DocsIntelligence ModulesIntent Map
🗺️

Intent Map

The "why" behind code disappears the moment the original author leaves. The Intent Map reconstructs what each file is for — and is explicit about which parts are computed from your repository and which are a model's reading of it.

How it works

Two layers, kept visibly apart. Most of the page is measured: derived deterministically from your code, with no model involved. A smaller part is inferred: a language model reads the file and states what it appears to be for.

Measured

  • Importance and blast radius — from the real import graph, citing the files that actually import this one.
  • Relationships — who imports it, what it imports, and what breaks if it is removed.
  • Entry points — the URL and methods a route answers on, read from the route map.
  • Step sequence — for entry points, the operations in the order the code performs them, read from the AST.
  • Lifecycle — active, zombie or dead, from the same findings the Dead Code and Zombie tabs report.
  • Operational facts — environment variables read, feature flags, and whether a test file covers the source.

Inferred

  • Purpose — a plain-English summary of what the file does.
  • Capability — the business capability it appears to implement, used to group files.
  • Actor, trigger, outcome and side effects.
  • Dependency rationales — why one file depends on another (opt-in, see Cost below).
NOTE
The model reads the file's contents and nothing else. The Intent Map does not read git history, commit messages or authorship — nothing in it can tell you who owns a file.

The tab

The Overview view answers “what does this system do”. The Files view beside it is the inspector, and carries the file count so switching is a decision about how much detail you want.

mapnostics.com/repo/mapnostics-app/intent-map
🗺️
Intent Map
AI-generated summaries at repository, file, and function level.
OverviewFiles (312)Last generated 31 Aug, 09:31Re-generate
System Overview
Purpose

A codebase intelligence platform that indexes a GitHub repository, then runs a set of scans over it — unused code, reachability, secrets, ownership and dependency structure.

Key Technologies
Next.jsTypeScriptSupabasepgvectorTailwindVercel
CapabilitiesAI-inferred19 capabilities
Raise and track support tickets
7 files
app/api/tickets/route.tslib/tickets/normalise.ts
Detect unused code
11 files
app/api/repos/[id]/dead-code/route.tslib/pipeline/detect-dead-code.ts
Export a report as CSV
1 file
lib/reports/legacy-export.ts
Ways into Raise and track support tickets2 entry points · 7 files
POST /api/ticketsCreates a ticket and notifies the admin channelroute.ts
Page/repo/[id]/ticketspage.tsx

Every label here is read from the code — the route table and the entry-point classifier.

Modulesfrom directories
app/api
41 files
tickets/route.tsrepos/[id]/impact/route.ts
lib/pipeline
23 files
file-importance.tscompute-health-breakdown.ts
components
96 files
tabs/dead-code-tab.tsxintent/capability-explorer.tsx
Start Understanding Here
3 core files define how this system works
Criticalroute.tsAccepts a new support ticket, validates the payload, stores it…
Criticalrepo-access.tsSingle gate every repository read passes through before any…
Corefile-importance.tsRanks each file by blast radius using the real dependency…

Understanding the output

Capabilities

Files are grouped by the capability the model named for them, with near-identical phrasings merged. Selecting one shows the ways into that capability — its routes and framework entry points — and filters the file list beneath it.

Evidence

Every file card carries a collapsed evidence block listing each claim and where it came from. Measured means derived from the repository; it does not mean verified, because Mapnostics never observes your code running. Corroborating facts make an inferred claim more plausible but never promote it to measured.

Intent smells

Mechanical signals that a file's purpose is unclear: a generic name, no tags, or no identifiable consumers. These are findings, not descriptions — a starting point for cleanup.

Cost & coverage

Generation makes one model call per file, so a large repository takes a while on the first run. Afterwards it is incremental: a file is only re-read when its content has actually changed, so re-generating an untouched repository costs nothing.

The Relationship Map — the AI explanation of why each dependency exists — is a separate, opt-in pass behind its own button, because it costs another call per source file. The dependency graph itself is always available without it.

TIP
If a run is interrupted or rate-limited, the tab says how many files still have no summary rather than reporting success. Click Re-generate and it picks up exactly the files it missed.

Tips & use cases

  • Start on the Overview tab to see the capabilities before inspecting individual files.
  • Open an entry point to read its step sequence — the fastest way to learn what a route actually does.
  • Cross-reference with Dead Code: a file marked Zombie whose capability nobody recognises is a strong deletion candidate.
  • Check the evidence block before acting on anything the model inferred.

See the Intent Map on the product page →