Topic
AI Workflows - Page 3
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.
583
breakdowns
Page 3 of 59
AI EngineerAgent to-do lists waste tokens. Move the plan to the harness.
After two years of rebuilds, Arize's agent team found the model is the easy part. Planning, memory, and stopping rules belong in the harness.
AI EngineerCode Mode Agents: Less Token Bloat, More Sandbox Complexity
Code mode agents can write and compose tools on the fly, slashing token usage but introducing sandbox management burdens. Arize AI shares production results…
AI EngineerWhy Agent Governance Needs Brakes, Not Walls
The $900M Revlon error is a masterclass in why agent governance must be baked in, not bolted on. Here's what Two Sigma does differently.
IBM TechnologyAI Flips Open Source Security: Discovery Is Easy, Fixing Is Hard
AI vulnerability discovery is outpacing remediation. New tools promise coordinated fixes, but the human bottleneck remains.
AI EngineerWhy Your AI Agents Need a Manager, Not Just Permissions
AI agents need HR-style governance: identity, sponsor, and machine-speed oversight. The talk from Gravitee offers a framework but no proof.
AI Engineer300 agents in 60 people: The ungoverned AI agent sprawl
A 60-person company discovered 300 AI agents running daily. The security and cost surprises that followed apply to every team deploying agents today.
AI EngineerStop Shipping Agents on Vibes: Build a Regression Loop
Arize's Xander Song shows Harbor, a sandboxed evaluation framework that turns agent changes into verifier-scored regression tests. The catch: realistic data.
NeuralNineOpenAI Agents SDK makes governance a first-class agent primitive
OpenAI's Agents SDK now ships guardrails, approval gates, and lifecycle hooks as core primitives. The demo shows the controls; production evidence is missing.
Latent SpaceWhy AI drug discovery agents need a known answer key
Leash Bio's pre-measured chemical environments reveal that better AI agents abandon bad hypotheses faster — a richer eval than final scores.
Hugging FaceMost RL environments are broken; data quality now gates agent training
Only 800 of 90,000 RL environments survived vetting. Agent post-training is failing on data quality and MLOps, not model capability.
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.