Verifiable Agents, Not Demos: A Problem-First Approach

Why I took this course I wanted a systems lens on Artificial Intelligence (AI) agents: when to use them, how to scope autonomy, and how to operate them in production under real constraints (cost, latency, reliability, compliance). I needed a repeatable method to go from a business problem → agent design → evaluation → rollout, not just a prompt that works on Friday and fails on Monday. The weekly Chai & AI (tea-and-AI) sessions were the best hook: people from varied backgrounds brought real problems, unpacked buzzwords, and shared concrete patterns—immediately useful for day-to-day work....

September 1, 2025 · 3 min · 525 words · Senthil Thyagarajan

Why Every Media Team Needs an Analytics Agent

Why Every Media Team Needs an Analytics Agent From dashboards to decisions — AI is now the analyst. 🧠 The “What’s Our Best Channel?” Moment Imagine this: A strategist opens Slack on Monday morning and types: “What’s our best-performing channel in Q2 for CPL under $20?” Seconds later, the reply pops up: 🏆 Top channel: Meta (CPL: $18.67, CTR: 1.3%) ⚠️ TikTok pacing 22% behind plan ✅ Google leads in conversion rate (6....

April 19, 2025 · 3 min · 516 words · Senthil Thyagarajan

The Death of Manual Data Analysis? Why AI Won't Replace You (Yet)

The Death of Manual Data Analysis? Why AI Won’t Replace You (Yet) Everyone’s talking about how AI is changing analytics. Dashboards whisper insights. ChatGPT writes SQL. Some tools promise “one-click” data stories. So is this the end of manual analysis? Not exactly. In fact, it might be the beginning of something better. What AI Can Do (Really Well) Let’s give it credit. In day-to-day analytics work, LLMs and AI tools are already helpful:...

April 5, 2025 · 2 min · 351 words · Senthil Thyagarajan