CASE 01 / 04·IBM
Research operations · scaling capability

An agent that challenges designers
to become senior researchers.

Building a self-service research framework that let an entire design team plan and run their own studies, with senior-level rigor.

PROJECT META
ORG
IBM
SURFACE
Secure UX
ROLE
Senior UX Research Strategist
TEAM
Embedded across the Secure UX design team
TIMEFRAME
Ongoing engagement · ahead of an upcoming release
SAMPLE
Whole-team deployment across the Secure UX design org
METHODS
M.01Research-ops design
M.02AI tooling (IBM Bob, Claude Cowork)
M.03Framework design
M.04Capability uplift
SENIOR SIGNALS IN THIS CASE
Critical thinkingSystems thinkingImpact & follow-through
§ 02

TL;DR

Facing a need for higher-quality tactical research without the headcount to support it, I built an AI-powered framework that guides designers through the end-to-end research process. This framework effectively upskilled the design team to produce near-senior level tactical insights, allowing me to shift my focus to long-term strategic initiatives.

§ 03
The framework, as built

Selected artifact

The framework, as built

A modular set of Markdown task files loaded into IBM Bob as senior-researcher personas. Designers chat with Bob to plan, run, and analyze studies. Each task carries domain context, mentoring rules, and a small canon of research literature (Portigal, Hall, Fitzpatrick, Goodman, Creswell) so the persona resists generic answers and pushes back where a senior researcher would.

FIG. 03.1· IBM Bob editor with the task framework loaded.
Screenshot of the IBM Bob editor showing five Markdown task files in the Archive folder, with the ux_plan_from_scratch.md file open. The file defines a senior researcher persona with product context, domain challenges, and a 6-phase study-design walkthrough.
FIG. 03.2· The five modular tasks, with their roles.
FILE 01
ux_plan_from_scratch.md
Walks a designer through a full study end-to-end in six phases (research questions, participants, method, guide, fieldwork, analysis), with Socratic challenges at each step.
FILE 02
select_best_method.md
Matches the research question to the right method, with tradeoffs and a falsification check for each candidate.
FILE 03
challenge_and_refine_plan.md
Applies rigor and bias checks to an existing draft plan before it goes in front of stakeholders.
FILE 04
analyze_your_data.md
Synthesizes qualitative and quantitative data without confirmation bias; surfaces the strongest counter-evidence before the headline insight.
FILE 05
senior_user_researcher_agent.md
Always-on Socratic mentor persona, referenced by the other tasks for in-context coaching on ad-hoc questions.
§ 04
Senior signal · Systems thinking

Systems map

From a research-ops gap to scaled influence

The framing the team came in with was a staffing problem: “we don't have enough researchers.” I reframed it as a capability problem with a different shape. Designers were already doing research; they just lacked the scaffolding to do it well. Treating this as a hiring problem would have produced a slow, expensive, unscalable answer. Treating it as a framework problem opened up a self-service path that compounds: every study a designer runs raises the floor of evidence informing the product, and frees the research function to focus on the questions only senior researchers can answer.

FIG. 04.1· Finding → strategy chain.
01SymptomDesigners running ad-hoc research with uneven rigor↓
02ReframeCapability gap, not a headcount gap↓
03InterventionModular task framework, AI-operationalized↓
04Scaled outcomeDesigners run their own studies at senior quality↓
05Strategic effectUser insight raises the floor of every product decision■
§ 05
Senior signal · Critical thinking

What I almost missed

What I almost missed

The first version of the framework was task-driven: “do this, then this, then this.” When I tested it with designers, I noticed they could follow the steps but were still producing leading interview questions and confirmation-biased synthesis. The framework was missing the part that's hardest to teach: why each step exists. I rebuilt the tasks to make the reasoning explicit. Not “write an unbiased question” but “here's what bias looks like in this question and why your answer will tell you nothing.” That reframe is what made the framework act like a senior researcher rather than a junior one.

METHODOLOGICAL NOTE

Every study gets a deliberate falsification pass before write-up: a structured hunt for the strongest evidence that the conclusion is wrong.

§ 06
What changed because of the work

Impact

OUTCOME 01
End-to-end
research execution by designers, no researcher gating
OUTCOME 02
Faster
timelines; no queueing on a dedicated researcher
OUTCOME 03
Higher
rigor + consistency across the team's studies
OUTCOME 04
Upcoming release
informed by evidence the team gathered themselves