Arky is the AI agent deep dive. Every day we take one AI engineering topic and pull it apart in a focused technical interview - sandboxes, agent memory, RAG, evaluation, security, and cost. For each topic we explain the architecture, the trade-offs, and what you'd actually build.Recent deep dives: The Engineering of Sandbox Agents, RAG vs File-Based Memory, You Can't Grade an Agent Like a Model.What you'll hear:- Sandboxing, isolation and agent security - DNS tunneling, microVMs, prompt injection, credential modeling- How agents actually remember - RAG, file-based memory, context management- Agent evaluation and grading - why you can't judge an agent like a model- Lifecycle, state persistence, cost engineering and LLM token economics- Production: local agents vs cloud sandboxes, control planes, snapshotsWho it's for: AI engineers, ML practitioners, and technical founders building and operating AI agents.Hosted by Daniel, with technical guest Maya. Full transcripts, show notes,
Required Pod Score for this podcast. PitchCentric checks your profile against host openness, topical fit, and audience signals before you generate a pitch.
Contact path
Public web form
Booking probability
36%
Guest openness
Selective
Sign up to generate a grounded pitch for Arky | AI Agent Deep Dive.
Signup to Generate a PitchArky is the AI agent deep dive. Every day we take one AI engineering topic and pull it apart in a focused technical interview - sandboxes, agent memory, RAG, evaluation, security, and cost. For each topic we explain the architecture, the trade-offs, and what you'd actually build.
Recent episodes include "为什么 AI 助手会忘事：Harness 持续学习" (28 August 2026, 15 minutes), "为什么 AI 助手会忘事：Harness 持续学习" (28 August 2026, 15 minutes), and "Why AI Assistants Unlearn Things: Harness Continual Learning" (28 August 2026, 15 minutes).
Arky | AI Agent Deep Dive publishes roughly daily, with episodes averaging 16 minutes across 5 episodes.
Booking probability for Arky | AI Agent Deep Dive is 36%, and the host is rated Selective on guests. Arky | AI Agent Deep Dive requires a Pod Score of 80 or higher. Arky | AI Agent Deep Dive's contact route on record: public web form.
The strongest fits for Arky | AI Agent Deep Dive are IT Services & Software Development. Arky | AI Agent Deep Dive has a technology audience.
Arky | AI Agent Deep Dive is a technology podcast with 5 episodes published.
Our AI reads these to draft pitches. Use them as grounding for a pitch that cites a real guest and a specific topic.
Episode #5
<p>为什么改动了 AI 助手的配置之后，老任务反而开始失败，模型本身却一点没变？一篇新论文（arXiv 2608.19013）给它起了名字：Harness 层级的遗忘。本集 Daniel 和 Maya 用大白话讲解 Harness 持续学习——冻结模型外层的四个部件（任务接口、经验记忆、能力图谱、自适应路由器），把出主意和上线分开的优化器与评估器（当前改进、历史保持、有效性三道门），以及那个在学得多快和留住多少之间做权衡的旋钮，并给出...
Episode #5
为什么改动了 AI 助手的配置之后，老任务反而开始失败，模型本身却一点没变？一篇新论文给它起了名字：Harness 层级的遗忘。Daniel 和 Maya 用大白话讲解 Harness 持续学习——冻结模型外层的四个部件、把出主意和上线分开的优化器与评估器三道门、以及那个在学得多快和留住多少之间做权衡的旋钮，并给出多个环境里的实验结果和诚实的局限。
<p>Why does an AI assistant start failing on old tasks after you change the surrounding setup, even though the model itself never changed? A new paper names it: harness-level forgetting. Daniel and Maya break down...
Why does an AI assistant start failing on old tasks after you change its setup, even though the model never changed? A new paper names it: harness-level forgetting. Daniel and Maya explain Harness Continual Learning...
<p>Why does an AI assistant start failing on old tasks after you change the surrounding setup, even though the model itself never changed? A new paper names it: harness-level forgetting. Daniel and Maya break down...
Episode #3
<p>Daniel and Maya separate the two failure classes of agent sandboxes: the eval-harness headlines (a testing/ops problem, not a boundary defeat) from genuine substrate breakouts like Unit 42's DNS tunneling. They walk...
Episode #3
Daniel and Maya separate the two failure classes of agent sandboxes: the eval-harness headlines (a testing/ops problem, not a boundary defeat) from genuine substrate breakouts like Unit 42's DNS tunneling. They walk...
Episode #2
<p>Why you can't grade an agent like a model. The accuracy number we all trusted collapses for agents: a 50x cost gap, reliability that diverges from mean accuracy, a 53-point benchmark swing caused by the scaffold and...
Episode #2
Why accuracy is the wrong score for an AI agent. A 50x cost gap with no accuracy reward, a 53-point CORE-Bench swing driven by the scaffold and the grader not the model, graders as an attack surface, and the four...
How do AI agents actually remember? This episode compares the two dominant approaches to agent memory. File-based memory, like the instructions and index files Claude Code and Hermes keep, has won real-world adoption...
How do AI agents actually remember? This episode compares the two dominant approaches to agent memory. File-based memory, like the instructions and index files Claude Code and Hermes keep, has won real-world adoption...
PitchCentric classifies Arky | AI Agent Deep Dive under these industries. Guests from them are the closest fit, and each links to the best podcasts in that industry.
Shows with the most semantically similar episode content. Pitch one, pitch all; producers cluster.
Is this podcast yours and you'd like to remove or correct details? Request removal or email privacy@pitchcentric.com.
Questions about the free trial? See the pricing FAQ
