PM Vision

Autopsy a slide deck from photos or screenshots of its slides — the narrative arc, the numbers, and what each slide is hiding. Use when given slide images (a competitor's pitch, a conference talk, your own deck before a big meeting) and asked what the deck argues, whether it holds up, or how to counter or improve it. Produces a slide-by-slide read, the reconstructed argument chain, weak links, and the questions the deck is engineered to avoid. Requires image input.

Turn photos of a whiteboard, sticky-note wall, or napkin sketch into a structured spec the team can execute. Use when given whiteboard photos after a workshop, sketch images of a flow or architecture, or asked to 'write up what we drew'. Produces a structured write-up — decisions, flows, open questions, owners — that preserves everything on the board and flags what was ambiguous. Requires image input.

Tear down a competitor's product from screenshots of its actual UI — onboarding, pricing page, core flows. Use when given screenshots of a rival's app or website and asked what they're doing, how their flow works, or what to learn/steal/avoid. Produces a UX-and-strategy teardown grounded in what is visibly on screen, with an inferences-vs-observations split. Requires image input. For a market-level teardown without screenshots use competitor-teardown.

Extract pixel-level data from an image of a chart or graph and produce a structured data table. Use when asked to extract data from a chart image, transcribe numbers from a graph, digitise a chart, or turn a screenshot of data into a table. Produces a structured table with extracted values, confidence levels, and a reconstructed chart source. Best used with Claude Opus 4.7 or newer for reliable chart data extraction.