SHOWCASE
AssistLive Answers for Sales Calls
ProblemMid-call a prospect asks the specific question about pricing, integrations or security, and the answer is buried in a deck nobody can open mid-sentence. The rep stalls, guesses, or promises to follow up, and the moment is gone.
ApproachA desktop app that listens to the call and answers from the company’s own documents in a floating, always-on-top overlay. Whisper transcribes, a fast model picks out the genuine questions, retrieval pulls the matching passages from the indexed doc set, and a stronger model writes the answer with its sources. Meeting profiles scope it to the call type, and a rep voiceprint keeps the seller’s own speech out of the trigger path.
In practiceThe answer lands in about a second in a translucent window the rep can drag anywhere, and when the documents don’t cover the question it says so instead of inventing an answer.
North-star metricSeconds between the prospect finishing the question and a usable, sourced answer being on screen. That is what forced the overlay, because an answer the rep has to alt-tab for has already missed the moment.
Why desktop, not a tab The two things this needs, capturing the meeting’s audio and holding a window above the call, are exactly what a browser tab cannot do. Electron for the shell and a bundled Python service for capture, diarization and retrieval; the cost is an installer instead of a URL.
Designed to be wrong out loud Every answer is graded against what retrieval actually found, and a weak match is labelled and told to escalate rather than dressed up as an answer. On a live call a confident wrong answer is far more expensive than an admitted gap, so the guardrail is the feature.
QuizzlyAI Quiz Builder & Live Match
ProblemBuilding a decent quiz means writing every question, answer and explanation by hand, and running one for a group means either paper and a projector or a heavyweight classroom platform.
ApproachPoint it at one or more sources (PDF, DOCX, TXT or a fetched page URL), then set the question count, difficulty, a focus area and which of nine types to draft (MCQ, true/false, fill-in-blank, short answer, numeric, cloze, poll, ordering, matching). Every question lands in an editor with its answer key and explanation; keepers go to a reusable bank. The quiz then ships as a link, QR or embed, or as a live host-controlled match players join by code.
In practiceSource material becomes a playable quiz in minutes, and a room can play it from their own phones with no account on the player side.
North-star metricTime from “I have this material” to a quiz someone can actually play. Everything else follows from that: ingesting a document rather than a blank form, drafting the explanation alongside the answer, and publishing to a link instead of an export.
Where AI stops Generation drafts questions, it never publishes them. Each item lands in the editor with its type, difficulty, points and explanation exposed for review, and the quiz keeps a record of which source documents produced it, because a wrong answer key costs far more in a quiz than a slow one, so the human check is the point rather than a formality.
Two modes, one quiz The same quiz works asynchronously (share a link, play alone, scored against a pass mark) and live (host opens a lobby, players join by code from their phones, host controls the pace). Building both off one question model meant no separate “live version” to maintain.
QueueLessVirtual Queues for Any Venue
ProblemClinics and service counters still run on paper tokens and called-out numbers, so customers have to physically hold their place in line and staff have no shared view of who is waiting or how long.
ApproachA QR at the venue opens a mobile queue: customers join, watch their position live and walk away; counter staff call the next token with priority and walk-in handling; a TV board mirrors “now serving”; operators get wait-time analytics, per-counter staff and an audit log.
In practiceZero hardware, with no kiosks and nothing to install on either side. Multi-tenant, so a business self-serves signup and its queue is live in about a minute.
North-star metricMinutes a customer spends physically standing in line, not time-in-queue. Someone can wait forty minutes happily if they spend them elsewhere, which is why the status page leads with position and estimated wait rather than a countdown.
Keeping the queue honest An open join link can be spammed from anywhere. The venue QR rotates every ~30 seconds and the link cannot be forwarded, so joining requires physically being there; optional CAPTCHA and a manual-approval mode with visual PIN matching cover higher-risk venues.
Built for the whole floor, not one screen Five surfaces share one live queue: customer phone, counter tablet, waiting-room TV, operator desktop and a platform admin. Counters, staff accounts, categories, operating hours and an audit log make it usable by a team rather than a single person.
QuickShareEphemeral File Rooms
ProblemGetting a file onto the presenting laptop mid-session means email, a USB stick, or borrowing someone’s cloud login. All are slow, and the file is left sitting on a shared machine afterwards.
ApproachA room-based handoff: a 6-character code or QR opens a shared space, guests upload up to 500 MB per file without an account, and the host keeps control through visibility toggles, room and panel passwords, kick, and a hard expiry.
In practiceFiles move in seconds with zero setup, and the room deletes itself and everything in it on expiry, so nothing lingers on a borrowed device.
Every app is fully functional. If you hit a problem, do let me know what went wrong. Thanks in advance for your feedback.