Topic
AI Workflows - Page 8
How engineering teams turn AI tools into repeatable work. Curated tldw.news briefings about ai workflows, with practical engineering takeaways from long-form AI and developer-tool videos.
215
breakdowns
Page 8 of 22
AI EngineerYour Auth is Broken for Agents. Fix It Now.
Auth fails agents: broad permissions and non-determinism are security time bombs, demanding fine-grained, dynamic controls.
AI EngineerAutomating the Performance Investigation Black Box
An agentic workflow that automates performance investigation, turning unpredictable firefighting into weekly high-ROI fixes—verified before you review.
AI EngineerRealistic Evals, Not Benchmark Scores, Gate Your AI Agents
Lyft’s team shows how realistic offline simulation and validated, actionable LLM judges create a production safety net for AI agents, not just a score.
AI EngineerHierarchy scaffolds break agent idea plateaus
Agent loops stall when they run out of ideas. A hierarchy decomposition trick helps propose bolder changes, escaping plateaus. Anecdotal but actionable.
AI EngineerAI Model Quality Is Table Stakes—UX Now Decides Adoption
Many AI features fail because users don't trust them. This talk breaks down the UX patterns—citations, transparency, control—that can make or break adoption.
AI EngineerAI Loop Hype Misses the Real Problem: Defining What “Good” Means
A Langfuse experiment shows self‑improvement loops gain most on first iteration with clear yes/no criteria—ditch fuzzy LLM‑judge scores for binary evaluators.
AI EngineerLoops Won’t Replace Your Engineers—Unless You Let Them
Loops promise speed but demand discipline: verification gaps, cost, and code rot threaten to undercut the hype. Pragmatic teams start small.
David OndrejManaging AI Agents, Not Just Using Them
An AI engineer uses an agent manager and adversarial code review catching 63% of AI-generated changes—a shift in how teams should design AI workflows.
AI EngineerYour Model’s Best Feature Won’t Survive a Bad Harness
AI models are getting smarter, but the largest accuracy regressions come from broken harnesses, wrong system prompts, poor quantization—not the model itself.
AI EngineerCode Is Free—Architecture and Security Are Now the Bottleneck
Code writing is commoditized, and human code review may vanish. The real engineering bottleneck shifts to architecture, specification, and security governance.
Get TL;DW
Too Long; Didn't Watch.
A concise breakdowns of the AI and devtools videos that actually matter for engineering leaders.
Free. Weekly. No hype.