#quality-assurance
29 articles
- Quantifying Human-Technical Stability: My Final Survey Deck & Its Weakest Slide
Five minutes to pitch a survey I designed end to end. One slide carries the whole validity argument, and that slide has a circularity problem.
- The Robotaxi Case: Competitive Pressure as a Root Cause
A sensor missed a pedestrian — that's the proximate cause. The fifteen-day concealment came from somewhere else, and incident reviews rarely name it.
- Letter to Reviewers: Answering Every Critique of My Scale in Writing
Ten critique points across eight sections, answered one by one. Sorting my replies revealed the pattern: my concessions were cheap and my refusals expensive.
- Nonresponse Bias Strategy: Planning for the People Who Won't Answer
Four strategies, submitted and defensible. Then I reread my own sentence about leveraging positional power to convert refusals — in a study about power.
- Digital Tools: Friendship Data, Filed Between a Pay Rise and Better Hiring
SAS models employee friendships, Alliant scores flight risk, Google asks five questions. One textbook heading files all three as the same kind of tool.
- My TKI Conflict Mode Results & the Instrument That Wasn't the TKI
A syllabus linked a free sample test and called it the TKI. Six modes, 36 items, a formula predicting who wins. The real instrument has none of those.
- Seven Files on Getting Triggered: The Toolkit & the Line I Had to Rewrite
Seven PDFs on emotional triggers are really one four-step protocol. The hardest step is noticing — the second hardest is writing down what a camera would see.
- The Telephone Survey Is Dying: Reading the Task Force Report on What Replaces It
Cell-only households went from 3% to 57% in fifteen years. The profession's own task force says the replacement is unsettled, and is honest about it.
- The Walls Were Doing the Counting
Kirkpatrick's four levels, controlled experiments, learning hours: every instrument L&D owns needs a program to point at. Continuous learning removed it.
- Mount Everest: A Case Study in Deference & the Decision Nobody Stopped
Both expedition leaders talked constantly about a turnaround time. Neither ever named one. A rule with no threshold in it cannot be broken, so nobody broke it.
- Shared Vulnerability: The Model, the Audit & the Studies They Both Point At
Carson cites Andreasen and Jamison as warrant. Schlesinger goes back to those originals. One number sits in both papers, meaning different things.
- The POP Model: Three Questions & the One I Was Always Skipping
Purpose, Outcomes, Process — asked before you start. A seven-page tool that showed me my agenda was only ever answering the third question.
- Conscious Capitalism as an Acceptance Criterion: Reading the Deck Skeptically
Conscious capitalism sounds unobjectionable until you ask what would count as failing it. Rewriting it as acceptance criteria is how I read a values deck now.
- The Merck Argentina Case: Localizing a Policy That Wasn't Built for the Place
A headquarters policy dropped into a country it was never designed for — and the Friday morning somebody asked for one small exception to it.
- Chetna Gala Sinha Is My Power Pose
I was asked to name a superhero. I picked a banker in a yellow saree who keeps one hand still for fourteen minutes — and learned why it works.
- How Not to Suck as a Manager: The Case Packet & the Self-Check That Cannot Fail
A case study tells two bad-manager stories from the employee's chair. Part C turns the chair around, with a self-check that cannot come out clean.
- Mental Health in Tech: The Stakes I Named, and the Sample That Couldn't Carry Them
Before touching the data I named stigma, geography, and legal stakes. The country breakdown then showed which of the three this sample could not carry.
- DORA Quick Check - A Critique
A benchmark that scores your team's delivery performance in under a minute. The speed is the product — and why two developers score it differently.
- Building the Catastrophizing Scale: Construction Log & Honest Audit
Three of us built a psychometric scale from nothing — construct, items, peer review, analysis. The honest log: strong reliability, weak validity, an N of 7.
- Industry Was a Costume: Seventy of Us Described the Same Tool and Thought It Was Ours
Seventy classmates described AI tools by industry. Underneath the costumes, we had all reached for the same few tools.
- No Root Cause: What Coincidence Analysis Taught Me About Organizational Interventions
Coincidence Analysis taught me that organizational change may not have one root cause — just different sufficient recipes for the same outcome.
- Religiosity vs. GDP: A Regression That Passed Every Check — and a Causal Story It Can't Tell
A clean regression linked religiosity and GDP. That statistical cleanliness is exactly why the causal story needs more caution.
- The QA Manager, Part IV: Rating the Raters — and Who Never Got a Vote
Designing a QA Manager appraisal showed me that a rating system is a value statement before it is a measurement tool.
- The QA Manager, Part III: The Satisfaction Survey I Built — and Every Way It Could Mislead Me
I built a six-question satisfaction survey for a QA manager role, then audited every way my own instrument could mislead me.
- Catching False Passes in a QA Selection Plan
I designed a QA selection funnel with validity coefficients and cutoff scores, then found the statistical error and bias I had built in.
- Shipping Defects in a QA Manager Job Description
Writing a QA Manager job description taught me that job posts and software requirements fail the same way: unclear specs ship defects.
- Can articles be password protected?
An experiment in keeping some writing private.
- Launching surojito.com: Setup Log & Honest Audit
Publishing a personal site taught me that every blocked step is just a negotiation — with a tool, a credential, or a UI that wasn't designed with you in mind.
- Persuasive Speech: Outline & Self-Evaluation
A persuasive speech assignment taught me to build an outline that does the heavy lifting — and that mid-speech corrections are just negotiating for clarity.