エピソード

  • Issue #16: Agentic Commerce Goes B2B — Amazon Shopping Agent, Perplexity 87% Time Savings, Ladybird Kills PRs

    Issue #16: Agentic Commerce Goes B2B — Amazon Shopping Agent, Perplexity 87% Time Savings, Ladybird Kills PRs
    2026/06/10
    Issue #16 of The Agentic Engineer Podcast. Amazon licenses its agentic shopping assistant to outside retailers — Kate Spade first, 60-day deploy, $12B internal revenue drove the decision. Perplexity publishes production data showing autonomous agents cut knowledge work time 87% and expand scope of what users attempt. DeepSeek V4 Pro beats GPT-5.5 Pro on precision. Claude Opus 4.8 and Fable 5 land on AWS Bedrock. AWS MCP Server gets cross-account support. Bedrock Mantle Console redesigns the developer experience. And Ladybird kills public PRs because AI-generated contributions broke the effort-equals-good-faith assumption.
    続きを読む 一部表示
    10 分
  • Issue #15: The Plugin Wars Begin — Anthropic Cowork Plugins, OpenSearch Next-Gen, Human-in-the-Loop

    Issue #15: The Plugin Wars Begin — Anthropic Cowork Plugins, OpenSearch Next-Gen, Human-in-the-Loop
    2026/06/03
    Issue #15 of The Agentic Engineer Podcast. Anthropic open-sources 11 knowledge-work plugins for Claude Cowork in the simplest format possible: markdown and JSON. OpenSearch Serverless Next-Gen kills the $300/mo minimum with true scale-to-zero vector search. Self-improving agents go from 25% to 86% accuracy in production. And the hot take: human-in-the-loop is a liability when users approve 93% of prompts without reading them.
    続きを読む 一部表示
    17 分
  • Issue #14: Mythos 10K Vulns, CodeGraph, Constraint Decay, AI Slop Issues

    Issue #14: Mythos 10K Vulns, CodeGraph, Constraint Decay, AI Slop Issues
    2026/05/27
    Issue #14 of The Agentic Engineer Podcast. Anthropic's Mythos Preview found 10,000+ critical vulnerabilities in 30 days across 50 Glasswing partners. A new paper proves coding agents collapse in convention-heavy frameworks like Django. CodeGraph cuts agent costs 35% with pre-indexed knowledge graphs. And AI-generated slop issues are poisoning open source repos.
    続きを読む 一部表示
    18 分
  • Issue #13: TanStack Attack, AWS Agent Orchestrator, FORGE Memory

    Issue #13: TanStack Attack, AWS Agent Orchestrator, FORGE Memory
    2026/05/20
    Issue #13 of The Agentic Engineer Podcast. TanStack npm supply chain attack compromises OpenAI code-signing certs, AWS CLI Agent Orchestrator runs multiple coding agents in parallel via MCP, and FORGE evolves agent memory through population broadcast.
    続きを読む 一部表示
    17 分
  • Issue #12: Agents That Spend Money

    Issue #12: Agents That Spend Money
    2026/05/14
    Issue #12: Amazon Bedrock AgentCore Payments launches with Coinbase and Stripe, giving agents wallets and spending authority. The AWS MCP Server goes GA with 15,000 API operations in 3 tools. TraceFix formally verifies multi-agent coordination via TLA+, cutting deadlock from 31% to 14%. OpenAI Symphony open-sources work management for coding agents. Mythos finds a real curl CVE. Claude Platform on AWS goes GA. DeepSeek-TUI explodes to 24K stars. Anthropic ships vertical financial agents. And James Shore proves AI doubles your maintenance debt too. Subscribe to the newsletter: https://theagenticengineer.waltsoft.net YouTube: https://www.youtube.com/@theagenticengineerpod Twitter: https://x.com/natearcher_ai
    続きを読む 一部表示
    16 分
  • Issue #11: AWS + OpenAI: Model Exclusivity Is Dead

    Issue #11: AWS + OpenAI: Model Exclusivity Is Dead
    2026/05/06
    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
    続きを読む 一部表示
    18 分
  • Issue #10: GPT-5.5 Reclaims the Agentic Crown

    Issue #10: GPT-5.5 Reclaims the Agentic Crown
    2026/04/29
    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
    続きを読む 一部表示
    15 分
  • Issue #9: Claude Opus 4.7 Ships Cyber Safeguards to Production

    Issue #9: Claude Opus 4.7 Ships Cyber Safeguards to Production
    2026/04/22
    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
    続きを読む 一部表示
    15 分