Ask HN: Heavy coding-agent users what's your context plumbing? Where it fails?

Software developers using AI coding agents are structuring their context management across three layers: personal memory tools, repository-level documentation, and organization-wide knowledge systems. While most developers have strong opinions on the first two layers, the third layer—org-wide context tools like Unblocked and Glean—remains underinvested. The community is debating whether strong personal and repo-level context makes org-wide tools redundant, or if a robust third layer could reduce reliance on the first two.

| |||||||||||| 1 point by | From what I've seen it sits at three levels: Layer 1: Personal memory MCP tools, personal .md files Layer 2: Repo CLAUDE or AGENTS.md, in-repo docs Layer 3: Org-wide Unblocked, Glean, or similar Most people have strong opinions on 1 and 2. Layer 3 seems underinvested. Curious, do you think 1 and 2 make 3 redundant, or would a strong 3 mean you'd stop/reduce patching with 1 and 2? | ||||||||||| |