Large-codebase AI work fails when you prompt without architecture. The piece argues you must provide live dependencies, module boundaries, and a readable map of what’s in play. Four preconditions before big edits: find the right code, understand dependencies, estimate blast radius, and separate live
AI development ships fast but often hides structural debt, as quick iterations outpace architecture awareness. The article promotes prevention—map the repo, search for existing logic before adding new code, check blast radius before refactors, and verify reachability from real entry points. It also
AI coding tools speed delivery but often hide architectural risks like duplicate utilities, unseen blast radii, and unreachable code. It proposes a open-source AI code quality framework with four layers: Standards, Deterministic Checks, Architectural Intelligence, and Outcome Measurement. Architectu
The article argues AI coding mistakes come from weak map awareness of the codebase, not just prompts, and that giving the agent an architectural map before coding reduces duplicates and broken refactors. It recommends steps: map the structure, search for existing logic, run blast-radius analysis, ve
AI code tooling fails more from context gaps than generation limits; Tree-sitter offers a fast, structure-first view to answer architecture questions before you touch code. It yields precise syntax trees that preserve locations and cross-language relations, enabling mapping of functions, imports, en
AI coding tools refactor in isolation and miss downstream structure; a code knowledge graph makes architecture traversable, answering what depends on this and if it’s reachable in production. It’s built by parsing code with Tree-sitter, extracting functions, modules, and endpoints, and storing their
The article argues the best MCP servers in 2026 aren’t the longest tool menus, but ones that give AI agents real context—current docs, codebase structure, and production signals. They should reduce blind guesses, save tokens, and keep setup friction low; more tools often add noise. It surveys 13 ser
MCP servers give AI hosts structured access to tools and repo data, not vague prompts. They separate tools, resources (readable data), and transports, enabling typed calls and schema-validated inputs. For codebases, structural context (graphs of modules and dependencies) beats raw file text, reducin
MCP is an open standard that lets AI tools connect to external capabilities—code, databases, services—to get grounded context before acting. It's not a model, plugin, or code generator; it's the wiring that standardizes discovery, context, and actions across tools like Claude Code and Windsurf. In c
Solo developers need code analysis that reveals the system’s structure, not just linting. Tools should map dependencies, show reachability and blast radius, and flag dead or duplicate logic before touching shared code. The article splits tools into linters, static scanners, local AI reviewers, and c
New posts on codebase intelligence, AI coding, and building Pharaoh.