When should Claude redesign the whole dashboard?

Answer for Dani · 21-11-2026 · read from the dev branch at commit 3728bae · nothing was changed in the repo

The short answer

  1. Your idea is right. Freeze what each screen shows first (numbers, maths, wording keys, rules). Then a design agent only builds the look and never decides what is shown.
  2. Do it in two waves, not one. Do not wait for the whole system to be finished, and do not redesign the unfinished parts.
  3. Wave A can start now. The screens whose content is final: login, numbers, cohorts, openers, people, follow-up list, break-off (core), the health cards. Plus the shared design system (colours, tables, rate cells, language switch).
  4. Wave B waits for four tickets: #38 judge verdict screen, #43 control room part 1 (pause and limits), #30 switch live (the panel) and Dani's yes on #8 (Umgesetzt). The coach screen waits for the coach-in-the-cloud decision.
  5. The tool that makes it safe: one content contract file per screen. The design agent may not change it. Tests plus check:numbers must stay green afterwards.

1. What the dashboard shows today, screen by screen

Source: system/dashboard/src/*.tsx and texts.ts on dev. “Final” = the fields and wording are settled; only rows of data change. “Changing” = a ticket that is not done will add or change fields.

Screen (file)What it showsData comes fromTicketContent
Login and header
Shell.tsx
Login form; header with the German/English button, log out; tab bar. Logged out, nothing else is drawn.Supabase login; allowed_users (stored language)#17 (logins), F7.4final (tab bar grows when new screens come)
Overview: numbers by week and day
Numbers.tsx
One table per period kind. Per channel: messaged, replies, reply rate, bookings, booking rates. Every percent shows its period and its base group.views numbers_by_week, numbers_by_day; counting_rules#17final (open items are checks, not content)
Booking rate by first-message week
Cohorts.tsx
Of the people first messaged in a week, how many have an appointment. Young weeks are marked “so far”.view cohort_numbers_by_weekW6final
Openers
Openers.tsx
Replies and bookings per opener variant, by week and day, totals, an “unrecognised openers” count and a note that rows are no fair comparison.views opener_numbers_by_week/_by_day, opener_totals, unrecognised_openers#19, #20final (one open data question: openers before 11-08, see section 2)
Health cards and warnings
Collector.tsx, Backup.tsx
Warning at the top of every screen when the collector stopped or the backup is over 48 hours old or unreadable; a card with the facts behind it.collector_health, backup_health#12 (collector), #13 (backup)final (backup shows “none” until the second Supabase project exists)
Money line and card
Budget.tsx
A line on every screen: what is left of the limit. Card: limit, spent, held by running calls, left, a bar, newest call, spend per part.function claude_budget(); limit from the model tableW4 of 20-11, #44 (cap $60)changing (#43 adds pause switch, daily limit, forecast)
Test number card
Shell.tsx
The first “tracer” number: a message count with its source and cut-off time.view tracer_number#10final but a leftover proof card. My suggestion: drop it, ask Dani.
People
People.tsx
Search by person or by message text. One person: details, first and last contact, whole history, reader summary and “where the conversation stands”. Other language by button, one message at a time.search_people, search_messages, person_overview, person_reader_forms, person_messages, message_translations; function translate#18, #26final
Break-off report
Breakoff.tsx
Where replied chats stop, step by step, with base and period; the causes with counts; examples that link to the chat; the health line for reasons; category list (new ones can be rejected once); reader accuracy.breakoff_base/_steps/_causes/_examples, reader_review, reason_category_list, reason_health, reason_chats, reason_accuracy_latest#27, W3, W5final fields; rows change when #37 turns on
“Said yes, no appointment” block
SaidYes.tsx (inside break-off)
Counts per signal (email, clock time, call link, our “booked”), then the chats with a link. No message text.said_yes_summary, said_yes_chatsW1, #40changing (#40 removes known clients: fewer rows, same fields)
“Quiet after our message” block
QuietAfterOurs.tsx (inside break-off)
Counts per kind of our message and the top 20 normalised messages. Every count opens its chats.quiet_summary, quiet_top_messages, quiet_message_chatsW3, #39final (#39 is speed only)
Follow-up “Nachfassen”
FollowUp.tsx
Who replied and went quiet, sorted by the reader's interest: days silent, summary, link to chat, open channel. CSV of exactly these rows.view follow_up_candidates#28final (#40 removes kiaus contacts: rows only)
Panel “Wer braucht uns”
Panel.tsx
Who needs a person, most urgent first, with the recap; taken-over chats with the 24-hour warning; switch buttons “Übernehmen” and “Zurückgeben”.view panel_conversations; function takeover#29, #30, #31will change (buttons are disabled until the switch is live; ai_off rule question open with Max)
Coach
Coach.tsx
Weekly brief, briefs on request, chat answers; a box that queues a question (limit 10 open per login). Quotes as written.table coach_outputs#32, #41will change (coach moves to the cloud with visible thinking: control room plan)
Ideen + Umgesetzt
Ideen.tsx, Umgesetzt.tsx
Ideas as a conversation between Dani, Max and the system: pick, change, merge, approve or send back; wording from the writer; copy-ready German wording, the “Umgesetzt” button, live-check state, days left of the judge's week.tables ideas, idea_events, idea_drafts, umgesetzt#33, #34, #8will change (#38 puts the judge verdict here; #8 waits on Dani's dated yes)
Grading
Grading.tsx
One chat at a time out of the 50, with the questionnaire; Dani and Max enter one agreed answer; progress; the key is frozen with a version.grading_sets, answer_key_answers, crm_messages; freeze_answer_key#22, #23final but a one-time tool. Lowest design priority.

2. What is still coming to the dashboard

Sources: V1-TEAM-PLAN-20-11.md, NIGHT-RUN-RESULT-21-11.md, CONTROL-ROOM-PLAN-20-11.md, T6-JUDGE-DESIGN-21-11.md, V1-EVALS.md, V1-ENGINE.md. Night run of 21-11: T4, T7, T8, T9 did not start (#39, #40, #42, #17, #24, #26, #35, #43).

TicketWhat it adds or changes on screenState on 21-11Waits on
#38 Judge on the reply countA verdict block per test: “{n} of {needed} chats, about {w} more weeks”; winner / not clear yet / tested, didn't work / lost on harm; buttons Extend and Revert; untouched steps shown beside; bookings shown beside (never deciding); wording-seen share; a note when the wording was never found; “retest allowed” (Dani only). Eight new text keys, German and English.Design page merged. Not built.Dani's 5 answers: 28-day before-window, 15-point minimum effect, never-found capped at “not clear yet”, untouched steps show-only or blocking, keep “booked” as a testable step
#43 Control room part 1Pause switch and daily dollar limit per paid part (reader, labeller, coach, writer); money forecast. Later parts: live map, activity feed, build-agent status, coach in the cloud with visible thinking, reader you can watch.Not started. Only a plan.Dani's 7 questions (who sees it; switches first; coach cost; thinking summary or full; build agents here or separate; how live; Telegram alerts)
#37 Live readerNo new fields. Lists and break-off fill within about a minute of a new message. Reader forms appear by themselves.Merged and deployed, switched off. The test run failed: Supabase's Anthropic key is not valid (HTTP 401, $0 spent).Dani: put the real key in Supabase, then switch on
#39 Per-chat facts table, faster lists
#40 Said-yes list without known clients
Same fields, less waiting. Said-yes list and every lead list drop known clients and kiaus contacts (Max's friends).Not started (no time or memory slot in the night run)Agents. Nothing waits on a person.
#42 Never-break rules on the real tablesNo screen. A daily check, e.g. “nobody on said-yes has a real appointment”.Not startedAgents
#30 / #31 Switch live and test with MaxThe panel's “Übernehmen” and “Zurückgeben” become real buttons. A note about ai_off is on the panel.Built and deployed. Not live: no switch key set; collector not redeployed.Max and Dani: key, tag, three passes. Still open for Max: does ai_off fire on every reply or only on TEST_DANI?
#8 / #34 UmgesetztBlock is on the Ideen screen now. Live check finds the new wording in the AI's messages. Real Haiku test needs gate A34.live (under 1 cent).Merged and deployedDani's dated yes closes #8; yes or no to gate A34.live
#13 Backup liveThe backup card gets real values.Code merged. The second Supabase project does not exist.Dani creates it
#20 OpenersOpeners screen: “unrecognised” line. All 16 openers recognised; but before 11-08, 61% of our opener texts are not on Max's list. L8.1 (under 2%) does not hold.MergedMax (pre-August wording) or Dani decides history before 11-08 is out of scope
#32 / #41 CoachFirst real brief stored (grade B). Coach chat answers only while Dani's PC runs the script; cloud version is part of the control room.#41 closed; #32 openControl-room decision
#36 First real cycleNo new screen. The cycle goes through Ideen, Umgesetzt and the judge verdict.Not started#38, switch test, Dani and Max

3. The rules a redesign must keep

Every rule below is already written down and, where marked, already tested. The design agent gets this table with the contract.

#RuleSource fileTested by
R1Every number is a value from the database and is marked data-value. Nothing is counted or divided in the page.V1-EVALS.md F7.1, L7.1; header of Numbers.tsx; Shell.tsxdashboard.test.ts, the screen tests, check:numbers
R2Every percentage shows its period and its base group.V1-EVALS.md F7.2; RateCell.tsxF7.2 test reads the page
R3A rate whose base is under 30 people (MIN_BASE) is grey and says “too few”. Break-off has its own minimum per cause.numbers-backend.ts, RateCell.tsx, _shared/breakoff.ts (MIN_CHATS_PER_CAUSE)numbers-w6.test.ts, breakoff-screen.test.ts
R4A week whose people can still book is marked open: “so far”, not final.Cohorts.tsxnumbers-w6.test.ts
R5German and English with one button. One text on screen at a time, never two side by side. Every fixed word comes from texts.ts. Max reads only German, Dani only English.DECISIONS.md “German / English switch (Dani, 15-11-2026)”; texts.ts; BRIEF decision 9 (German words such as Angeschrieben, Antworten)dashboard.test.ts (every text node outside data-value must come from texts.ts)
R6Customer messages are shown as written and marked data-value, so the language button never changes them. A translation is stored beside the original, never replaces it, and only Claude translates.DECISIONS.md same row; V1-EVALS.md F26.1; header of Grading.tsxpeople-screen.test.ts, grading-screen.test.ts
R7A shown quote is copied word for word. The reader's “stated reason” is found word for word in the chat (100%). A coach example is a real message it was shown. Quotes are never translated.V1-EVALS.md A2, Q3, F32.2; Coach.tsx headercoach-screen.test.ts, coach-refusal.test.ts
R8Logins for Dani, Max and Adnan, each their own. Logged out, nothing is visible: the page carries no data and tells search engines to stay out.DECISIONS.md Q7, Q10; V1-EVALS.md F7.4; Shell.tsx; public/_headerscheck:dashboard, check:access
R9Every dashboard number must match an independent recount from the raw tables (code that shares nothing with the dashboard). Last run: 1,068 rows, 0 differences.V1-TEAM-PLAN-20-11.md section 5; V1-EVALS.md F7.1, L7.1; system/scripts/check-numbers.tsnpm run check:numbers
R10The funnel stops at “booked”. No show-ups, closes, conversion or revenue. “Booked” means an appointment in the CRM.BRIEF.md Locked decision 4; CONTROL-ROOM-PLAN-20-11.md (W1)counting rules tests
R11Reasons the person stated are kept apart from reasons the AI guessed. The reader's own guess is shown, marked.V1-ENGINE.md station 3; V1-EVALS.md Q3breakoff-screen.test.ts
R12No bare codes on screen. A code is shown as words; an unknown code is humanized, never raw.Logs/Log-Folder-Self-Improving-System/20-11-2026-w3-dashboard-reasons-story-health-line-drill-down-no-bare-codes.md; codes.tsreasons-dashboard.test.ts
R13A read that fails is shown as a warning or message, never as silence and never as an invented number. The failure of one block never fails the rest.App.tsx; Collector.tsx; Budget.tsx; V1-EVALS.md L4.3claude-budget-screen.test.ts, collector-dashboard.test.ts, backup-dashboard.test.ts
R14The Anthropic budget stays in view on every screen: the limit and what is left, going down as it is spent. Limit is $60 now.DECISIONS.md “Budget for Anthropic API use”; NIGHT-RUN-RESULT-21-11.md; Budget.tsxclaude-budget-screen.test.ts
R15Human in the loop. People decide what is tried. Every idea shows where it came from. The Umgesetzt click cannot be undone and the screen says so before it. The wording to copy is always German.V1-ENGINE.md “Human in the loop”; Ideen.tsx, Umgesetzt.tsx headersideas-screen.test.ts, umgesetzt-screen.test.ts
R16The judge shows harm beside the result and never hides it. Bookings are shown beside the verdict. Never promise or claim anything we cannot deliver (applies to every text).DECISIONS.md Q28; T6-JUDGE-DESIGN-21-11.md sections 4, 6-8judge tests (when #38 is built)
R17The dashboard writes only what each screen's backend already allows (ideas, events, Umgesetzt click, answer key, reject a category, a coach question, the switch). A redesign adds no write. Never an action on the CRM except the switch.headers of Ideen.tsx, Panel.tsx, Grading.tsx, Coach.tsx; V1-ENGINE.md “Takeover switch”check:access
R18Proof screenshots contain no names and no message text.V1-EVALS.md H7.1made with the synthetic page synthetic.html

Note: BRIEF.md decisions 5 and 8 (typed-in numbers, rates from the sheet) were replaced when we integrated with the CRM. The working files win where they differ.

4. The right moment, and how to do it

Two waves

WaveScreensStarts whenWhy
A: nowDesign system (colours, type, table, rate cell, cards, tab bar, login, language button, grey “too few”, empty / loading / failed states) and the screens marked final: Login, Overview numbers, Cohorts, Openers, People, Follow-up, Break-off with its two blocks, Collector and Backup cards, money line.The contract files for these screens are written and checked by Dani (about one day of agent work)Their fields are final. Open tickets there only change which rows are shown, not which fields (#37, #39, #40).
B: after four ticketsPanel, Ideen + Umgesetzt + judge verdict, money card with pause and limits.#38 built, #43 part 1 built, #30 live (switch test passed), #8 yes givenEach adds fields or buttons. Designing before would mean redoing it.
Later, separateCoach in the cloud with visible thinking, live map, activity feed, build-agent status (control room parts 2 to 5).Dani answers the 7 control-room questionsTheir content is not even decided. Give them a “Control room” area, so wave A and B never wait for them.

Tickets that must be done first, so the content is frozen

TicketNeeded forNeeded beforeWho
#38 judge built (after Dani's 5 answers)the verdict block, Extend / Revert, untouched steps, bookings besidewave B (Ideen)Dani answers, agents build
#43 control room part 1pause switch, daily limit, forecast on the money cardwave B (money card)Dani answers 7 questions, agents build
#30 (and #31 test), ai_off questionthe panel's real buttons and what they saywave B (panel)Max and Dani
#8 yesthe Umgesetzt block as it standswave B (Ideen)Dani
#39, #40final shape of the lists (fewer rows, same fields)nice to have before the break-off and follow-up screens are checked on live data; not needed to startagents
#37 on, with a real keyreal forms arriving by themselves, to look at the redesigned lists with live rowsnot needed to start; needed to review wave A on live rowsDani (the key)
#36 first real cyclenothingnot needed. V1 proven does not have to come before the look.-

The content contract: one file per screen

One file per screen, kept in the repo next to the screen, for example system/dashboard/contract/numbers.contract.json. The design agent receives these files and the rules table. It may not edit them. A person (Dani) signs each one with a date; that is the freeze.

Each file lists

  • Screen id, ticket, who may see it (Dani, Max, Adnan)
  • Status: frozen on a date, or open with its blocking ticket
  • Fields: key, text key in texts.ts (German and English), source (view or function and column), format (formatCount, formatPercent, formatDate, formatTime, formatUsd), data-value yes or no
  • Order and grouping: what comes first, what the rows are (per channel, per week)
  • Rules that apply: R-numbers from the table above, e.g. a percent field lists R2, R3
  • States: loading, empty, failed, too few, so far
  • Actions: the only writes the screen may do

Rules for the design agent

  • May change: layout, colours, type, spacing, icons, charts that show the same values, animation, responsive behaviour, empty-state look.
  • May not change: which fields exist, their order of meaning, their text keys and wording, their source, their format, any formula, any data-value, any rule R1 to R18, any write.
  • May not touch: texts.ts, *-backend.ts, supabase/, tests/, the contract files. A needed change is a request to Dani, not an edit.
  • New wording or a new field is a new ticket, not part of the redesign.

A sample contract (one field, short)

{
  "screen": "numbers",
  "ticket": 17,
  "status": "frozen 2026-11-22 by Dani",
  "see": ["dani", "max", "adnan"],
  "rows": "one per period and channel, newest first",
  "fields": [
    { "key": "reply_rate",
      "label": "numbersReplyRate",              // key in texts.ts, de + en
      "source": "view numbers_by_week.reply_rate",
      "format": "formatPercent",
      "dataValue": true,
      "rules": ["R1", "R2", "R3"],
      "shows": ["period start", "base group", "count and total"],
      "belowBase": { "min": 30, "style": "grey", "text": "numbersTooFew" } }
  ],
  "states": ["loading", "failed", "empty"],
  "writes": []
}

The label key name is an example. Real keys are the ones already in texts.ts.

How the redesign is checked afterwards

CheckWhat it catchesHow
Full test suite stays green (904 of 904 on dev at the night run)A changed text, a lost data-value, a lost rulenpm test, npm run typecheck, npm run lint
check:numbers stays at 0 differencesA number that changed because of the markuprun on the live copy after deploy
check:dashboard and check:accessAnything visible logged out; a new writerun after deploy
New: contract testA field missing, an extra field, a field without data-value, a percent without period and basea test reads each contract and the rendered synthetic page and compares them
New: scope check on the diffThe design agent touched a file it may not touchthe diff may only change styles and the markup of screen files; texts.ts, backends, migrations, tests and contracts must be unchanged
Both languages, side by sideA layout that breaks with long German wordsscreenshots with synthetic.html (made-up data), via desktop-vision. No names or message text.
Pristine review, then Dani looksThe restno merge to dev without a clean run; no merge to main without Dani

5. What I need from Dani

DecisionMy recommendation
Start wave A now?Yes. Contract files first (one agent, short), Dani signs, then the design agent.
Drop the old “tracer” test card from the overview?Yes. It was the proof of ticket #10 and says nothing a person needs.
Where do the control-room parts go?A separate area, designed after the 7 questions are answered.
The 5 judge points (#38)Answer them soon: they decide what the verdict screen has to show. They are the biggest blocker of wave B. Defaults in T6-JUDGE-DESIGN-21-11.md are 28 days, 15 points, cap on never-found, show only, keep “booked”.
#8 dated yes, gate A34.live, the real Anthropic keyQuick answers that clear wave B and the live reader.

Read from dev at 3728bae and the open GitHub issues on 21-11-2026. Not verified live: no database, CRM or browser was used. Ticket numbers are the GitHub numbers, as the screen files name them.