Make capability measurable
AI systems only become durable when quality, regressions, and risk are visible to the whole team.
Senior AI engineer focused on agent experience
Shashwat Jain
I write about agent experience: the tools, context, evals, permissions, and recovery paths that turn AI agents from impressive demos into dependable products.
- Agent experience
- Tool-using AI systems
- Enterprise AI
- Platform architecture
- Evals and observability
- Commerce systems
Latest writing
Field notes on agent experience and production AI
Every Application Has Two Surfaces—and Agent Evals Should Diagnose the Second
Agent experience is not an alternative to agent evals. It is the product surface those evals should help us diagnose and improve.
DevOps Is Moving Toward LoopOps
DevOps made shipping and operating software a continuous discipline. LoopOps is the next step: making improvement itself a first-class, measurable loop for humans and agents.
Telemetry Should Close the Improvement Loop
Telemetry should not end at observability. As software teams add coding agents and agentic workflows, telemetry needs to become the evidence layer that helps products get better.
Agent Experience Is Bigger Than Developer Experience
More tokens, more context, and more connectors do not automatically create better AI products. Agent experience borrows from user experience and developer experience, but agents need a working environment for every kind of operational task.
Operating principles
How I think about durable AI products
Design the agent environment
Better tools, context, permissions, and recovery paths create more value than simply adding tokens.
Treat autonomy as earned
Ship narrow, observable workflows first. Expand autonomy when the system has proved it deserves trust.