allsrc.dev
RSS FeedA space where I share articles and lessons drawn from my real-world engineering experiences. I write about building governed enterprise AI, shaping platform architecture, scaling distributed systems, and my work in open source.
This blog is my way of documenting my journey, breaking down complex technical trade-offs, and giving back to the community. Read more about my background at shashikanth.me.
Featured
What is an Agent Harness?
An introduction to the Agent Harness series: defining why the LLM is just a reasoning engine and how the harness manages memory, tools, and execution boundaries.
Recent Posts
Pattern 12: Agent Lifecycle Profile
A pattern for treating agents as governed runtime assets with identity, owner, purpose, limits, and retirement state.
Pattern 11: CI/CD Evaluation Gates
A pattern for blocking unsafe agent changes before they reach production.
Pattern 10: Agent Evaluations
A pattern for evaluating agent behavior through trajectories, policy checks, groundedness, and cost limits.
Pattern 9: Sandboxed Execution
A pattern for constraining agent-directed code execution with workspace, command, network, and approval policies.