★ INTERVIEWER COPILOT · TCG EDITIONBuild a sharper
Build a sharper
interview in minutes.
Paste a resume + JD. A frontier AI model deals you a 10-card pack — snapshot, expected answers, follow-up trees, a turn-meter timeline, and a guided level-up scoring wizard. No recording. No candidate-facing UI.
no login · runs on resume content only · ~3–5 min per pack
10
MODULES PER PACK
11
CARDS DEALT PER MATCH
8 ✦
RUBRIC STATS
✦ AI
FRONTIER AI
EVIDENCE
RESUME · 14 HITS
✦
STR: 6 · RSK: 3
AMB: 4 · DIVE: 1
AMB: 4 · DIVE: 1
⚡PWR 60
QUESTION
SYSTEMS DEEP-DIVE
?
“take it 1× → 10× tomorrow — which three things?”
⚡⚡PWR 70
Load the cards before opening the pack.
Paste a resume + JD (real ones — the model needs evidence). Lens is optional but improves expected-answer quality. Signed-out sessions stay mostly local; sign-in saves the deck and source text to your account.
SLOT 1CANDIDATE RESUME○ NEED ≥30 words
0 words · need 30 more
SLOT 2JOB DESCRIPTION○ NEED ≥20 words
0 words · need 20 more
SLOT 3SETUP● SETUP
✦Skip the typing — paste a resume in Slot 1 and AI auto-fills name + role below.
CANDIDATE NAME
ROLE
TYPE
DURATION
DECK SIZE· 30-50s/draw · 5 cards ≈ 3 min
LANGUAGE · questions, expected answers, report
SLOT 4INTERVIEWER LENS◐ OPTIONAL
✦ Need a starter? Tap one to insert·
tip drop 1–3 sentences. The model uses them to angle every question.
DECK READINESS
◐
Setup
name + role required
◐
Resume
0 words · need 30 more
◐
Job Description
0 words · need 20 more
◐
Interviewer Lens
optional
EXPECTED PACK
10 modules · 10–12 question cards · 8 rubric stats · follow-up trees · 1 level-up report
still need: name + role required · ROLE · CANDIDATE RESUME (≥30) · JOB DESCRIPTION (≥20)
privacy: signed-out sessions live mainly in localStorage. After sign-in, resume, JD, deck, notes, scoring, and report are saved to your account.
WHAT YOU GET
four loops, one match
PACK
10-MODULE BRIEF
Snapshot, resume highlights, role-fit map, validate areas, question bank, expected answers, follow-up trees, rubric, red flags, timeline.
ARENA
BATTLE WORKSPACE
Three cards at a time. Mark asked, pin, log notes. Expected answers collapse so you don't anchor on them mid-conversation.
MAP
BIRD'S-EYE OVERVIEW
All cards in one view — filter by category, see asked / pinned, switch to a different question without losing your place.
LEVEL UP
GUIDED SCORING + REPORT
8 rubric dims · multiple-choice helpers · 1-5 score override · auto-drafted Markdown report. Copy, paste into Slack, done.
✦ SEE IT LIVEall 3 frames below are real screenshots from the Joey Jiang demo
✦ DRAW · 1 OF 3#01 / 03
Each draw deals 3 variants
AI deals 3 variants per draw. Hover any card to see the full evidence chain — resume + JD anchors, PWR, cost, deep-dives — before you pick.
◆ MISSION MAP#02 / 03
Resume × Questions × JD, side-by-side
Resume on the left, hex question path in the middle, JD must-haves on the right. Dashed lines wire each node to its resume highlight + JD anchor. Hover one — all three light up.
⚔ BATTLE ROOM#03 / 03
Single-question focus + live score/notes
Click a node → full TCG card + key points / deep dives / evidence / 1-5 score + handwritten notes (click saves immediately · typing autosaves on 600ms idle). Arrow keys navigate, Esc back to map.
HOW IT WORKS
3 stages · start without login · sign in to save across devices
1
OPEN THE PACK
Drop resume + JD. 10 cards reveal one by one in an intelligence pipeline — snapshot, highlights, questions, expected answers, follow-up trees.
2
PLAY YOUR HAND
During the interview, see 2-3 question cards at a time. Switch, pin, mark-asked. Expected outlines stay collapsed so you don't lead the witness.
3
LEVEL UP
End match → 8-stage scoring wizard. MCQ helpers nudge a 1-5 score per dim. Override. Then the AI drafts the Markdown report from your notes.
SAMPLE MATCH
this is the Battle Arena you'll be in once the pack opens
OPPONENT ZONE
FE / AI hybridLV.54
MAYA CHEN
Sr. FE · AI Products
MC
ATK 240DEF 180HP 800
Passive · Streaming First
System-design questions cost −1 ⚡.
System-design questions cost −1 ⚡.
ACTIVE LINE-UP · 3 cards selectable
★ FEATURED · Q.04⚡⚡PWR 70
SYSTEMS DEEP-DIVE
“You mentioned leading the migration of the editor to a streaming-first architecture. If you had to take it from 1× to 10× concurrent users tomorrow, which three things would you change first, and why?”
▾ EXPECTED⇡ FOLLOW-UPS · 3🎯 SYS · OWN
● ASKED · 📌 PINNEDQST/0407
NOW PLAYING
▾ EXPECTED ANSWER · Q.04
STRONG Names a specific bottleneck (CPU / socket / state sync).
⇡ FOLLOW-UP · 3 branches
if vague → which decision was hers?
if AI → how did she verify?
if AI → how did she verify?
YOUR PARTY · RUBRIC STATS
Role fit4/5
Tech depth4/5
Ownership3/5
Problem—
AI collab—
also includes· bird's-eye Map View · in-line notes per Q · LEVEL UP wizard · Markdown Match Report