Castuner

Automatic

Automatic.co

Agentic AI and automation from the perspective of whoever has to maintain it in six months. Where an agent genuinely belongs in a process, where a plain script is enough, how to design a handoff to a human, and what breaks quietly at scale.Each episode takes one automation decision and reasons it through end to end — including the maintenance burden, the failure modes and the honest question of whether the process should exist at all. Written for operators and technical leads, deliberately free of hype. Five or six minutes an episode.Topics include where an agent belongs versus a plain script, designing human handoffs, error handling and observability, maintenance burden, process mapping before automation, measuring what a workflow saves, and knowing when a process should be deleted instead.Produced by Automatic.co, agentic AI and automation consulting. Full details, services and further reading at https://automatic.co

Сайт подкаста

Слушайте в своём приложении

Эпизоды

117 эпизодов

  1. Prompt Injection: When Your AI Gets Too Chatty 5:10
  2. Microservices: Distributed Bliss or DevOps Dumpster Fire? 5:09
  3. Multi-Agent Systems: Herding Cats with Protocols 5:10
  4. Multi-Tenancy with AI Agents: How to Share Without Screwing Everyone 5:18
  5. Overfitting: When Your Model Loves the Past Too Much 5:15
  6. Queue Backpressure: When Your System Says Stop 5:10
  7. Persistent Queues: When Memory Isn't Enough 5:07
  8. Why You're Still Getting 429s: The Hidden Cost of Distributed Rate Limiting 5:05
  9. Race to Zero Latency: Why Physics Wins and How to Build Faster Anyway 5:01
  10. Predictive Autoscaling: Smarter Infrastructure Before the Storm Hits 4:52
  11. Middleware Mayhem: Taming the Beast Between Your Disparate Systems 4:44
  12. Multi-Region Deploys: Resilience or Ruin? 4:47
  13. Model Versioning: Because Final_Final_v2 Isn't Cutting It 5:11
  14. Memory Leaks in Serverless: Still a Thing 4:55
  15. Machine Learning Models: Overhyped or Just Underfed? 4:46
  16. Message Brokers: Who's Actually in Charge Here? 5:44
  17. Why Your Failover Isn't Actually Failing Over 5:39
  18. Can Private LLMs Actually Fix the Hallucination Problem in Enterprise AI? 10:04
  19. Interoperability Nightmares: How to Wake Up from Your Data Silos 9:16
  20. Why General-Purpose AI Falls Short in Regulated Workflows 9:21
  21. Incremental Backfills: How to Rewrite Data History Without Breaking Everything 9:02
  22. Why Healthcare and Government Are Going All-In on Private AI 8:09
  23. Kernel Tuning: Because Defaults Are for Amateurs 8:59
  24. The Anatomy of a Secure AI Knowledge Base 8:40
  25. LLM Guardrails: Not Just for PR Anymore 7:42
  26. The End of Vendor Lock-In: How On-Prem AI Restores Technical Freedom 8:33
  27. Kubernetes Secrets: Spoiler, They're Not Actually Secret 8:43
  28. From Compliance Burden to Compliance Automation With Private LLMs 9:54
  29. Idempotency: Solving the Double-Click Problem for APIs 9:26
  30. AI Agents for Finance Teams: Reconciling, Reporting, and Reviewing at Scale 8:42
  31. How to Scale Your Business with Automation 6:27
  32. Building AI Agents You Can Actually Trust in High-Stakes Workflows 8:54
  33. Idempotent APIs: Because Users Always Double-Click 8:24
  34. Zero-Trust AI: Building Secure Language Models for Classified Environments 9:00
  35. Feature Flags at Scale: More Flags, More Problems 7:09
  36. Train Your LLM Like a Partner: AI for Legal Research and Drafting 7:49
  37. Why One-Size-Fits-All AI Is a Lie — And What Actually Works 7:28
  38. Stop Renting Intelligence: Why You Should Build Proprietary AI IP 8:16
  39. Hot vs. Warm vs. Cold Storage: Pick Your Poison 7:48
  40. Wiring Your Private LLM Into the Tools Your Team Already Uses 8:12
  41. Graph Databases: When Relational Just Won't Relate 8:23
  42. Legal AI With No Cloud Required: A New Standard for Confidentiality 8:23
  43. Optimistic Locking: Hope Is a Strategy (Sometimes) 7:42
  44. Private LLMs for Law Firms: Training AI on Case Law Without Breaking Confidentiality 9:33
  45. Data Anonymization: Your Privacy Theater Toolkit 8:58
  46. The Context Window Trap: Why Bigger AI Memory Isn't Always Better 6:36
  47. Private vs. Public LLMs: What Every CTO Needs to Know 8:32
  48. Real-Time Joins: Making SQL Cry 9:18
  49. LLMs Behind Closed Doors: Building Secure, In-House AI Models 10:58
  50. ACID vs. BASE: The Database Cold War 9:15