The Agentic Stack | VekktorAI

VekktorAI

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.

Episódios

  1. há 4 dias

    Prompt Injection Breaks the Transcript Assumption | The Agentic Stack

    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 built for long-horizon agentic sessions, a second paper recasts injection payloads as something found by test-time search rather than authored by hand, and a third evaluates multimodal injections against agentic frameworks instead of isolated models. A practitioner piece from the same week describes these injections as hidden from human overview. This episode names the failing assumption rather than cataloguing attacks: detection placed at the transcript level, output scanning and human review, is the layer all three are aimed past. We cover what actually changed, one practical shift for builders — move enforcement to the action layer and treat retrieved content as attacker-controlled input by default — and one limitation worth saying out loud, which is that none of this names a specific vulnerable framework.  **Keywords:** indirect prompt injection, agentic AI security, long-horizon agents, multimodal prompt injection, test-time search attack, agent framework security, tool-using agents, AI agent guardrails, prompt injection benchmarks, agent orchestration security, ECLIPSE attack, LLM agent security

    Prompt Injection Breaks the Transcript Assumption | The Agentic Stack

  2. 27 de ago.

    The Stack Gets Stateless | The Agentic Stack

    You’ve built agents that can do amazing things. But can they survive production—load, audits, routing, cost pressure, and real users? In this episode of The Agentic Stack, Mouli Sri breaks down five signals that show agentic AI is moving from clever demos to operational infrastructure for regulated industries like FinTech, InsurTech, and mortgage. You’ll learn: Why adding more agents can actually make your system slower and more expensive (the “interaction tax”)How LangGraph is quietly becoming a go‑to framework for durable, stateful agent workflowsWhat changed in the new MCP 2026‑07‑28 spec and why it matters for enterprise deploymentsWhy “cost per token” is the only infrastructure metric that really matters for agentic AIThe governance checklist you need before letting agents touch customer decisions, policy wording, or credit pathsPlus: real architect’s notes from building agentic systems in financial services, and concrete examples from underwriting and insurance advisory workflows. If you’re designing agent systems that must survive production, this episode gives you the spine of what to optimize—and what to avoid.

  • 2 episódios

Sobre

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.

Informações

  • Criado por
    VekktorAI
  • Anos de atividade
    2026
  • Episódios
    2
  • Classificação
    Livre
  • Copyright
    © 2026 The Agentic Stack | VekktorAI