Case study · athenahealth · Exploration

AI in reporting

Three concepts that help people understand, build and maintain reports, without taking decisions away from them.

AI in reporting at a glance

Validated, not shipped

Three AI concepts for reporting: insights that explain a report’s data, describing a report in plain language to build it, and reporting-health recommendations for admins. AI proposes; people decide.

Outcome. Participants said the concepts addressed major pain points. The work was later deprioritised in favour of the platform migration.

3
AI concepts across the reporting lifecycle
15
end users saw them in the Report Library RITE prototype
6
design principles, from grounded to reversible
0
changes AI makes without the user choosing
Report Builder prototype with the AI insights panel open beside the report results, synthetic data.

My roleDesigner on Report Library and Report Builder · Designed all three concepts · Put them in front of 15 users in the Report Library RITE prototype

Insights you can check

Two or three observations from the report’s own data, each linked to the rows behind it.

Describe it, then edit it

A plain-language request becomes columns and filters in Report Builder, tagged as AI-drafted.

Recommend, never act

Library-health suggestions show the system fact and the reasoning. AI never archives or pauses on its own.

Captured from the interactive prototypes with synthetic data.

Full case study

Problem

Running a report returned data, not meaning. Building one meant thinking in data terms. And libraries grew faster than anyone could clean them. Each was a moment where people needed help without losing control.

Context

I explored these concepts as the designer on Report Library and Report Builder. They covered three moments: interpreting a report, describing the report you need, and keeping the library healthy.

Process

I designed each concept around one rule: the report, its data and the user's decision stay in view. All three were included in the Report Library RITE prototype so participants could react to them during testing. Because Report Library connects to Report Builder, the test included a flow from the library into Report Builder, where report insights appeared.

Bringing intelligence into the reporting workflow

Exploring AI across the reporting lifecycle

I explored moments where AI might help users interpret results, express reporting intent, or review library health. The concepts kept the report, its data, and the user's decisions in view. All three were included in the Report Library RITE prototype for exploratory feedback. They are not presented as shipped features or measured impact.

  1. 01Run report
  2. 02UnderstandAI
  3. 03InvestigateAI
  4. 04BuildAI
  5. 05Schedule
  6. 06MaintainAI
Capability 01

Interpreting a report

Running a report returned the data, not the meaning. Experienced users already knew the surface metrics mattered; the harder question was what changed and where to look next.

Problem
Users had to visually diff numbers across periods and open other reports to understand why.
AI intervention
A contextual "Show me insights" surfaces 2–3 observations grounded in the report's own data.
User control
Each insight links back to contributing rows; users decide what to investigate next.
Report Builder results with the AI Insights panel open Full results with the insight “A/R concentrated in a few claims” selected and its three contributing rows highlighted in the table
Captured from the interactive Report Builder prototype at 1440 × 1024 — use the arrows to see each screen. Screen 1: “Show me insights” opens the panel beside the results. Screen 2: choosing “View contributing data” on an insight highlights the exact rows behind it in the full results. Synthetic data.
Capability 02

Describing the report you need

Users often knew the business question — show denied claims by payer — but not the data model, dimensions, or filters needed to build it. The gap was translation, not intent.

Problem
Report Builder asks users to think in data terms. Not every user does.
AI intervention
Natural-language intent is translated into a transparent, editable Report Builder configuration.
User control
Report Builder remains the source of truth. AI proposes; users review, edit, and run.
The Describe the report you need dialog with a sample request Edit Query after AI drafts the configuration, with AI-tagged columns
Captured from the interactive Report Builder prototype at 1440 × 1024 — use the arrows to see each screen. AI turns a plain-language request into columns and filters tagged “AI”; everything stays editable and nothing runs until the user chooses. Synthetic data.
Capability 03

Keeping the library healthy

Admins carried the weight of a library that grew faster than it was cleaned. Most work there isn't generative — it's deciding what to review, archive, or leave alone.

Problem
Stale, duplicate, failing, or badly-timed reports are hard to spot without time-consuming audits.
AI intervention
Governed system signals produce ranked, explainable recommendations with the reasoning visible.
User control
AI never archives, pauses, or reschedules on its own. Every action remains a human decision.
Admin Dashboard with system summary and the Reporting health section A recommendation drawer showing system fact, AI interpretation and recommended action
Captured from the interactive Report Library prototype at 1440 × 1024 — use the arrows to see each screen. Reporting health sits beside the existing admin KPIs; each recommendation separates the system fact from the AI’s reading. Synthetic data.
Principles that shaped these experiences

Six commitments the design kept, from first prompt to final action.

GroundedRecommendations connect to governed reporting data, not opinions.
ExplainableUsers can see why something is being suggested, in product terms.
TraceableInsights can be traced back to the contributing data.
User-controlledAI proposes; users review, edit, and decide.
Permission-awareAI respects the same access model as the rest of the product.
ReversibleNo irreversible changes without explicit user confirmation.
Status

All three concepts were included in the Report Library RITE prototype for exploratory feedback. Participants responded positively and said the concepts addressed major pain points in their current reporting work. This supported their perceived value; it did not establish sustained usage or measurable impact. The concepts were later deprioritized as work shifted toward foundational Sigma migration and platform capabilities.

Walk the interactive extensions: Report Builder — Insights & Describe your report → Report Library — Reporting health →

Key Decisions

  • A few grounded insights, not a full analysis. "Show me insights" surfaces two or three observations from the report's own data, each linked to the rows behind it, so users can check it rather than trust it.
  • Translate intent into an editable configuration. A plain-language request becomes columns and filters in Report Builder, tagged as AI-drafted. Report Builder stays the source of truth; nothing runs until the user chooses.
  • Recommend, never act. Library-health suggestions come with the system fact and the reasoning visible. AI never archives, pauses or reschedules on its own.
  • Separate fact from interpretation. Every recommendation shows what the system knows apart from what the AI infers, so users can judge both.

Outcome

Participants responded positively and said the concepts addressed major pain points in their current reporting work. That supported their perceived value; it did not establish sustained usage or measurable impact. The concepts were later deprioritized as work shifted toward foundational Sigma migration and platform capabilities.

How this scales

Follow-up thinking, 2026 · Built in the prototype · Not tested with users

Looking back, the reporting-health concept showed one recommendation per report. That works with four. In a library of hundreds, an admin would face a wall of cards. I reworked the admin view around one rule: the facts sit on top, AI explains, and the table is where people act.

  • Facts stay facts. The summary numbers count what the system knows. Each one is also a filter, with the same name as the matching filter on the table.
  • One insight, not a feed. A single critical insight in one line, “One change upstream is behind 4 of your 5 failing reports,” with three more behind a teaser. Each says what it is based on and can be dismissed.
  • Act in the table, in bulk. Filters for failing, inactive, ownerless and possibly duplicate reports. Select many, act once, and undo any row.
  • The sparkle means judgement. Only AI inferences carry it: the insights, possible duplicates, and the likely reason a schedule is paused or slow. A failed run is a fact, so it is never marked as AI.
  • Reasons where people ask why. A paused schedule shows the system fact, such as “auto-paused after 3 failed runs”, and separately the AI’s likely reason with what it is based on.
Admin dashboard: summary numbers, one critical insight in a single line, and a table of queries with filters for failing, inactive, no owner and possible duplicates. Schedules filtered to Paused: each row shows the system fact, such as auto-paused after 3 failed runs, and the AI's likely reason with what it is based on.
Captured from the updated Report Library prototype at 1440 × 1024. Use the arrows to see each screen. Synthetic data.

Lessons

  • Useful AI in data products shows its evidence.
  • Let AI propose; keep the decision with the person accountable for it.
  • Positive feedback on a concept is a starting signal, not proof of value.