Concept case study · 2026

Groundwork

CRM, rethought. The AI does the groundwork; your team makes every call.

A CRM where AI preps, drafts and answers, every line shows its source, and nothing saves until a person approves. From research to a coded prototype.

Role
Research, design, front end
Platforms
Desktop web and phone
Built with
Next.js, React, TypeScript
Ask about any account: a person picks “Why is Fernhill slipping?”, the AI reads emails, tickets, the last call and usage, then answers in three bullets with a source on every claim, three numbers, a suggested next move and suggested actions. Choosing “Draft it” drafts a note, and “Review it” opens Review, where the note waits under Drafted from Ask, ready to approve.

The story in six lines

  1. 01GoalA CRM that account managers keep current without the typing.
  2. 02Problem68% of sellers say note taking and data entry take the most time (Salesforce State of Sales).
  3. 03ApproachAI drafts the record from meetings, every line shows its source, and a person approves.
  4. 04DecisionEvery AI line waits for a person, over saving on its own. None of 13 similar products shows a source on every line.
  5. 05LaunchA concept: a working web and phone app, about 8,500 lines of TypeScript, with tests.
  6. 06ResultWhat I’d measure: drafts approved without edits, and meetings logged within a day.

On the phone

For the minutes between meetings

On the way to a meeting, the phone shows what to know, not a dashboard. After it, a minute logs it. Same rule as the desktop: the AI drafts, a person approves.

  • Next up: the next meeting and what changed, each line with its source.
  • Approve: swipe right to approve, left to dismiss.
  • Ask: the same sourced answers as the desktop.
  • Voice note: each sentence becomes a line to approve.

The recording plays the loop above. Try the working app with sample data.

The phone loop, recorded: from Next up, a person approves a waiting card, asks why Fernhill is slipping and reads the sourced answer, then records a voice note, whose words become lines to approve as Draft log lines.

01 · THE PROBLEM

CRMs are built for reporting, not for the people who fill them in

Account managers type for a dashboard above them. The data goes stale, so the AI on top can’t be trusted.

I started from the people who keep the record.

Three findings, shown in turn: 40% of a seller's time goes to selling; 68% of sellers say note taking and data entry take the most time; 76% of CRM users say less than half their CRM data is accurate.

Take the typing out of the week.

The AI drafts, the person approves, and the record is current by the end of the call.

BEFORE · THE RECORD IS A CHORE

  1. Prep from five tabs
  2. Take notes on paper
  3. Type the call in later
  4. A promise slips
  5. The record goes stale

AFTER · THE RECORD IS A BY PRODUCT

  1. Read the brief
  2. Talk
  3. Approve the drafted log
  4. Follow ups land on Your tasks

02 · RESEARCH

Briefs and automatic logs are now expected. Trust isn’t built in yet.

I read thirteen products that already put AI around the meeting, from Salesforce and HubSpot to Gong, Attio and newer AI first CRMs, against the six things Groundwork set out to do.

None of thirteen products shows a source on every AI line. So Groundwork competes on trust.

Interviews so far are simulated; real ones are next.

How many of 13 AI sales products do each thing, from their public pages
CapabilityYesPartlyNo mention found
Call log into the CRM931
Brief before a meeting733
Deal risk with a reason481
What changed since last time256
Person approves first337
Source on each AI line058
Thirteen products that put AI around the meeting, read from their public pages on Nov 6, 2026. Not hands on trials.

03 · ASK

Ask anything about an account. Every claim brings its source.

Ask answers in plain words, with a source after each claim.

  • 01ReadsEmails, tickets, the last call and usage, showing each step as it goes.
  • 02AnswersPlain words with a source after every claim, each one a click away.
  • 03Sums upThe three numbers that matter for this question, and one next move.
  • 04Changes nothingRead only, and it says so. Nothing reaches the record.

HOW IT WORKS

Approve, ask for a list, and keep going on the phone

Recorded from the working prototype, in three steps.

Approve drafts where they sit

AI writes drafts with a source. Approve, edit or dismiss in place.

Review: a person opens the source behind a drafted line, today’s call at 12:05, and the quote shows in place; they approve the line, then approve an opportunity Spotted by AI, which saves to the record at once.

Say the list you want

Type what you want. It shows how it understood you, as chips you can remove.

Accounts: a person points at Fernhill on the portfolio map and its numbers appear, then picks “quiet for 2 weeks with more than 10 stores” under Lists; the AI shows how it understood it as two filter chips with a reason beside each account, and removing one chip drops that reason.

Keep going between meetings

On the way to a meeting: read, approve drafts, ask. Nothing saves without you.

Mobile app: from Next up, a person opens the drafts waiting for them and approves one card, then opens Ask, picks “Why is Fernhill slipping?”, reads the answer in bullets with its sources, three numbers and suggested actions, and chooses “Draft it”, which offers “Review it”.

Designed for the moment the AI is wrong

One bad suggestion breeds doubt, so how sure the AI is and how people correct it were designed first.

  1. Price the 12 new stores as a separate expansion.

    CONFIDENCE MEDIUM · CHECK THIS

    1. It says how sure it is

    Every AI line carries its confidence. Medium means check this.

  2. Dismissed: Late data refreshes are their main complaint.

    SENT TO THE TEAM ·WrongOut of dateWrong source

    2. Saying no takes one tap, and says why

    Dismiss a line and tap why. Undo is always there.

  3. WRONG 1OUT OF DATE 2SOURCE 1

    3 corrections trace back to Ticket 4821. Worth checking that source first.

    3. The team sees the pattern

    Corrections gather by source, so a bad source gets checked first.

Try it: dismiss any line or flag an Ask answer in the prototype, then open Review.

04 · DATA VISUALIZATION

Every chart is built backward from a decision

A dashboard that only reports gets closed. Each chart here starts from a decision an account manager has to make, and ends where the decision is made. The portfolio map is the longest walk.

The portfolio map: accounts plotted by days until renewal against the eight week usage trend, bubble size showing stores. A shaded corner is labeled renewing soon and falling. The cursor rests on Fernhill Outfitters, with a dotted day line at 74 days and a tooltip giving health, renewal, usage and stores.The portfolio map: accounts plotted by days until renewal against the eight week usage trend, bubble size showing stores. A shaded corner is labeled renewing soon and falling. The cursor rests on Fernhill Outfitters, with a dotted day line at 74 days and a tooltip giving health, renewal, usage and stores.
01 · THE QUESTION ON THE WALLDays until renewal against the usage trend; the shaded corner is the one that costs money. The hover brings the exact numbers: Fernhill renews in 74 days with usage down 36%.
The account panel opened from the map: Fernhill Outfitters with its health tag, renewal, usage, last touch and store count on a night periwinkle block, then the next step, ten lines waiting for approval with a Review link, people, the renewal opportunity, and the latest interactions.The account panel opened from the map: Fernhill Outfitters with its health tag, renewal, usage, last touch and store count on a night periwinkle block, then the next step, ten lines waiting for approval with a Review link, people, the renewal opportunity, and the latest interactions.
02 · THE ACCOUNT BEHIND THE BUBBLESelecting the bubble opens the account in place: the numbers, the people, and what waits for approval.
Review: the Fernhill Outfitters quarterly review group with nine drafted cards, each carrying its source and confidence, with approve, edit and dismiss controls.Review: the Fernhill Outfitters quarterly review group with nine drafted cards, each carrying its source and confidence, with approve, edit and dismiss controls.
03 · IT ENDS IN A MOVEReview holds the drafted lines the chart led to, each with its source and confidence. Approving saves to the record; nothing moves without a person.

The rules the charts follow

  • Color never works alone

    Health is three solid colors and three words; confidence is bars that count as well as color. The three are checked for colorblind separation, so a row of accounts still sorts itself with the color gone.

  • Periwinkle is data, rose is action

    Marks and trends are periwinkle; the one warm color on the page is the rose of the actions. A chart can sit beside a button without competing for the eye.

  • The exact number is one hover away

    The surface shows the shape; a cursor line with its day label and a tooltip carry the numbers. The same data sits in a table below the chart, for screen readers and for anyone who wants rows.

  • Readable in both themes

    Text on every chart passes WCAG AA in light and dark, and the marks hold at least 3:1 against their cards.

How the palette was chosen

The colors came out of a recorded exploration, not a mood board: twelve rounds, each a set of options compared on the same screens.

  • 01 · Dark and glossy first: glass cubes, faceted tetrahedra, prisms. Striking, and too heavy for a tool used all day.

  • 02 · So the palette went light and the art carried the weight: six directions, from pearl cubes to ink marble.

  • 03 · The shards read as blades, so they grew into glass leaves: broad ones against long arching ones. Broad won.

  • 04 · The leaves in all six pastel palettes, compared on the same screen.

  • 05 · The last two blended: periwinkle warming to rose quartz, led from either end.

  • 06 · Both blends at night. Rose leads won: on a periwinkle page, the rose actions are the one warm thing.

Then the numbers: white on the rose button 5.1:1 in light and 4.5:1 in dark, rose draft text 6.1:1 on cards and 8.5:1 at night, periwinkle chart marks 3.7:1 and 5.8:1 against their cards. The whole exploration, image by image, is in the repo.

05 · DESIGN SYSTEM

Calm to use all day, rose where the AI asks you to act

Space and rules instead of boxes, one friendly typeface, and one material: soft periwinkle blocks with glass leaves, night periwinkle in the dark.

Rose is the one warm color, for the AI and the actions it asks for. Periwinkle carries the data.

See the tokens and contrast checks

  • Page

    #f9f8fc / #11111c

  • Mist

    #ece9f5 / #24243a

  • Ink

    #1e2140 / #eceefa

  • Rose: AI, actions

    #b03c77 / #f394c4

  • Draft wash

    #f0f2fd / #1f2140

  • Charts

    #6576d4 / #8f9cf0

Left half light, right half dark. Every text color passes WCAG AA on every background in both.

Three directions, one kept

Three directions, judged on one question: does someone who can’t see color still know a line is a draft?

  • LedgerDROPPED

    Calm and editorial, one deep green

    Drafts were marked by italics alone, which a screen reader can’t hear and low vision can miss.

  • SignalKEPT

    Dense and precise, one electric blue

    Chosen: DRAFT is a word, so everyone gets it, and density suits a tool open all day. Its blue later became today’s violet.

  • Margin noteDROPPED

    Warm and human, a clay accent

    The clay sat too close to the warning colors a risk flag needs, and drafts relied on a tint.

The three, as they were judged: see the directions page.

06 · BUILT IN THE OPEN

Every prompt, decision and commit is public

Built by prompting AI, with a record for every decision and prompt.

It is designed from scratch and uses nothing from any CRM I worked on before.

07 · BUILT IN CODE

How it works, and why it is built this way

An AI CRM is mostly rules about trust, and they only feel real when you can approve a line and watch the record change.

About 8,500 lines of TypeScript, over 100 commits.

WHY THIS STACK

  • Next.js and React

    Web and phone from one codebase.

  • TypeScript, strict

    A line without sources fails the build.

  • Tailwind CSS

    Tokens for light and dark, contrast checked.

  • No component library

    Focus and labels designed, not inherited.

THREE CHANGES I’D WALK THROUGH

  1. 1. One gate for everything the AI writes

    Problem. Every new path to the record was a chance to skip review.

    What I changed. One gate for every line, with a test that proves it.

  2. 2. Phone and web share one store

    Problem. Phone and web had to agree.

    What I changed. One store and one commit function for both.

  3. 3. “Drafted”, but where?

    Problem. A confirmation pointed to a draft with no way to reach it.

    What I changed. Review it now opens the draft, with focus moved there.

THE RULES, CHECKED IN CODE

Nothing saves without you, and tests prove it.

See the tests (opens GitHub in a new tab)See the store (opens GitHub in a new tab)All the code (opens GitHub in a new tab)

WORKING WITH AI

AI drafted components and tests. I read every change and made every call.

  • Saving with nothing approved saves nothing
  • Approving a log line doesn’t save it; Save does
  • A record fix saves as soon as it is approved
  • An edit counts as an approval and keeps the words
  • A draft from Ask waits in Review until approved
  • A task from Ask goes to the top of Your tasks, once
  • A dismissed line can say why, and the team sees it
  • A flagged Ask answer reaches the team; flagging again takes it back

08 · THE TEST I’D RUN FIRST

Approve every line, or approve the meeting?

Approving line by line keeps the core rule strict, but it’s work, and work made CRMs go stale.

So the first test questions the rule itself.

A · One line at a timeToday’s design
B · The meeting at onceThe challenger
Hypothesis
Approving a meeting at once logs more meetings the same day, without more mistakes.
Who sees what
Split by person, not by meeting.
Main number
Meetings with an approved log on the same day.
Guardrails
Edits after saving, sources opened, lines flagged later.
How long
Four weeks, so each person has enough meetings to compare.
Decision rule
Ship B only if same day logs rise and corrections don’t.

09 · NEXT

What I’d want to learn next, and how I’d measure it

A concept, so no outcomes yet. What I’d measure:

What I’d do differently

Talk to account managers first. Real interviews would have tested the core bet sooner.

  • Do people approve drafts as they are?Drafts approved without edits.
  • Is the record more complete?Meetings logged within a day.
  • Do people trust Ask?Answers opened to their source.

Try it.

Ask, approve, make a list. Next: real interviews.