על אודות פודקאסט זה 🔗

תדירות עדכון:
every 8 days
אורך אודיו ממוצע:
8 minutes
אנגלית
ארצות הברית
8 פרקים
מאז 27 באוגוסט 2026
episodic

הפרק החדש ביותר 🔗

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,‮…

חיפוש פרקים ישנים

חפש פרקים קודמים של The Agentic Stack | VekktorAI.

פרקים קודמים

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 com‮…
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 p‮…
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 ha‮…
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 bu‮…
צפית בכל הפרקים של פודקסט זה
הצהרה: הפודקאסט והגרפיקה המוטבעים בדף זה הם מ-VekktorAI, שהוא רכושו של בעליו ואינו קשור או מאושר על ידי Listen Notes, Inc.