A guided tour
kapi holds the context for one project, and Kapi Desktop is where a person reads and edits it. This tour walks each surface in the order the app presents them. For what the app is and how to install it, see the overview.
Where the project stands
The desktop opens to your projects and reopens the ones you had last time. A project's home answers "where is this" on two axes before it offers to do anything.
Content is what has been read into the project, what has changed on disk since, and what is missing. Governance is the voice profile in force, the terms store bound, when the project last converged, and whether it is in sync with the venue it declares.
Beneath, the point map gives one row per point the recipe declares, with the collections sitting there and the voice bound to them. A single-point project is one row.
Bring up to date runs the project's default flow until every gated scope ships or parks. Plan… beside it is the pre-flight: the pending work, the leverage available from content memory, and a token estimate, before anything runs.
The interface has changed since this was recorded. The workflow it demonstrates still applies, but some screens and labels differ from the current release. The clip shows an earlier layout of the project home. The app now opens on the two-axis standing and the point map, above the convergence hero.
The context that governs it
The Context hub is the part of the app this tour exists for. Four surfaces, one graph.
Explorer asks by location or by content. Point it at a file and it resolves what applies there. Search a word and it returns the terms that cover it, the prior wording that used it, and where.
Voice renders the profile that governs a point, resolved rather than declared: tone, style rules, vocabulary with severities, examples, and the locale, channel and persona overrides that apply. Where a binding was skipped because its validity window had closed, the page says which one and why. Editing writes the YAML in your working tree, the same file a reviewer reads in a pull request.
Terms is the concept store: the words the project decided on, their status, their definitions, and their translations.
Content Memory is the record of prior wording, searchable, with provenance intact so you can see where a phrasing came from before you reuse it.
Collections and formats
A project's content is grouped into named collections: documentation, store copy, contracts, templates. Each is a set of patterns, and the home shows one card per collection with the real files matched beside the format kapi detected.
Opening a file previews it the way the engine reads it. A Preview of the rendered document, a Blocks list, and, where the format carries them, a Structure view of roles and reading order and a Layout view of page-scaled bounding boxes. Media renders as itself: an image with its recognized text boxed, or an audio or video player with the recognized cues as a synced subtitle track. Opening a file whose format needs an engine plugin offers to install it there and then. The format reference lists what kapi reads.
Checks
Checks are tests for prose, and the panel reads like a test report. A finding names the rule that fired and the point it is scoped to, and clicking it lands on Context at that point with the rule in view.
That click is the loop: see what was found, see the rule that found it, then change the wording or change the rule. Collections can be re-run individually as you work.
Flows and the toolbox
The Toolbox holds the flows a project runs over its content: a plain AI translation, a translation followed by quality checks, a pseudo-translation for testing. Each is a named sequence of steps saved beside the project and shared through version control. Open one to edit its pipeline, and run it through the runner with live per-file progress.
The tool browser beside it is a reference. It says what each tool does, what it consumes and produces, and the command line that runs it.
The interface has changed since this was recorded. The workflow it demonstrates still applies, but some screens and labels differ from the current release. The clip shows an earlier Toolbox. Flows now run through the runner, and the tool browser is a reference rather than a second runner.
Settings, providers, and plugins
Settings has four tabs: General for appearance, AI Models for the providers and models kapi runs with (keys stay in your OS keychain, never in the project file), Plugins for the formats and tools that extend it, and Locales. Project Settings carries the recipe itself: the languages, the governance bindings (the voice profile, the default point and the profiles), and the default flow.
Plugins install from the registry in one click, and the formats and tools they add appear in the project immediately. The manage plugins recipe walks it step by step.
The interface has changed since this was recorded. The workflow it demonstrates still applies, but some screens and labels differ from the current release. The clip shows an earlier settings layout. Terms and Content Memory now sit under Context, and Project Settings carries the governance bindings.
And in every language
A project that declares target languages gets the multilingual half. Per-language coverage appears on the collections it applies to, and the Review queue takes whatever the loop could not carry to its ship gate. Inspection puts source and target side by side with their findings, to edit, approve, reject, or sign off, keyboard-first, with an optional AI pre-review to triage a long queue. See Review & approve.
A project that declares no target languages is complete without this, and Review stays quiet.
A project whose recipe declares a bowrain: block reaches a Bowrain server for
the shared work: one content memory and terminology across projects, team review,
and convergence runs on the organization's keys. The kapi-bowrain plugin
(brew install neokapi/tap/bowrain-cli) carries the transport. See the
Bowrain documentation.
Next
- Overview: what the app is and how to install it.
- Your first project: the step-by-step path through these surfaces.
- Kapi CLI guides: each task guide notes how it maps to Kapi Desktop.