Case 06 · Inqom · Product design · UI/UX · Accounting
Inqom already flags anomalies and accountants close them without reading. I redesigned bank reconciliation around three ideas. When a bank line won't match, its receipt, its history and the balances now appear right next to it. What was checked is kept. The AI suggests an account and explains why, but never decides.
My role
This is a business case for Inqom, done in two days and presented to the product team. I didn't design the accounting rules or the existing product. I designed how an accountant understands, decides and hands over a bank line that won't match.
What I was given
The brief, user verbatims and product data: alert usage, Excel exports, help center visits. Plus the existing reconciliation screen.
What I owned
The synthesis, the scope, the journey, every screen in Figma, the state matrix, the MVP split and the test protocol.
Who I worked with
I worked on this case alone. Every design decision on this page is mine, from the first sketch to the last screen.
Context
Inqom is accounting software used by firms to keep their clients' books. Reconciliation means matching every bank line to an accounting entry. Most lines go through on their own. The ones that don't are where the time goes.
When a line won't match, the screen only says "not reconciled". The document is in one place, the history in another, the balances in a third. Doubts get settled by phone, email, or Excel. None of it is kept.
Before: 14 alerts on the file, one "close all" button, and nothing that says what is blocking each line.
Two profiles share that pain, and the design had to serve both: the one who produces the entry, and the one who reviews it.
Julien · accountant, 6 years, ~50 files
Loses time finding the document and the history. Exports to Excel to see everything flat. Starts from zero when the client answers. His name is on the entry, so he only accepts a suggestion that explains itself.
Nadia · team lead, 4 accountants
Her review load is the heaviest. She doesn't know why an entry was made this way, and the accountant has forgotten too. She wants to save time without the AI doing the job: juniors need to keep learning.
The problem
The interviews pointed one way. The data pointed another. I designed for what actually happens.
Julien said he reads every alert. In reality, 72% are closed without action, in bulk. Anomalies are already detected. Adding detection would only add noise.
Julien said he doesn't need help. He calls Nadia two or three times a week and exports to Excel. Fewer than 1 in 20 users opens the help center.
Julien puts a line on hold and emails the client for a receipt. When the answer arrives days later, he has forgotten what he already checked.
Nadia doesn't know why an entry was made this way. She calls the accountant back, who has forgotten too. Juniors don't dare to call.
So the problem wasn't detection. It was that the reasoning behind each line got lost between tabs, phone calls and Excel.
Synthesized from the verbatims and product data in the brief.
Where I invested
Julien forgets what he checked. Nadia can't see what was checked. I focused on the bank line that won't match.
01 · Gather
No AIThe document, the history and the balances in one place, on the line.
02 · Suggest with reasons
✦ AIThe AI suggests an account, explains why, and says what is still missing before it can be sure.
03 · Keep the trace
No AIWhat was checked and decided. Julien finds it again, Nadia reads it.
Left asideAlert triage (V2) · automatic validation · a dedicated review view for Nadia
What the brief demanded
The accountant's name goes on every entry, so his reputation is on the line, not the software's. The design could not make the AI look smarter than it is. Every decision here is a direct answer to a constraint.
Constraint 01
Julien's name is on the entry. He won't validate what he doesn't understand.
Decision
Every suggestion needs a human click. Everything can be undone.
Trade-off: less time saved on obvious cases.
Constraint 02
"If the tool is wrong once, I stop trusting it."
Decision
The suggestion lists reasons taken from the data, and what's missing to be sure. When the AI isn't sure, it says so clearly, with the data to back it up.
Trade-off: a less spectacular display, less flexible wording.
Constraint 03
72% of alerts are closed without action.
Decision
A "To do" column says what blocks each line. Secondary information moves into the panel.
Trade-off: less information at a glance in the list.
Constraint 04
"Why not", then "if it's the AI, no".
Decision
Repetitive cases stay manual. It also answers Nadia's wish: juniors keep learning by doing the work themselves.
Trade-off: repetitive work remains.
The flow, step by step
The main journey follows a single card payment: CB STATION, €86.70. It is blocked on day 1, waits for the client, comes back on day 4, and ends in Nadia's review.
Each line now says what it's missing. One click opens a panel beside the list: the document, similar past payments, and a suggestion with its reasons. Here, three payments at the same merchant in 2024 were booked to 6251 Travel. What's missing: no receipt confirms it's a business expense.
Since the document is missing, the main button is "Put on hold", not "Validate". Julien picks the reason, and a pre-filled message goes to the client. The line moves to the suspense account and will come back by itself.
The line rises to the top: "Document received". The trace shows first: what was checked, what was suggested, what was asked. The receipt confirms the date and amount, and the client confirms it's business fuel. What was missing is now resolved. Julien accepts, and can still undo.
No starting from zero.
The trace is saved automatically and can't be edited. Nadia sees who decided, what was booked, and why, in three lines. She can tell the AI's steps from Julien's.
AI steps and human steps, clearly separated.
When it doesn't go to plan
The happy path proves nothing. Trust is won when the history disagrees, when there's nothing to go on, or when Julien changes his mind.
History disagrees: both accounts shown, nothing preselected.
Not enough to go on: the AI suggests nothing rather than guess.
| Situation | What the screen does |
|---|---|
| Two accounts in the history | Both shown, neither preselected |
| No history | The AI suggests nothing and says why |
| Julien corrects the suggestion | His choice applies, the trace keeps both the AI suggestion and his choice |
| Julien undoes after validating | The line goes back to not reconciled |
| The client doesn't answer | The line shows its age, follow-up in one click |
The contract with the devs
Rows are the line's state. Columns are what the "To do" column can show. Each cell says whether the combination exists, what it means, and where it appears in the journey.
Rule 1
If two apply, the most urgent wins: Document missing › Document received › Account suggested › none.
Rule 2
On hold or reconciled, there's nothing for Julien to do: the column stays empty.
Rule 3
Red = blocked. Green = good news or done. Purple ✦ = AI. Orange = waiting. Everything else is grey.
Scope
The two batches without AI come first and solve most of the problem on their own. Batch 3 then adds the AI suggestion, on top of a context the accountant can already check.
Batch 1
No AIBatch 2
No AIBatch 3
✦ AIAnnotated for handoff
Label, amount, date: from the bank statement. A single label, the most urgent.
Searched in the client file. States: found, missing or received.
Same merchant, 3 at most, link to the general ledger.
Only if the history agrees. Otherwise two accounts, or nothing. Reasons drawn from the data.
The main button follows the state: document missing → Put on hold.
Saved automatically, read-only: what was shown and what was decided.
How I worked with AI
It suggests with its reasons. I check. I decide. The same rule I designed for the product applied to how I made it.
AI did
Translated the brief and the accounting vocabulary into plain terms, so I could understand the domain better and faster.
I decided
Built my own understanding of reconciliation from it, then framed the problem and made every design call myself.
AI did
Laid out the journey diagram, the annotated screen and the matrix visuals, and suggested some layouts.
I decided
Built every screen in Figma myself, the matrix and its three rules, and all the edge cases.
AI did
Re-read my mockups for inconsistencies.
I decided
Fixed my own data errors (balances, dates, debit and credit) and the ambiguous language, such as replacing "Suggestion seen" with "Account suggested".
AI widened what I could check. It never signed anything.
Validation · test plan
7 participants: 5 accountants, 2 of them juniors, and 2 team leads. 45 minutes on the prototype, thinking aloud, with an observer taking notes.
Task 1
Does he read the reasons? Open the history? Leave the screen?
Task 2
Does he pick the most frequent account by reflex?
Task 3
Does he find what he did without searching? Re-check it anyway?
Task 4
Can she tell the AI from Julien? Validate without calling?
Success
They decide without leaving the screen, explain their decision in their own words, and don't re-check what's in the trace.
Red flag
Someone accepts without reading the reasons.
How I'll measure it
Main metric
Time between opening an unreconciled line and the decision.
Weekly Excel exports (6 in 10 users today). Lines reopened before deciding.
Days spent in the suspense account.
Suggestions accepted, corrected, refused. Undos after validation.
Baseline measured over 4 weeks before setting targets with the PM.
The takeaway
The strongest AI decision in this project was where not to use it. Gathering the context and keeping the trace solved most of the problem on their own.
The AI came last, and only where it could explain itself.