The Agentic Engineer Podcast

Issue #11: OpenAI models, Codex, and Managed Agents land on Amazon Bedrock. Model exclusivity is officially dead. T-MAP red-teams frontier agents at 57.8% attack success rate using multi-step tool-use manipulation. AgentCore Optimization ships the continuous agent quality loop. DeepClaude runs Claude Code's agent loop at 17x less cost. Cloudflare + Stripe lets agents buy infrastructure autonomously. Matt Pocock's skills repo hits 57K stars. Google renames Vertex AI to Gemini Enterprise Agent Platform. And shadow agents outnumber humans 45:1 in enterprise. Subscribe to the newsletter: https://theagenticengineer.waltsoft.net YouTube: https://www.youtube.com/@theagenticengineerpod Twitter: https://x.com/natearcher_ai

Issue #10: GPT-5.5 reclaims the agentic crown with 82.7% on Terminal-Bench 2.0 and fewer tokens per task. Stanford's SWE-chat study reveals 44% of agent-produced code gets thrown away. ToolSimulator from Strands Evals SDK lets you test agents without live APIs. NVIDIA exposes AGENTS.md injection as a supply chain attack vector hiding in every coding agent. Plus: Bedrock AgentCore, Deep Research Max, context-mode, and the Agent Index. Subscribe to the newsletter: https://theagenticengineer.waltsoft.net YouTube: https://www.youtube.com/@theagenticengineerpod Twitter: https://x.com/natearcher_ai

Issue #9: Claude Opus 4.7 ships differential capability reduction as the first production cyber safeguard baked into model weights. Vercel breached through an AI tool's OAuth scope. Spring AI SDK for Bedrock AgentCore goes GA for Java. GTA-2 paper proves your agent harness matters more than your model. And CMU documents 6 million fake GitHub stars across the AI ecosystem. Subscribe to the newsletter: https://theagenticengineer.waltsoft.net YouTube: https://www.youtube.com/@theagenticengineerpod Twitter: https://x.com/natearcher_ai

Issue #8: Anthropic ships Managed Agents, UC Berkeley breaks every major AI benchmark, AWS Agent Registry launches in preview. Plus Cursor 3, Copilot Rubber Duck, Cloudflare Agent Cloud, and the hot take on exploitable benchmarks. Subscribe to the newsletter: https://theagenticengineer.waltsoft.net YouTube: https://www.youtube.com/@theagenticengineerpod Twitter: https://x.com/natearcher_ai

Anthropic published the blueprint for multi-hour coding agents. GitHub shipped /fleet for parallel multi-agent coding. Amazon Nova Act MCP gives your agent a browser with one install. Plus: Gemma 4 goes agentic on-device, Oh-My-Codex hits 17K stars, and LiteLLM fixes 3 CVEs post-breach. Subscribe to the newsletter: https://theagenticengineer.waltsoft.net YouTube: https://www.youtube.com/@theagenticengineerpod Twitter: https://x.com/natearcher_ai

This week: JetBrains Central launches an open control plane for coding agents. ARC-AGI-3 drops and frontier AI scores below 1%. Claude Mythos gets leaked via CMS misconfiguration. MolmoWeb beats GPT-4o at 8B parameters. AI Scientist v2 passes peer review. 177K MCP tools show agents shifted from reading to writing. AWS Labs ships Agent Plugins for Claude Code and Cursor. Microsoft merges Semantic Kernel and AutoGen. And Copilot literally put an ad in someone's pull request. Subscribe to the newsletter: https://theagenticengineer.waltsoft.net YouTube: https://www.youtube.com/@theagenticengineerpod Twitter: https://x.com/natearcher_ai

This week: OpenCode crosses 120K GitHub stars and 5M monthly devs. Claude Code ships Channels for event-driven coding agents. Hindsight hits #1 on LongMemEval for agent memory. Plus: Flash-MoE runs 397B params on a MacBook, NVIDIA open-sources NemoClaw, and our hot take on why memory is the real moat. Subscribe to the newsletter: https://theagenticengineer.waltsoft.net YouTube: https://www.youtube.com/@theagenticengineerpod Twitter: https://x.com/natearcher_ai

This week: An autonomous agent hacked McKinsey's AI platform in 2 hours with no credentials and no human in the loop. Amazon mandates senior engineer sign-off on all AI-assisted code. Claude gets 1M context at standard pricing. METR proves SWE-bench scores are misleading. Agent Browser Protocol freezes JavaScript for deterministic agent browsing. George Hotz says stop running 69 agents. Subscribe to the newsletter: https://theagenticengineer.waltsoft.net YouTube: https://www.youtube.com/@theagenticengineerpod Twitter: https://x.com/natearcher_ai

This week: LangChain releases Deep Agents, an MIT-licensed coding agent built on LangGraph that works with any model. GPT-5.4 ships native computer use (75% OSWorld score). Karpathy drops autoresearch for autonomous ML experiments. Claude finds 22 Firefox zero-days in two weeks. Anthropic's labor market study shows junior hiring slowing. Alibaba OpenSandbox provides agent isolation infrastructure. SWE-CI benchmark tests long-term code maintenance. Shannon AI pentester only reports verified exploits. And the Clinejection attack: how a GitHub issue title compromised 4,000 developer machines. Subscribe to the newsletter: https://theagenticengineer.waltsoft.net YouTube: https://www.youtube.com/@theagenticengineerpod Twitter: https://x.com/natearcher_ai

This week: Researchers analyzed 2,430 Claude Code responses and mapped the default developer stack. Anthropic gets designated a supply-chain risk AND drops its safety pledge in the same week. Mercury 2 hits 1,009 tokens/sec via diffusion. Steerling-8B explains every token it generates. CLIHub cuts MCP token costs by 94%. Plus the Agent Index and a hot take on the end of the "responsible AI" era. Subscribe to the newsletter: https://theagenticengineer.waltsoft.net YouTube: https://www.youtube.com/@theagenticengineerpod Twitter: https://x.com/natearcher_ai

This week: Mercury 2's diffusion-based decoding hits 1,000+ tokens/sec. Emdash runs 21 coding agents in parallel. Cloudflare ships a full agent hosting SDK. Hugging Face standardizes agent skills. And why "agentic" just became an infrastructure category. Subscribe to the newsletter: https://theagenticengineer.waltsoft.net YouTube: https://www.youtube.com/@theagenticengineerpod Twitter: https://x.com/natearcher_ai