Smart Fill: AI data entry for community engagement records

Smart Fill: AI data entry for community engagement records

Source-linked answers, honest blanks and AI web research that cut entry time by about 35%.

Source-linked answers, honest blanks and AI web research that cut entry time by about 35%.

Collaboratory is where ASU and other universities record the work they do with their communities: food drives, education programs, local partnerships. That data ends up in national reporting, so it has to be right.
I redesigned Smart Fill, the AI that fills in these records from a news article. Every answer now links back to where it came from, the AI leaves a field blank when it isn't sure, and it searches the web for missing details. People spend time only on the fields that need them, and entries take about 35% less time.
Where I came in
In my first week, I got to use both versions of Collaboratory: the original, where we filled every field by hand, and the AI version engineering had just launched.

The AI version was built one assumption: entry is slow because there are many fields to type. So it parsed the article and filled every field.

I expected it to save me time. It didn't. With the manual version, I read the article and filled the form.

With the AI version, I still read the article, and then checked every answer the AI gave me. My time per entry went up.

Problem at hand

Each entry took 15 to 30 minutes. The AI parser filled the form, but didn't show where its answers came from, so people still read the article and checked every answer. The AI saved typing, not time.

What testing showed

How I tested
I tested the current AI version with 12 participants, using the same 3 articles. Each was completed twice: once with AI, once by hand. I timed every entry and averaged across participants.

The bias I had to manage: doing the same article twice teaches you the answers. So I made two choices:
AI round first

Any familiarity would help the manual round, not the AI one, so the results could never flatter the AI.

AI round first

Any familiarity would help the manual round, not the AI one, so the results could never flatter the AI.

Separate sessions

I spread the rounds out so people wouldn't remember the answers.

What I found
People reacted in two opposite ways
  1. Over-trust. When checking feels pointless, people stop, and a wrong answer reaches the dashboard looking like a right one.
  1. The role flip. People went from doing the work to auditing a system they couldn't see into.
"Now I'm the manager. I have to check the article and the AI."

"Now I'm the manager. I have to check the article and the AI."

"Why am I doing double work? The AI already did it. I'll just send it."

The tension these create: push people to verify more and they drift back to manual; make it frictionless and they rubber-stamp it. Verification had to be fast enough that people actually do it, and targeted enough that they only do it where it matters.


The tension these create: push people to verify more and they drift back to manual; make it frictionless and they rubber-stamp it. Verification had to be fast enough that people actually do it, and targeted enough that they only do it where it matters.
Design principles
Icon
Verify at a glance

Checking an answer should take seconds, not a re-read.

Icon
Verify at a glance

Checking an answer should take seconds, not a re-read.

Icon
No evidence, no answer

If there's no source, the AI leaves it blank and indicate.

Icon
No evidence, no answer

If there's no source, the AI leaves it blank and indicate.

Icon
Flag what needs review

Point people to the risky fields, so the rest move fast.

Icon
Flag what needs review

Point people to the risky fields, so the rest move fast.

Design Process

Exploring the problem
Each exploration started from a problem I saw in testing. Some ideas worked, some I discarded.
Exploration 1: A browser extension

What I built

A side panel, like Jobright, that opens over any article you're reading. Add it in one click, without opening Collaboratory, and review it later.

Why it failed

Parsing an article takes time, so people sat waiting on the page they were reading. Running the AI outside Collaboratory also brought engineering constraints the team couldn't take on.

Insight

Fast capture doesn't help if the scan still makes people wait.
Exploration 2: One workspace. Findable answers. Form and AI in one window.

What I built

Everything inside Collaboratory. The AI fills the form, and the person reviews it on the same screen.

Why it worked

The scan runs once, in one place, and people check answers right where they work, with no switching between tools.

Insight

Fast capture doesn't help if the scan still makes people wait.

DESIGN DECISION 1

With the AI and the form on one screen, the next question was how to show where each answer came from. I tried three ways:
V1: The answer with a quick summary below

AI summarized where in the article it found the answer.

V2: The answer with a citation underneath.

People still had to find that sentence in the article.

V3: Highlight in the article beside the form.

Select a field, and the passage the AI used highlights.

Why Option V3 worked

The AI already finds the passage to get its answer, so showing it costs almost nothing. Checking goes from a search to a glance.

DESIGN DECISION 2

Once people could see where each answer came from, three gaps became obvious. Each one led to the next design change.
Gap 1: The article didn't have the answer, The AI still filled the fields

Fix: with no direct evidence, the field stays blank, with suggested answers below for the person to pick from the multiple options

Gap 2: Short articles left out key people, like a unit's VP or a college representative.

Fix: the AI searches the web for them and shows the link. Web answers are less reliable, so they had to look different from article answers.

Gap 3: People didn't know which fields to check first. Answers now came from the article, the web, or nowhere.
Option 1: Traffic light indicators

Why I dropped it: yellow read as "probably fine," so people skimmed, and red read as "error" instead of "your call."

Option 2: Source status tags

Neutral styling. No color implies "safe" or "broken." The words carry the meaning and also gave instruction to user what to do next.

DESIGN DECISION 3

Identifying the correct entries

The tension

Collaboratory is for community engagement, so filtering the right enteries was very crucial

The call

First screen asks for the article link, the activity owner and four qualifying questions together. Any "no" ends the flow with a clear message that this isn't community engagement.
Show the AI working

The tension

A blank wait while the AI scans gives people nothing to trust when the answers appear.

The call

A loader with a step list (scanning the document, checking the Collaboratory platform) and a scanner animation, so people see what the AI did before they're asked to check it.
Three review layouts, one decision

The tension

This is where people decide whether to trust each answer.

The call

A split view, with the five-step form on one side and the article on the other. Highlights follow the field in focus, and a drag handle lets people give more room to whichever side they're checking.

Reflection

What I'd do differently
I'd tie the confidence signal to the source from the start, instead of shipping colors and correcting later. I'd also measure accuracy alongside time in the first study, since accuracy is what the stakes demanded.
Icon

AI's job isn't to produce answers. It's to produce answers people can afford to trust.

If checking costs as much as doing, you've built a second job, not a shortcut.

Icon

Abstaining is a feature.

A system that knows when to say "I don't know" earns more trust than one that always has an answer.

Icon

Design can't start after AI ships.

V1 was a reasonable engineering solution to the wrong problem. The problem framing is design work.

Pull up a chair.
The kettle’s always on.

Most of my best design calls started as a chat over chai. Building something tricky? Bring the problem, I'll bring the chai. Or just pick a side below and say hi.

PERSONNEL 01

back

back

MY TOOLS

Figma · Framer · Notion

back

back

back

back

before we work together

• I'll ask "who's this for?" a lot

• I'd rather show than tell. I'll build it in code and send you a link.

• Teaching made me a better designer.

• A little OCD, about life in general.

• Chai first, critique second.

FILE NO. 04453

*************

everything you need to know before we work together. I'm organised by nature, intentional by design

I'm Samiksha Jain, a product designer in the US.

My expertise spans fintech, enterprise SaaS, internal tools and AI products.

• Thinking in Systems by Donella Meadows • Before the Coffee Gets Cold by Toshikazu Kawaguchi

CLOSE FOLDER

ABOUT ME

personal file on the designer behind the work.

Samiksha Jain

Product Designer

Say hi!

Ideal weekend

Best Bagel in NYC

Pull up a chair.
The kettle’s always on.

Most of my best design calls started as a chat over chai. Building something tricky? Bring the problem, I'll bring the chai. Or just pick a side below and say hi.

Samiksha Jain

Product Designer

Say hi!

Ideal weekend

Best Bagel in NYC

Pull up a chair.
The kettle’s always on.

Most of my best design calls started as a chat over chai. Building something tricky? Bring the problem, I'll bring the chai. Or just pick a side below and say hi.

Samiksha Jain

Product Designer

Say hi!

Ideal weekend