이 팟캐스트 소개 🔗
Welcome to The Agentic Stack, a podcast for people who design and ship agentic AI. In 8-10 minutes per episode, we unpack real‑world architectures for LLM agents: how to structure multi‑agent systems, add guardrails and governance, evaluate performance, and run reliably in production. If you’re a staff/principal engineer, architect, or tech leader in fintech, insurance, or enterprise software, this show gives you focused, actionable ideas—no fluff. New episodes drop regularly. Hit subscribe and strengthen your agentic stack.
업데이트 빈도:
every 8 days
평균 오디오 길이:
8 minutes
영어
미국
에피소드 8 개
2026년 8월 27일부터
episodic
이 팟캐스트 내 🔗
최신 에피소드 🔗
Microsoft Agent Framework Python 1.24.0 changes the beta RedisContextProvider scope schema and refuses to auto-migrate incompatible indexes. Persistent agent memory becomes a planned-downtime migration: delete the legacy raw-scope index and context hashes, let the new version create a fresh index, …
이전 에피소드 🔗
This episode treats framework patch notes as the real reliability signal for production agents. We examine OpenAI Agents SDK v0.24.0 and Microsoft Agent Framework .NET 1.26.0, focusing on multi-turn orchestration, session-write batching, parallel tool-call gating, Copilot hook composition, and comp…
Meta's Muse Spark Open brings open weights, a 1M-token context window, and explicit tool-calling tuning to the repo-scale coding agent conversation. This episode treats it as a build-vs-buy decision: what to test, how to pin hardware and runtime, and why independent benchmarks matter before pr…
Orca Agent Engine is now Apache 2.0 Developer Preview, a production-used agent runtime moving to a self-hostable model with governance controls, CLI, and TypeScript, Python, and Go SDKs. This episode covers what changed, practical builder evaluation steps, portability testing across SDKs, the risk …
Strands shipped a harness on September 21st, 2026 with a headline claim of frontier performance at 28% lower token cost. Three days later, Dark Reading reported a prompt-injection vulnerability in the agentic app Manus that could have enabled data theft and compromise. This episode connects the har…
Agent skill supply-chain security is where prompt injection is heading next. This week on The Agentic Stack, we work through SkillSecurer, an arXiv preprint submitted on September 12, 2026, that detects and patches prompt injection vulnerabilities inside the reusable capability modules agents load.…
Indirect prompt injection is being stress-tested from three directions at once, and the shared assumption underneath current agent security practice is what's under pressure. Three papers published within nine days of each other reframe the problem: ECLIPSE describes a self-evolving attack bui…
이 팟캐스트의 모든 에피소드를 보셨습니다
면책 조항: 이 페이지에 포함된 팟캐스트와 작품은 VekktorAI에서 가져온 것입니다. 이 팟캐스트는 소유자의 재산이며 Listen Notes, Inc.와 제휴하거나 보증하지 않습니다.
팟캐스트 검색 엔진
당사 웹사이트를 사용하여3,832,269팟캐스트 및196,969,060에피소드를 사람, 장소 또는 주제별로 검색할 수 있습니다.
I have no special talent. I am only passionately curious, and
I listen to podcasts.
‐ Albert "Llamacorn" Einstein
이 팟캐스트 요청하기
Why to claim podcasts?
If you are a podcaster, the best way to manage your podcasts on Listen Notes is by claiming your Listen Notes
podcast pages.
It is a great, free way to engage the podcast community and increase the visibility of your podcasts.
After claiming your Listen Notes podcast pages, you will be able to:
✓
Manually refresh the RSS feed to sync up
✓
Get a verified badge (
✓
) alongside with your podcast name on Listen Notes
✓
Post 분류 광고 for sponsorship,
guests, co-hosts,
cross-promotion...
✓
Respond to listener comments on Listen Notes
✓
Use speech-to-text techniques to transcribe your show and
edit transcripts
✓
Improve the presence of your podcasts, e.g., self-service
팟캐스터 인터뷰...
✓
If you share your Listen Notes page and at-mention @ListenNotes
on X (formerly Twitter),
공식 X(구 Twitter) 계정 will retweet to promote
your show to our followers.
Coming soon:
◯ Self-service promotion on Listen Notes
◯ Track your podcast stats on Listen
Notes, e.g., listens, page
views...
◯ Manage episodes
