Siddhartha Borah from Brackett: teaching agents work that was never written down (Heavybit DevGuild)

In this episode, Siddhartha Borah, cofounder and CTO of Brackett AI, joins us at Heavybit DevGuild. Siddhartha explains how Brackett is building agents that can learn complex business work — especially in areas like supply chain and operations, where the real context often lives in people’s heads rather than documentation. We talk about teaching agents by doing the work, turning messy human knowledge into reliable workflows, agent-in-the-loop systems, memory, knowledge graphs, and why the last mile of enterprise automation is so hard.Links:• Siddhartha Borah’s LinkedIn• Brackett AI• Heavybit DevGuild 00:00 Intro00:30 What Brackett AI is building01:40 Learning work that was never written down03:30 Turning human context into repeatable workflows05:20 Why real-world agents fail without hidden context08:00 Teaching agents by doing the work09:50 Handling edge cases and human handoff11:30 Memory, knowledge graphs, and “déjà vu” for agents14:00 Where to learn more