Accenture Ludio R&D · Learning & Performance · 2020–2021

Flow Journal

An internal Accenture Ludio R&D project that reimagined the performance review. Instead of one stressful annual write-up, Flow Journal asked one targeted question in the flow of work, stored answers privately, and synthesized the employee's own words into insights they could choose to bring into coaching.

Role Product Designer
Org Accenture Ludio (R&D)
Pilot 4 Weeks · N=42
Key Metric 4.2× Actionable Coaching Moments
What this project proves
  • Advanced research — a diary study, calendar telemetry, and Wizard-of-Oz testing pinpointed reflection latency as the real failure, not low motivation.
  • In-flow learning design — a 45-second capture loop that fits real work rhythms instead of a separate journaling chore.
  • Trust-sensitive AI — synthesis acted as a mirror on the employee's own words rather than authoring a performance story for them.
  • Systems thinking — one loop connected private capture, pattern synthesis, and the manager 1:1.
01 / Product Opportunity

The disconnect between daily work and performance reviews.

Learning happens every day. Employees solve hard problems, navigate client conflicts, and develop new skills in the flow of work. But because there was no lightweight way to capture these moments, the evidence evaporated. By review time, people relied on recency bias, reconstructing a whole year from a blank form.

Employees

"I struggle to write my self-review because I forget the specifics of what I accomplished and learned months ago. I just remember that I worked hard."

Managers

"I want to coach my team on their actual challenges, but I only have visibility into their final deliverables, which are lagging indicators of their performance."

Example · the legacy way

Annual self-review form

Start typing… due in 2 days

A blank form, months after the work. This is the moment the evidence had already decayed — the problem Flow Journal set out to solve upstream.

Root-cause diagnostic

Reflection latency was the product problem.

The issue wasn't that employees disliked reflection or coaching — it was that the system asked for it after memory had already decayed. The defining design move of this project was relocating capture from formal review moments into natural work pauses.

Legacy self-review
~90 days later
Flow Journal prompt
45 seconds
02 / Research Deep Dive

Capture timing mattered more than motivation.

We didn't just ask people if they liked journaling. We triangulated a diary study, calendar telemetry, and Wizard-of-Oz testing. The non-obvious insight: employees were learning constantly. The system was simply asking them to reflect long after the details were gone.

Method 01
Diary Study
N=12 consultants · 2 weeks

Tracked how often participants recognized a learning moment versus how often they could recall specifics by Friday.

Method 02
Calendar Telemetry
N=42 schedules · 4 weeks

Analyzed inter-meeting gaps to validate whether an in-flow reflection window actually existed.

Method 03
Wizard-of-Oz AI Test
Prototype comparison

Compared AI-authored reflections against AI synthesis of the employee's own words.

75%
Recall Failure
100% of participants learned something new, but 75% couldn't recall a specific example by Friday. The problem wasn't learning; it was reflection latency.
9 min
Inter-Meeting Gap
Calendar telemetry revealed the median gap between meetings is just 9 minutes. If an intervention takes longer than 2 minutes, it gets deferred and dies.
-29 pts
AI-as-Author Drop
Wizard-of-Oz testing proved that when AI tried to write reflections on the employee's behalf, trust scores fell 29 points. Synthesis of user-authored words was preferred.
Telemetry: Inter-Meeting Gap Distribution
0-2 min
27%
2-5 min
31%
5-15 min
29%
15+ min
13%

73% of inter-meeting gaps are longer than 2 minutes, proving the addressable window exists.

Diary Study Snippet

"I know I solved a huge problem with the client data pipeline on Tuesday, but it's Friday and I honestly can't remember how I fixed it. I just remember feeling stressed."

— Participant 04, End of Week 1
03 / Strategy & Principles

Three principles drew the trust boundary.

I translated the research into three named principles, then used them to negotiate scope with product, engineering, and learning stakeholders. They decided what the product would refuse to do as much as what it would do.

Principle 01

Quiet Coaching

Intervene only during natural calendar pauses. Never interrupt deep work — the nudge waits for the gap.

Principle 02

AI as Mirror, Not Author

Synthesize and cite the employee's own words. Never generate a fictional growth story on their behalf.

Principle 03

Private-First Architecture

Raw reflections stay employee-owned. Sharing is explicit, granular, and reversible.

Said yes to
  • Short, contextual prompts inside existing work surfaces.
  • Evidence-backed synthesis with quoted source material.
  • Employee-controlled handoff into manager 1:1s.
Said no to
  • Always-on manager analytics — would turn reflection into surveillance.
  • AI-written self-review drafts — users rejected them as inauthentic.
  • Gamified streaks — encouraged performative completion over honest reflection.
04 / Personas

Designing for two competing priorities: privacy and visibility.

We synthesized our research into two key user archetypes. The product only worked if it could hold the employee's absolute need for privacy and the manager's need for actionable coaching visibility at the same time.

Aisha

The Mid-Career Consultant
Behavior

Picks up implicit knowledge constantly but never writes anything down. Avoids tools that feel like "extra work" or HR surveillance.

Goal

Wants to notice what she's learning while it's happening, so she doesn't have to invent a growth story at performance review time.

Design Implication

Make capture fast, private, and anchored to the work moment itself.

Dev

The Coaching Manager
Behavior

Wants to coach his team well but only sees their final deliverables. Defaults to generic advice because he lacks insight into their daily struggles.

Goal

Wants coaching to be anchored in the actual patterns and challenges his reports are experiencing week-to-week, without micromanaging.

Design Implication

Share summarized themes only — and only after explicit employee consent.

05 / Core Product Loop

Capture, Synthesize, Perform.

I translated the research into a frictionless loop: detect a natural pause, ask one relevant question, store the answer privately, synthesize patterns only when enough evidence exists, and let the employee decide what becomes coaching material.

Phase
Employee Frontstage
System Backstage
UX Constraint
1. Detect
Subtle nudge appears only between meetings.
Calendar API scans for gaps ≥ 2 minutes. Maps meeting title to Prompt Taxonomy.
Quiet Coaching
2. Capture
Types 1-2 sentences directly in Teams. Hits send.
Data encrypted and saved to isolated employee-owned vault.
Private First
3. Synthesize
Reads new "Growth Pattern" summarizing their past week's entries.
Model extracts themes once threshold (14 entries) is met. Anchors themes to exact quotes.
AI as Mirror
4. Perform
Clicks "Add to 1:1 Agenda" to securely forward theme to manager.
Strips raw quotes, sends high-level theme to HR/Performance DB.
Consent Gradient
06 / Interaction Design

The 45-second micro-journal.

A journaling tool for busy consultants cannot feel like homework. The capture interface lived inside their existing workspace. A nudge asks one context-aware question, the user types a sentence or two, hits enter, and the interaction is over in 45 seconds. It took three iterations to get there.

Design evolution · the capture surface

Where should reflection live? We killed two versions first.

Dedicated journal app

Open your reflection space

Asked users to context-switch into a separate learning product, away from their work.

Too much friction.

Participants understood the value, but the separate app recreated the exact deferral pattern of the formal self-review — "I'll do it Friday" — and by Friday the details were gone.

"I would save this for Friday and then forget what happened."

— Pilot participant
Median completion time: 6.5 minutes — far outside the window
End-of-day digest

Three moments to reflect on

Batched the day's meetings into one evening summary with prompts for each.

Better timing, weaker specificity.

Daily batching solved the interruption concern, but users had already lost the texture of morning events by 5pm. Recall quality improved over baseline — but not enough.

Recall quality: +12 pts vs. baseline — still losing morning detail
Flow Journal Bot · in Teams

You have 9 minutes

What was the turning point in that last client presentation?

The pause became the product surface.

The final nudge appears only between meetings, asks one question tied to what just happened, and makes the expected effort legible up front. No app. No context switch.

Median entry time: 45 seconds — inside the 9-minute gap
Example · prompt taxonomy

Context-aware questions, not generic journaling.

After a client presentation

"What was the turning point in that presentation?"

After a 1:1 with a report

"What did you learn about how your report works best?"

After a blocked problem

"What finally unblocked it — and what would you try sooner next time?"

After pushback or conflict

"Where did alignment break down, and how did you respond?"

The system mapped a taxonomy of ~120 prompts to calendar signals and project phases, so the question always felt relevant to what just happened.

FJ
Flow Journal Bot
FJ
Quick Reflection
You have 9 minutes before your next meeting.

What was the turning point in that last client presentation?
Saved to your private vault. (14/15 towards next insight)

Live coded mockup — try it. Saving routes the entry to the private vault; snoozing defers until after the next meeting.

07 / Product System & Trust

Separating reflection from surveillance.

The terminal risk of any enterprise journaling tool is that employees refuse to use it if they feel a manager is reading their raw thoughts. So I designed a strict "Consent Gradient": private by default, summarized by the system, and shared only when the employee explicitly chooses. Getting the synthesis card right was the hardest design problem in the project.

Design evolution · the synthesis card

How do you make AI synthesis feel like evidence, not judgment?

AI-generated narrative

"You struggle with ambiguity"

The system wrote conclusions about the employee's growth in its own voice.

Felt presumptive — the clearest trust failure in the project.

Users rejected conclusions that sounded like assessment. Even accurate themes read as the system judging them with words they never wrote.

Trust score impact: -29 pts
Concise theme

Pattern: Client ambiguity

A short, neutral theme label with no source material attached.

Useful, but ungrounded.

Participants wanted to know what the system was using to make the claim. A theme without receipts still felt like a verdict.

Trust rating: 3.1 / 5
Proposition with receipts

Consider this pattern

You often create momentum by reframing conflict around shared criteria — with your exact quotes cited underneath.

Evidence changed the interpretation.

The card became a mirror: a theme the employee could inspect, edit, keep private, or share. Citing their own words moved the locus of authorship back to them.

Voluntary share opt-in: 82%
Example · private vault, employee-only

The raw entries the pattern was built from.

Oct 12

"We were treating alignment like agreement. I reframed the conversation around shared success criteria."

Oct 18

"Instead of arguing features, I pulled the client back to our shared success criteria."

Oct 23

"The standup unblocked once we agreed on what 'done' actually meant for this sprint."

These stay private. The system only proposes a theme once enough evidence exists — and the employee decides whether it ever leaves the vault. Below is what the synthesis looks like.

My Vault
Performance Insights
Manager 1:1 Prep
Settings

New Growth Pattern Detected

Based on 14 private entries this month, the system synthesized the following theme.

Conflict Resolution
Theme: You've successfully navigated complex client ambiguity and maintained project alignment during scope shifts.
Evidence from your vault:
"I realized the team is stuck because we're treating alignment like agreement." (Oct 12)
"Instead of arguing features, I pulled the client back to our shared success criteria." (Oct 18)
Added to your upcoming 1:1 agenda with Dev.

Live coded mockup — the Consent Gradient in action. The employee chooses whether a synthesized theme stays private or enters the 1:1 agenda.

08 / Product Validation

Proving the model works.

In a longitudinal 4-week pilot (N=42), we tested the prototype against the legacy self-review process. Employees walked into 1:1s with concrete, synthesized evidence — and the trust architecture held.

4.2×

more actionable coaching moments per manager 1:1 — from 1.2 to 5.1 per session.

82%

of employees voluntarily chose to share synthesized insights, proving the privacy architecture and consent gradient worked.

Actionable coaching moments per 1:1
Legacy
Flow
1.2 → 5.1
Performance-prep utility (NPS)
Legacy
Flow
-15 → +42
Time to capture a reflection
Legacy
Flow
1-2 hrs → 45 sec
Honest limitation

The pilot validated the behavioral hypothesis and informed Ludio's continuous learning strategy — but this remained an internal R&D concept, not a public product launch. Manager-side analytics demand was an open risk we deliberately left unresolved rather than compromise employee trust.

09 / Takeaways & Leadership

Learning as a continuous product.

While this exact prototype remained an R&D concept, the core interaction model — targeted in-flow capture leading to user-controlled performance insights — became a foundational blueprint for Ludio's continuous learning strategy. The lesson: the best way to improve performance isn't always more formal training. Sometimes it's helping people capture and apply the learning they're already doing every day.

01

Negotiated the trust boundary

HR stakeholders wanted manager-facing analytics. I made the case — with the Wizard-of-Oz data — that visibility would kill the behavior the business outcome depended on. Raw entries stayed employee-owned.

02

Designed the edge cases, not just the happy path

Defined model confidence rules: synthesis stays silent until 14+ entries exist, preventing premature or generic insights from eroding trust in week one.

03

Scoped the pilot to the riskiest question

Cut the broad HR-platform ambitions and shipped only the prompt → vault → insight → share loop, so four weeks of pilot time tested the core behavioral hypothesis.

"The design challenge was never proving that reflection matters. It was designing the smallest trustworthy behavior that could turn daily work into transferable learning."