Can use synthetic-vs-real calibration with a defined task, suitable inputs, and a basic validation check.
augmented skill · Stage 02
Synthetic-vs-real calibration
Anchor skill
Synthetic-vs-real calibration is the discipline of knowing when synthetic data is and isn't a valid proxy. It helps a designer build a verified fact base without confusing generated synthesis with lived evidence while keeping the final judgment traceable and human-owned.
Why it matters
This is an anchor skill. Weakness here limits maturity for the entire Intelligence Gathering stage because it protects the non-negotiable human checkpoint.
Stage outcome
Build a verified fact base, user behavior, market landscape, competitive structure, grounded in the charter's success metrics from Stage 01
What good looks like
01
Frames synthetic-vs-real calibration against a clear goal, relevant evidence, and the stage quality gate.
02
Directs AI with scoped inputs, reviews uncertainty, and redirects weak or unsupported output.
03
Documents the decision, trade-off, correction, or override so another designer can follow the reasoning.
Checkpoint application
Apply this skill before the Stage 02 gate is approved. The accountable designer must be able to explain how it changed the work, what evidence was considered, and why the result is safe to advance.
Common failure patterns
- Confusing clustered or synthetic patterns with observed user truth, especially when outliers are inconvenient.
- Accepting fluent or high-confidence output without testing its evidence, assumptions, exclusions, and downstream effects.
- Recording the final artefact while omitting the rejected option, correction, trade-off, or override that explains the decision.
Five-minute practice
Use it on the work you already have.
Take one current intelligence gathering artifact. Apply synthetic-vs-real calibration for five minutes, then record one AI contribution, one human correction, and the evidence that justified the final decision.
Evidence of capability
- A reviewed research synthesis, validated persona, or evidence map showing the skill in use.
- A short rationale linking the decision to evidence, risk, and intended outcome.
- An example of an AI suggestion that was corrected, rejected, or deliberately accepted.
Leadership assessment questions
01
Can the designer demonstrate synthetic-vs-real calibration on a real intelligence gathering decision?
02
What observable evidence distinguishes competent performance from confident explanation?
03
Would weakness in this skill make the human checkpoint ceremonial rather than protective?
Maturity ladder
Can diagnose weak output, redirect the work, combine sources, and explain the resulting trade-off.
Can decide when not to delegate, own the human checkpoint, and remain accountable for the outcome.
Backlinks and relationships