Feature Flags for Behavior, Not Features
Author(s): Shrashti Singhal Originally published on Towards AI. Progressive rollout of prompts, policies, and tool loadouts — plus why percentage rollouts lie when the metric is quality. The team in this composite story had excellent release engineering. Twelve years of it, in …
Deadlines as a First-Class Input
Author(s): Shrashti Singhal Originally published on Towards AI. Propagating a latency budget into the reasoning, so the agent trades depth for time on purpose instead of timing out mid-thought. Here is a race condition currently running in production at more companies than …
Multi-Agent Orchestration Patterns — and When Not to Use Them
Author(s): Shrashti Singhal Originally published on Towards AI. Everyone wants an AI team. Most tasks want one strong agent. This is a field guide to the orchestration patterns that actually work, the economics nobody mentions in the demos, and the discipline of …
Everything Is a Plugin: Inside DeepSeek Harness, the Week the Scaffolding Became the Product
Author(s): Shrashti Singhal Originally published on Towards AI. Everything Is a Plugin: Inside DeepSeek Harness, the Week the Scaffolding Became the Product A year ago, “the harness is the product” was an argument. On August 13, DeepSeek turned it into a strategy: …
Durable Execution: Agents That Survive Crashes, Restarts, and Weekends
Author(s): Shrashti Singhal Originally published on Towards AI. Your agent will die mid-task. The only question is whether the work dies with it. Part ten of a series on production agentic AI. Here is a story that every team building production agents …
Prompt Injection and Agent Security: The Unsolved Problem
Author(s): Shrashti Singhal Originally published on Towards AI. Your agent can’t tell your instructions from an attacker’s. Nobody’s fully fixed that — and the more capable your agent gets, the more that costs you. Part nine of a series on building production …
The Economics of Agents: Token Accounting, Caching, and Routing
Author(s): Shrashti Singhal Originally published on Towards AI. Your agent doesn’t have a performance problem. It has a unit-economics problem — and the fix is engineering, not a bigger budget. There’s a moment every team building agents eventually hits. I’ve started calling …
Recent Posts
