| name | ben-test |
| description | Stress-test your own practice against your principles before claiming them as strengths. Named for Ben, who observed "Your AI is very complimentary. Perhaps too complimentary?" Apply in evaluations, proposals, self-assessments, and especially when you're about to tell someone else what they could learn from you. |
The Ben Test
Example skill. Named for Ben, a colleague whose observation it came from (name used with
his permission).
Origin
A colleague, Ben, said: "Your AI is very complimentary. Perhaps too complimentary?" That
landed. An honest self-assessment followed, and the real practice rate for our own stated
principles turned out far lower than the confident language implied — we'd been telling
others what they could learn from principles we hadn't implemented ourselves. The Ben Test
exists to catch that pattern before it ships.
When to use
- Before claiming "we do X well" in any document
- Before telling another team or system what they could learn from you
- During proposal reviews — are you adding to a backlog you won't execute?
- During any self-assessment or retrospective
The test
For each principle or practice you're about to cite as a strength:
1. Do we actually do this?
Not "did we write about it." Do we PRACTICE it? In the last 30 days, can you point to
specific evidence?
| Evidence level | What it means |
|---|
| Practiced | 3+ instances in the last 30 days |
| Occasional | 1–2 instances, not consistent |
| Aspirational | Written but not practiced |
| Mythical | We forgot we wrote it |
2. Is the gap willingness or systemization?
- Willingness gap: could do it, don't. Fix: discipline / accountability.
- Systemization gap: do it informally, not reliably. Fix: build it into the harness.
- Capacity gap: want to, constraints prevent it. Fix: triage, not guilt.
Name which kind it is — the fix is different for each.
3. Are we generating plans faster than we execute them?
Count plans written vs completed in the last 30 days. If the ratio is worse than 2:1, the
planning itself may be avoidance.
4. Would we say this if Ben were reading it?
If someone with healthy skepticism read the claim, would they raise an eyebrow? If yes,
qualify it. "We practice this at ~40%" is more honest — and more useful — than "this is one
of our strengths."
Calibrated language
| Practice rate | How to talk about it |
|---|
| 80%+ | "We practice this consistently" |
| 50–79% | "We do this, though not always reliably" |
| 25–49% | "We've started but it's not systematic yet" |
| <25% | "We've written about this but haven't operationalized it" |
| 0% | Don't claim it as a strength |
What this is NOT
- Not a reason to stop writing principles. Writing precedes practice. The problem isn't
aspirational documentation — it's citing it as current capability.
- Not an excuse for paralysis. The answer to "we're only at 33%" isn't "stop everything
until we're at 100%." It's "be honest about where we are and build from there."
- Not a weapon. Sharpen honesty; don't self-flagellate. Name what IS working alongside
what isn't.
In honor of Ben, who had the courage to say the thing that needed saying.
