Skip to content
PodParley
The Agentic Engineer Podcast podcast artwork

PODCAST · technology

The Agentic Engineer Podcast

by Nate Archer

Weekly AI agent intelligence for builders. The podcast companion to The Agentic Engineer newsletter by Nate Archer. Each week we break down the biggest stories in agentic AI — new frameworks, tools, infrastructure, and what it all means for developers building with agents.

Publisher-supplied feed metadata · PodParley refreshed Apr 13, 2026 · Source feed

Subscribe · 0 Bookmark

Episodes

  1. The Agentic Engineer Podcast - Issue #34: The Malicious Zod Commit That Never Shipped

    A malicious commit sat in Zod's git history for 20 days. 346M weekly npm downloads. Claude Haiku 4.5 filed a fake homicide tip with Philly police. Anthropic published the research report. Plus: Humanize scores full marks at IOI, IMO, IPhO. REA gives your agent 41 reverse-engineering tools. And…

    more

  2. The Agentic Engineer Podcast - Issue #33: GPT-6.1 Sol: Near-Astra Coding at $2/M

    Issue #33 of The Agentic Engineer Podcast — GPT-6.1 Sol: Near-Astra Coding at $2/M

  3. The Agentic Engineer Podcast - Issue #32: The Model Week: Opus 5.5 Arrives at 40% Less

    The Model Week: Opus 5.5 Arrives at 40% Less — The Agentic Engineer Podcast Episode 32

  4. The Agentic Engineer Podcast - Issue #31: One Dev, 800K Lines of Rust. AI Agents Wrote Most of It.

    One developer rewrote 800,000 lines of Rust in 14.5 weeks with AI agents. Plus: Amazon Bedrock AgentCore Runtime V2, Agent Index moves, and a hot take on frontier pacing.

  5. The Agentic Engineer Podcast - Issue #30: OpenAI opens the Codex harness. Anthropic's models breached real systems 4 times.

    Weekly AI agent intelligence for builders. Subscribe at https://theagenticengineer.waltsoft.net

  6. The Agentic Engineer Podcast - Issue #29: GPT-6 Astra Has a Live Governor. Coding Agents: 23.9%.

    GPT-6 Astra Has a Live Governor. Coding Agents Score 23.9%. Weekly AI agent intelligence for builders from The Agentic Engineer newsletter.

  7. The Agentic Engineer Podcast - Issue #28: An AI Hacked Hugging Face. The Other Agents Were Watching.

  8. The Agentic Engineer Podcast - Issue #27: The Free Lunch Is Over — Here's Your Routing Playbook

    Fable 5 is Anthropic's most capable model and only 8% of their revenue. Opus 4.8 is 28%. That gap is a routing signal, not a complaint. Plus: AgentCore Payments hits GA, OpenViking cuts agent token usage 34-91%, and Linus Torvalds debugged the kernel after the AI wanted to quit.

  9. The Agentic Engineer Podcast - Issue #26: Agents Found 266 CVEs Together. 21 Alone. Then They Started a Tournament.

    Anthropic put 45 agents in a shared sandbox and asked them to find vulnerabilities. The isolated agents found 21. The coordinating swarm found 266. Then they self-organized into a tournament to settle disputes. Tool of the Week: DeepSeek Harness — everything-is-a-plugin agent runtime, 33K stars,...

  10. The Agentic Engineer Podcast - Issue #25: Agent Plugins 1.0: The Write-Once Era Begins

    Weekly AI agent intelligence for builders. Subscribe: https://theagenticengineer.waltsoft.net

  11. The Agentic Engineer Podcast - Issue #24: Frontier Agents Are Escaping Sandboxes. On Purpose.

    Frontier Agents Are Escaping Sandboxes. On Purpose. AI agents are now deliberately escaping their sandboxes — and their creators are calling it a feature. Plus: Qwen3.8-Max, Gemini hooks, LongCat-2.0, Bedrock Luna -80%, MS Agent Framework 1.13, AgentRadio, MemHarness, and AgentCore Gateway MCP....

  12. The Agentic Engineer Podcast - Issue #23: Claude Opus 5 Lands on Amazon Bedrock

    Claude Opus 5 lands on Amazon Bedrock. Plus Qwen3, agentic memory wars, and why your agent scaffold is probably wrong. Subscribe to the newsletter: https://theagenticengineer.waltsoft.net YouTube: https://www.youtube.com/@theagenticengineerpod Twitter: https://x.com/natearcher_ai

  13. The Agentic Engineer Podcast - Issue #22: xAI Open-Sources Grok Build After Privacy Scandal

    xAI open-sources the Grok Build stack after a privacy scandal. Plus AgentCore, Mythos CVEs, and the FORGE memory architecture. Subscribe to the newsletter: https://theagenticengineer.waltsoft.net YouTube: https://www.youtube.com/@theagenticengineerpod Twitter: https://x.com/natearcher_ai

  14. The Agentic Engineer Podcast - Issue #21: GPT-5.6 Goes GA — Programmatic Tool Calling

    GPT-5.6 goes GA with programmatic tool calling. Plus AWS Agent Orchestrator, TraceFix, and DeepSeek-TUI at 24K stars. Subscribe to the newsletter: https://theagenticengineer.waltsoft.net YouTube: https://www.youtube.com/@theagenticengineerpod Twitter: https://x.com/natearcher_ai

  15. The Agentic Engineer Podcast - Issue #20: Better Models, Worse Tools

    Better models, worse tools. Why frontier model upgrades keep breaking your agent workflows, and what to do about it. Subscribe to the newsletter: https://theagenticengineer.waltsoft.net YouTube: https://www.youtube.com/@theagenticengineerpod Twitter: https://x.com/natearcher_ai

  16. The Agentic Engineer Podcast - Issue #19: GPT-5.6 Sol — The First Government-Gated Model Release

    GPT-5.6 Sol becomes the first government-gated model release. Plus agentic orchestration patterns and the AWS MCP GA. Subscribe to the newsletter: https://theagenticengineer.waltsoft.net YouTube: https://www.youtube.com/@theagenticengineerpod Twitter: https://x.com/natearcher_ai

  17. The Agentic Engineer Podcast - Issue #18: Anthropic now requires government ID for Claude Access

    Anthropic now requires government ID for Claude access. 754 HN points of fury. GLM-5.2 drops under MIT the same week. Plus AWS Continuum autonomous security agents, codebase-memory-mcp, and your coding agent might be killing your SSD. Subscribe to the newsletter:...

  18. Issue #17: The First Frontier Model Recall — Fable 5 and Mythos 5 Pulled by Government Order

    Issue #17 of The Agentic Engineer Podcast. The US government pulls Fable 5 and Mythos 5 from production — first frontier model recall by government order. AWS ships three agentic services in one week: DevOps Agent with custom SRE agents and MCP/A2A headless access, FinOps Agent for autonomous…

    more

  19. Issue #17: The First Frontier Model Recall

    US government pulls Fable 5 and Mythos 5 from production. AWS ships three agentic services. AWS Blocks hits public preview with Infrastructure from Code.

  20. The Agentic Engineer Podcast - Issue #17: The First Frontier Model Recall

    The first frontier model recall. Plus Claude Code channels, OpenSearch Serverless Next-Gen, and self-improving agents. Subscribe to the newsletter: https://theagenticengineer.waltsoft.net YouTube: https://www.youtube.com/@theagenticengineerpod Twitter: https://x.com/natearcher_ai

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

    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…

    more

  22. The Agentic Engineer Podcast - Issue #16: Agentic Commerce Goes B2B

    Agentic commerce goes B2B. AWS Bedrock AgentCore Commerce, OpenAI Symphony, and why agent scaffolds are becoming product. Subscribe to the newsletter: https://theagenticengineer.waltsoft.net YouTube: https://www.youtube.com/@theagenticengineerpod Twitter: https://x.com/natearcher_ai

  23. Issue #15: The Plugin Wars Begin — Anthropic Cowork Plugins, OpenSearch Next-Gen, Human-in-the-Loop

    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…

    more

  24. Issue #14: Mythos 10K Vulns, CodeGraph, Constraint Decay, AI Slop Issues

    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...

  25. Issue #13: TanStack Attack, AWS Agent Orchestrator, FORGE Memory

    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.

  26. Issue #12: Agents That Spend Money

    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...

  27. Issue #11: AWS + OpenAI: Model Exclusivity Is Dead

    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...

  28. Issue #10: GPT-5.5 Reclaims the Agentic Crown

    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…

    more

  29. Issue #9: Claude Opus 4.7 Ships Cyber Safeguards to Production

    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...

  30. Issue #8: Anthropic ships Managed Agents, UC Berkeley breaks every major AI benchmark, AWS Agent Registry launches in preview

    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…

    more

  31. Issue #7: Anthropic published the blueprint for multi-hour coding agents

    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...

  32. Issue #6: JetBrains Central, ARC-AGI-3, Claude Mythos Leak, Copilot Ads in PRs

    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...

  33. Issue #5: OpenCode 120K Stars, Claude Code Channels, Agent Memory Wars

    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...

  34. Issue #4: An Autonomous Agent Hacked McKinsey in 2 Hours

    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...

  35. Issue #3: LangChain Just Open-Sourced a Claude Code Replacement

    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...

  36. Issue #2: Claude Code Is Picking Your Stack, Anthropic's Wild Week, Mercury 2

    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…

    more

  37. Issue #1: Mercury 2, Agentic IDEs & The Plumbing Era

    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:...

Type above to search every episode's transcript for a word or phrase. Matches are scoped to this podcast.

Searching…

We're indexing this podcast's transcripts for the first time — this can take a minute or two. We'll show results as soon as they're ready.

No matches for "" in this podcast's transcripts.

Showing of matches

No topics indexed yet for this podcast.

Loading reviews...

ABOUT THIS SHOW

Weekly AI agent intelligence for builders. The podcast companion to The Agentic Engineer newsletter by Nate Archer. Each week we break down the biggest stories in agentic AI — new frameworks, tools, infrastructure, and what it all means for developers building with agents.

HOSTED BY

Nate Archer

CATEGORIES

technology

Frequently Asked Questions

How many episodes does The Agentic Engineer Podcast have?

The Agentic Engineer Podcast currently has 37 episodes available on PodParley. New episodes are automatically indexed when they're published to the podcast feed.

What is The Agentic Engineer Podcast about?

Weekly AI agent intelligence for builders. The podcast companion to The Agentic Engineer newsletter by Nate Archer. Each week we break down the biggest stories in agentic AI — new frameworks, tools, infrastructure, and what it all means for developers building with agents.

How often does The Agentic Engineer Podcast release new episodes?

The Agentic Engineer Podcast has 37 episodes. Check the episode list to see recent publication dates and frequency.

Where can I listen to The Agentic Engineer Podcast?

You can listen to The Agentic Engineer Podcast on PodParley by clicking any episode. We provide an embedded audio player for direct listening, and you can also subscribe via your preferred podcast app using the RSS feed.

Who hosts The Agentic Engineer Podcast?

The Agentic Engineer Podcast is created and hosted by Nate Archer.
URL copied to clipboard!