ MOREIn April 2026, Anthropic introduced Ultraplan and the Monitor tool to Claude Code. Here is a look at the new collaborative development workflow β from cloud-based planning to intelligent background process monitoring.
READ MORE