Comprendia makes the code context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → behind an AI explanation visible to the developer. The Eclipse plugin for Java combines an interactive dependency graph with explanations generated from selected methods called by the code under inspection. Its selection procedure uses relationships in that same graph, so the context supplied to the model can be traced to visible nodes. Research abstract.
This connects navigation and explanation: the developer can inspect the relationships used to build the prompt. The reported evidence is a project demonstration, rather than a measured improvement in how quickly developers understand code.
Terms in this piece · Glossary
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
grounding — Tying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.
articleBetter Call Grep: Evaluating and Improving Grep-Like Lexical Retrieval for Repository-Level Code CompletionBaoyi Wang, Xingliang Wang, Guochang Li, Chen Zhi, Junxiao Han, Xinkui Zhao, Nan Wang, Shuiguang Deng, Jianwei Yin
videoThe AI Skill I Rely On Daily — Priscila Andre de Oliveira, SentryAI Engineer
videoHow to Generate Mergeable Code with a Context Engine — Peter Werry, UnblockedAI Engineer