templates/candidate.md
Lens: Candidate Interview (hiring)
When: an evaluative interview with a candidate for a position. Difference from VMDI org-mapping and exit interviews: the goal isn't to understand the system from the inside, but to assess the candidate's FIT for the role and collect verifiable facts about their past experience. Coding unit: a candidate's statement about their experience with a direct quote + a verifiability tag (specific fact / general claim). Collection discipline: look for STAR episodes (Situation-Task-Action-Result) with numbers and names, not generic self-assessments ("I'm a team player," "good communicator").
Layer 1 — operational (facts + quote + line)
- K1 Stated relevant experience — what the candidate names as their key experience for this role.
- K2 STAR episode(s) — a specific situation → task → action → result, with details (timelines, numbers, the candidate's own role vs. the team's).
- K3 Motivation for leaving — why they're leaving their current job / looking for work; what they're seeking here that was missing there.
- K4 Expectations of the role — how they picture their tasks, scope of responsibility, first 90 days.
- K5 Response to a hard/failed case — asked to describe a failure — what they chose to share, how they explain the cause (external circumstances vs. their own role).
- K6 Candidate's questions to us — what they ask — what they're worried about, what matters to them (a signal of priorities).
- K7 Terms and constraints — salary expectations, availability date, work format, other constraints — specific numbers/dates.
Layer 2 — analytical (conclusion + quote; CAPS) — to council
- A1 Episode verifiability — SPECIFIC FACT (dates/numbers/names, verifiable via reference check) / GENERAL CLAIM (not verifiable). For each K2. (unstable)
- A2 Result attribution — attributes the result to THEMSELVES / THE TEAM / CIRCUMSTANCES — does the scale match the seniority of the role.
- A3 Locus of responsibility for failure (K5) — owns it / deflects outward. (unstable — latent trait)
- A4 Role fit — which specific job-profile criteria match/don't match (not a general impression, but point by point).
- A5 Risks and red flags — inconsistencies in the story, avoidance of specifics, mismatch between expectations and the role's actual conditions.
- A6 Key insight — 1 sentence: candidate confirms experience [X] with a STAR episode [verifiable/not], risk is [Y], recommendation — [next step].
Forcing questions
Tell me about a specific case where [skill] came into play — what exactly did you do, and what did the team do? What was the result, in numbers? Tell me about a situation that didn't work out — what went wrong and what would you do differently? Why are you looking for a job right now?
Limitation
Latent traits (motivation, honesty of self-attribution, cultural fit) are a classic weak spot for LLM analysis. All A2/A3/A5 cells are candidates for mandatory human review, not a final mapping decision.