Agent Code Explainer

Connect agent session context to code diffs so engineers understand what AI actually changed

Problem

After an AI agent writes code, git diff only shows line changes while the real intent lives in the session context and often disappears during long runs. On unfamiliar codebases where agents are the primary contributor, engineers struggle to build judgment.

Solution

Locally bind agent sessions to commits, automatically extract the session snippets, key decisions, and unverified assumptions behind each change, and present them as a timeline, per-file annotations, and a 'why the agent did this' summary.

Users

Developers who use Claude Code, Codex and similar agents as primary tools, especially when inheriting unfamiliar repos or reviewing agent output

MVP

Local session import and diff binding; per-file intent summaries; unverified-claim markers; multi-repo switching; exportable review report.

Revenue

One-time purchase or subscription ($8–15/mo) for individuals; per-seat team pricing; code host integration as an upsell.

Why now

Agents are shifting from assistants to primary contributors, making long sessions normal, yet tools for understanding agents are nearly non-existent. Local-only processing also eases code-leak concerns.