A build without them used learning-lab's dev Clerk key, so production
users signed in to the wrong instance and saw no data.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The sidebar now groups Production under Dashboard and the four existing
pages under Settings, and Production is the landing page. It shows content
in progress, material, content made, approved and LMS-ready counts, plus a
knowledge graph linking Brain documents, results, found sources and
schedules, with the schedule and what is being made right now beside it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Read from GET /organizations/me, refreshed after every action and every
30 seconds, since agents and schedules spend credits in the background.
The date is dropped from the topbar, and its items wrap on phones.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Clicking a document's title fetches the original file from the engine:
viewable formats open in a new tab, the rest (or a blocked tab) download
under the original name.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Drop the Open button: the title's hit area now covers the whole card,
with Retry kept on top so it doesn't open the preview.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Shorten the story header so the form shows without scrolling, keep the
Clerk card inside the screen, and run one blue background behind the
whole page.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The agent answers in the language each message is written in (Indonesian
or English), whatever the UI language; short replies such as "LLM" keep
the conversation's language. inLang() runs t() in that language.
Each turn now reads like a person: a thinking step with what the agent is
doing, the reply typed out with "Thought for Ns" above it, a short typing
pause, then one question, with its options shown once it is typed.
Reduced motion skips the animation.
"dari file LLM" / "from the document X" is read as the topic, and topics
keep the user's capitals.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The Instruction agent now confirms the output language before the plan is
ready: Bahasa Indonesia, English or 中文, the languages the engine writes
in. It can also be named in the instruction ("pakai bahasa Inggris"), is
read from short replies, and can be changed in the plan. Research alone
is not asked about.
The engine's content production has no language field, so the choice
goes into the agent's instructions; video schedules also set
video_options.language. ruleOf reads it back, so editing a topic keeps
it. The audio player recognises Chinese scripts and uses a zh-CN voice.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The Instruction page is now a conversation with the Express Agent. Each
message updates the draft plan, and when something is unclear (a part it
did not understand, a video count with no cadence, a schedule over 50 per
week, weekly research with no day, a missing topic) the agent asks right
in the chat, one question at a time, with replies to pick or type. Once
the plan is clear it offers to start the schedules and reports the result
in the chat. The plan stays editable beside the chat.
The chat text is also larger and darker than the mockup's 9-11px grey.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
