https://1shubham7.blog/tags/ai/ Recent content in AI on Shubham Singh Hugo -- gohugo.io en-us https://1shubham7.blog/spec-driven-multi-agent-workflow/ Mon, 01 Jan 0001 00:00:00 +0000 https://1shubham7.blog/spec-driven-multi-agent-workflow/ A spec-driven workflow for Claude Code agents: a numbered spec that gets attacked before any code, checks set up before features, three roles with walls between them, a PreToolUse hook that enforces the rules, and injected bugs to grade the tests. Written after running it once and logging every confident mistake. https://1shubham7.blog/agent-evals/ Mon, 01 Jan 0001 00:00:00 +0000 https://1shubham7.blog/agent-evals/ Normal code has tests; agents need evals. What an eval harness is, the vocabulary that goes with it, how I would build one in Go for an SRE agent working against Kubernetes, why pass^k matters more than pass@k for ops, the tools that exist (and the one OpenAI is shutting down), the ways a harness's numbers lie to you, and the habits that keep a suite useful. https://1shubham7.blog/agent-harness/ Mon, 01 Jan 0001 00:00:00 +0000 https://1shubham7.blog/agent-harness/ What an agent harness actually is, where the word comes from, and the dozen or so primitives hiding inside the term. A companion to the loop engineering post. https://1shubham7.blog/claude-code-loops/ Mon, 01 Jan 0001 00:00:00 +0000 https://1shubham7.blog/claude-code-loops/ What loop engineering actually means, where the term came from, and how /loop and /goal turn Claude Code into something that babysits deployments and works until the tests pass. https://1shubham7.blog/system-one-models-jev/ Mon, 01 Jan 0001 00:00:00 +0000 https://1shubham7.blog/system-one-models-jev/ Most LLM calls in a backend are structured decisions dressed up as chat. TypeSafe's Jev answers only that kind of question: typed answers with probabilities, in one pass, with no text generation. What it is, how its confidence numbers work, what 'can't hallucinate' does and does not mean, the open-source alternatives that appeared within weeks, and where an SRE would put one. https://1shubham7.blog/mcp-servers/ Mon, 01 Jan 0001 00:00:00 +0000 https://1shubham7.blog/mcp-servers/ A breakdown of the Model Context Protocol - the problem it solves, its architecture, and how a tool call actually works under the hood.