AI coding tools struggle when they only read files, missing architecture, dependencies, and cross-service links in large repos. It promotes deterministic parsing and knowledge graphs to give LLMs true context and unlock graph-based queries. Pharaoh and MCP enable live, queryable repo graphs that int
AI coding assistants that see files in isolation breed architectural drift, duplicates, hidden blast radii, and unsafe suggestions. A structure-first workflow builds a live codebase map with module profiles, blast-radius and reachability graphs, and global function searches; enforces spec-to-code al
Claude code context windows often hit a limit, causing forgotten files, duplicated code, and dropped context during real work. Expanding the window isn’t a fix: code is token-heavy, histories accumulate, and latency and cost rise. The cure is disciplined context: modular sessions, /clear and /compac
AI tools can only see fragments of a codebase due to context limits and no system-wide view, causing duplicate utilities, broken callers, and hidden dependencies. Pharaoh turns TS/Python into a live Neo4j knowledge graph (Tree-sitter) and exposes it to AI tools via MCP, enabling blast-radius, reacha
The article argues that AI coding tools often rewrite or duplicate code because they only see partial context and misinterpret intent. Linearly reading files, missing architecture, and vague prompts cause regressions, dead code, and hidden dependencies. It advocates using knowledge graphs to map mod
AI tools often duplicate code because they only see local files, not the whole project, creating maintenance headaches for small teams. The article argues for architectural awareness—giving AI access to the entire codebase to reuse canonical logic. It highlights Pharaoh, a knowledge graph that maps
AI refactoring often breaks other code by editing one file at a time, duplicating utilities, or changing signatures without full dependency context. Without a live map of modules and calls, cross-module breakages slip into production. Blueprint-driven refactoring maps the repo into a knowledge graph
AI coding often re-creates similar logic under different names because tools lack global architectural context, creating semantic duplicates. The guide promotes mapping the repo into a live knowledge graph (Pharaoh) to reveal structure, surface duplicates early, and give agents reliable context. It
AI coding tools often generate redundant functions because they lack a holistic view of the repo. This duplication burden especially harms small teams through more reviews, tests gaps, and regression risk. A knowledge-graph approach (Pharaoh) maps code into a Neo4j graph, surfacing canonical utiliti
AI coding tools like Claude Code struggle with codebase context due to limited memory and no persistent map, causing duplicate logic and missed dependencies. The article advocates a persistent knowledge graph that encodes modules, dependencies, and endpoints to enable blast-radius analysis and dead-
New posts on codebase intelligence, AI coding, and building Pharaoh.