Helping sales managers understand performance changes
I moved the product from AI scoring toward evidence-led investigation, then stopped building when discovery showed the causes sat outside the system's data.
My role
Product Designer
Ownership
Discovery, design, React v1 build
Project
Independent project · 2026
Finding, evidence, and manager context
Outcome
Sunset after 10+ discovery conversations showed that performance changes depend on factors the system could not see. No paying customers.
- 10+
- discovery conversations
- 2
- prototypes: React v1 and the later investigation prototype
- 3
- requirements: fit existing tools instead of adding a dashboard, reduce cognitive load, include business context
Key decision
Stopped building. Performance causes sat outside the system’s data, so a second build would have answered the wrong question.
Rejected: Keep developing the investigation prototype.
Problem
A performance change needs explanation. A score alone does not provide the context needed to act.
My responsibility
Challenged the scoring model, set a new direction, and designed a workflow from finding to human decision.
Product direction
Manager feedback exposed two gaps: dashboard numbers lacked context, and AI scores were hard to trust. I removed the dashboard from the current workflow and brought findings, source evidence and manager context together.
Assumption I changed
The early idea used employee reports and KPIs to produce AI scores. The new direction gives managers findings, evidence, and room to add context.
Early assumption
Set KPIs
Set Employee reports
AI Scores
Coaching
In discovery conversations, one manager said they did not trust AI scores. Another described investigating why those patterns occurred as the bigger challenge.
New direction
Collects data
Add context
Manager decides
Findings
The system prepares the evidence. The manager judges what it means.
AI-assisted research
Tools: Fireflies, Google Drive and ChatGPT for interview synthesis, checked against the transcripts.
Design changes from feedback
Unclear dashboard numbers led me to remove the dashboard and narrow the current workflow. Investigating patterns was already part of one manager's job and a bigger problem for another. Distrust of AI decisions informed visible evidence, missing context and manager control.
Evidence and control
A finding should help a manager investigate. The interface separates what changed, possible reasons, and the decision.
Evidence
Show the change and supporting signals before suggesting a possible cause.
Uncertainty
Label missing context so a possible reason is not mistaken for an established fact.
Human context and judgment
Let the manager add context and choose what happens next.
Traceability
Store the action alongside the evidence and context used to make it.
Edge cases
A finding changes when a manager or employee adds context. The record keeps the evidence, context and decision together.
Default state
Employee context and decision made
Both contexts added and summary updated
Earlier version · Evaluation and patterns
Earlier prototype: employee scoring
These screens show the React v1 scoring prototype before I changed direction.
Earlier RAG decisions
In the earlier scoring product, I designed the retrieval-augmented generation (RAG) assistant around a selected set of reports, people and dates. Answers linked to source reports, and the assistant was set up to decline questions outside the retrieved evidence.
Choose where AI judgment belongs
Numeric criteria used targets and deterministic checks. Judgment criteria used weighted rules and report quotes to support the score. This kept numeric checks separate from AI interpretation.
Keep a human review path
Managers could override a score with a reason while preserving the original score. Employees could see the criteria and score a draft before submitting it.
Design foundations
I defined tokens and interaction states in Figma, demoed the investigation workflow from Figma, then built it as a prototype.
Primitive and semantic tokens
Tools: Figma tokens with ChatGPT; Claude Code and Codex for the React v1 build.
Notion informed the drawer pattern and Attio informed the visual language. I explored a Gmail-style list to make findings easier to scan.
Reflection
What didn’t work
I spent considerable time polishing the v1 prototype without a customer request or feedback. I demoed the investigation workflow in Figma first and only built it as a prototype later.
What’s next
Two leads asked for integration with their existing tools. One said business context is needed to explain performance changes. Both shape my next project.
Next project · Purno