Using Agents to Fix Our Agents

I lead product on a browser agent that fills out job applications for candidates. Where previously the best option for candidates was a browser extension, job boards can now use LLM-driven browser automation to enable candidates with better UI/UX. Our product traverses enterprise applicant tracking systems (e.g., Workday, iCIMS, Oracle, Ashby) and submits tens of … Read more

Your Redshift Cluster Is Probably Idle 85% of the Time — And You’re Paying for All of It

A production Redshift cluster with a single node running Zero ETL integrations. At 99% disk capacity with recurring storage crises requiring frequent manual intervention. When I ran a workload analysis on this cluster, the result was stark. It was actively processing queries for only 15% of the day. The remaining 85% was idle billing at … Read more

Monitor and debug generative AI inference with SageMaker detailed metrics and Insights dashboard on CloudWatch

Monitoring and troubleshooting generative AI inference endpoints operating at scale is challenging. When your large language model (LLM) endpoint’s P99 latency spikes, you must determine in minutes whether the root cause is GPU memory pressure, a saturated KV cache, unbalanced traffic across Availability Zones, or an auto scaling policy that hasn’t triggered. The shift from … Read more