AI for Officer Efficiency
Turning a workflow pain point into an AI opportunity
Renee Romero • AI Systems Designer • 2025
A case study in specification precision, evaluation design, trust & security, and context architecture.
Project overview
My role:
AI Systems Designer, Renee Romero
The product:
A letter editor used by government officers to create and send official correspondence to applicants and petitioners.
Responsibilities:
Evaluation design, user flow analysis, stakeholder synthesis, cost & token economics, specification precision for AI concept, roadmap influence
Project duration:
8 weeks (September – October 2025)
Project overview
The problem:
Officers were spending more time fixing formatting than writing official letters. A program stakeholder walked me through the workflow and, describing it, surfaced a cost report he had built two years earlier and never connected to it. I treated the two as one finding: officers leaving the system to hunt citations, and a quantified case for fixing it already sitting unused. Formatting broke on paste, costing 5 to 15 minutes per letter.
The goal:
Identify the root cause of this inefficiency and define precise specifications for a solution that could be added to the product roadmap. Quantify the cost impact to build a business case for in-editor citation retrieval within a trust-critical government letter editor.
Understanding
the system
Evaluation design
Conducted a systematic evaluation across 3 key pages using Nielsen's 10 Usability Heuristics to identify failure patterns and design gaps
Dashboard Page
Draft Page
Letter Page
The insight
A two-fold pain point revealed a deeper design gap.
1. Context switching
Officers leave the letter editor to find legal citations from external sites, interrupting workflow.
2. Manual reformatting
Pasted citations break formatting, requiring manual fixes that waste time and create inconsistency.
→
The context architecture gap
Officers lacked the right context surfaced at the right time to find and apply citations efficiently within the editor.
This exposed a decision-support gap. The system had no context architecture to help officers complete their core task without leaving the application.
Quantifying
the impact
Cost analysis
5 to 15 min
Time Saved
×
$49.11/hr
GS 12-5 Rate
×
91,256
Notices
=
$372K to $1.1M
Annual Recoverable Time
5 to 15 minutes
Range of time officers spend per letter leaving the system to find citations and manually fixing formatting after pasting.
$49.11 per hour
GS 12-5 hourly rate from OPM federal salary tables.
91,256 notices
Total correspondence volume from FY2023 data provided by stakeholders.
Note: Modeled at full volume. The same model at 25 to 75% adoption yields $93K to $840K. Quantifying ROI before building.
The
opportunity
Current state: The letter editor
Officers use this interface to compose official correspondence
Current pain points:
What if the system surfaced the right citations at the right time?
Proposed solution: Scribbler
A precisely specified in-editor retrieval layer that surfaces relevant legal citations as officers write
Suggested citations for this letter:
8 CFR § 214.2(h)(4)(ii)
INA § 101(a)(15)(H)
Click to insert with formatting
Key benefits:
"AI isn't magic. It's specification precision that anticipates what users need next."
Stakeholder alignment
From pain point to validated build: making the case for in-editor retrieval
1. Discovery
Synthesized insights from officer interviews and stakeholder research
2. Evaluation design
Connected pain points to measurable time-on-task inefficiencies through systematic evaluation
3. Cost & token economics
Translated time savings into dollar impact to justify building before committing resources
4. Validation
Design lead validated Scribbler as the next build after MVP
Key outcome
The design lead validated Scribbler as the next build after MVP, with analytics tracking set up via Matomo for ongoing impact measurement.
✓
Validated
Going
forward
Impact
$372K to $1.1M
Annual recoverable time
5 to 15 min
Saved per letter
91K+
Notices impacted yearly
Key achievements
Takeaways
AI is a specification precision problem, not just a tech solution
The opportunity was not about adding AI. It was about defining precisely what officers needed and removing friction, and AI happened to be the right tool.
Evaluation design speaks louder than opinions
Quantifying the cost impact through systematic evaluation transformed a "nice to have" into a business priority.
Connect the pain to the context architecture gap
The problem and a dormant cost report surfaced together. Treating them as one finding built the case.
"AI isn't magic. It's specification precision that anticipates what users need next."
– Project reflection
Let's connect!
✉
If you're interested in further discussions or collaboration, I'm Renee Romero, AI Systems Designer, and I warmly welcome the opportunity to connect. Thank you for exploring this case study!
Email: reneeromero326@gmail.com
LinkedIn: linkedin.com/in/renee-romero
Portfolio: muralderomero.com