Workflow Automation
273 episodes · Page 7 of 12
#2473: GitHub Actions Beyond CI/CD: What You're Missing
Cron jobs, self-hosted runners, NPM publishing, and self-healing repos — GitHub Actions does way more than run tests.
#2472: When Guardrails Break: The Hidden Costs of AI Gateway Filtering
PII detection at the gateway layer can block legitimate invoices. Here's how guardrails actually work and where they fail.
#2471: Creative Briefs for AI Agents: What Agencies Already Know
How agency best practices for briefing creatives map directly onto getting reliable output from AI agents like Claude Design.
#2468: When Tokens Meet GPU Seconds
How to track AI spend across Open Router, Replicate, and more — without a unified dashboard.
#2464: Batch APIs: The 50% Discount You're Probably Misusing
Batch inference APIs offer 50% off — but only for the right workloads. Here's when they actually make sense.
#2460: Shopping in a Fragmented Market
The real challenges of building an AI agent that navigates Hebrew e-commerce, geographic shipping quirks, and whitelist curation.
#2453: Escaping the AI Doom Loop in Hiring
What if job matching was built on desire, not desperation? How one signal outperforms 100 applications.
#2440: Build Your Own CRM With AI Agents
Off-the-shelf CRMs are built for sales teams, not solo operators. Here's why building your own with AI might be smarter.
#2439: AI Collapses the Framework Decision
Why Airtable fails for multi-user tools, and how AI builders are changing the framework decision for small businesses.
#2404: What Tool-Calling Benchmarks Miss About Production Failures
BFCL, tau-bench, and Nexus each reveal different failure modes. None of them test what actually kills production agents.
#2401: Designing Data Models That Mirror Your Work
Why 60% of small businesses hate off-the-shelf SaaS—and how to build tools that actually fit your workflow.
#2395: Engineering a News Pipeline for the Edges
Building a news pipeline that goes beyond headlines to reveal underreported developments in Israel-Iran coverage—without amplifying noise.
#2391: When Anti-Bot Defenses Break Accessibility
How browser automation hits a wall with Israel's strict geo-restrictions and anti-bot measures—and what practical workarounds exist.
#2390: The Low-Grade Digital Arms Race
Discover how browser automation is reshaping web interaction, from job applications to navigating geo-restrictions and anti-bot measures.
#2371: The Graph That Thinks: From Data Dots to Human Judgment
Discover how tools like Maltego and Spiderfoot transform single data points into intricate webs of connections, bridging digital and physical inves...
#2361: The Cognitive Load of Logs
How Claude Code transforms Linux system administration by automating log analysis and proactive maintenance.
#2332: Voice-to-Task: Building the Claude Task Planner
How does a voice note turn into a completed task? Dive into the architecture and tradeoffs of building a Claude-powered task execution system.
#2329: The Notification Trap: Escaping Communication Overload
How do you manage messages across ten apps without losing focus? We explore the chaos of modern communication and tools to tame it.
#2287: Is AI Code Generation the Future of Low-Code?
Exploring the rise of AI code generation and its potential to reshape the low-code movement.
#2278: Visual Programming's Enduring Tradeoff
Why do visual programming tools keep resurfacing—and why do power users keep hitting their limits?
#2254: How to Test an AI Pipeline Change
When you tweak one part of a complex AI agent system, how do you know if it actually improved anything? The answer lies in engineering checkpoints.
#2250: How Incentives Shape AI Safety Research
Vendor labs, independent research orgs, government agencies—the AI safety field is messier and more diverse than most people realize. A map of wher...
#2196: The Invisible Workforce Behind AI
Annotation is the invisible foundation of AI—and a $17B industry by 2030. Here's what dataset curators actually need to know about the tools, platf...
#2192: How We Built a Podcast Pipeline
Hilbert reveals the complete technical architecture behind 2,000+ episodes—from voice memos to GPU-powered TTS, with Claude models, LangGraph workf...