The interesting part of a result is rarely the result. This is research for the beat writer, the front-office analyst, the scout and the serious fan that works the after-action question — which decisions held, which broke down, where the game actually turned — beside the cap sheet, the transaction line, the CBA article and the official final. Predict anchors on a rating maintained nightly and is graded by code against the box score the morning after, so the number carries its own record.
Spain's midfield trio of Rodri, Fabián Ruiz, and Pedri completed 647 passes to Argentina's 337 — a structural suffocation that made the 106th-minute winner inevitable.
Real sports research from the public library, shown as it was published. The stamps and the sources are the product.
Each one is a question a specialist actually brings, and each is answered by a scan this domain carries — not a generic report with the name swapped in.
“What actually decided the game — the plan, the execution, or the break?”
“What are the options on this roster and this cap, and what does each one cost over three seasons?”
“Where does this player’s production come from, and does it travel to a new system?”
“What does the record say about this matchup — and how good has the number been at this?”
Every judgment carries a grade for how it is actually known, every figure carries who reported it, and the structured record below is read on every scan before the model writes a word.
44 first-tier sources for sports, and 31 blocked outright. Search results are one input; every figure is graded on where it came from, not on being found. How the grades work →
Scale here is how much of the season, the franchise or the league a storyline touches — and Complexity is how much of the outcome the record can actually explain.
Small impact, easy to understand. A routine storyline with limited wider significance.
Real franchise weight and the implications are clear. You can see where this is heading.
Real stakes with genuine uncertainty. This could play out in multiple directions — cap moves, trades, or locker room dynamics make the outcome hard to predict.
Very high stakes at franchise or league level. The magnitude makes this the dominant storyline, regardless of how simple or complex the situation is.
No precedent. The kind of moment that reshapes a franchise era or the league itself.
When franchise-level weight grows to large scale, FLOW C reclassifies to FLOW D immediately. The situation shifts from 'interesting analysis' to 'the dominant story.'
Large franchise-level weight means FLOW D regardless of complexity. A simple, well-understood situation that carries franchise-wide implications is FLOW D, not FLOW A.
FLOW A and B differ only in scale (both low complexity). FLOW S is legacy-defining — max 1-2 per analysis. The test: will this be in the documentary?
One vocabulary across every domain — a FLOW D here reads at the same weight as a FLOW D in any other — so the classification travels, and so does your judgment. The framework in full →
7 ways in, then the rest of the catalog organised as the Sports workbench organises it — establish the background, map the argument, work the record, analyse the connections, decide what to do. Every one comes back graded, sourced and exportable.
Don’t know which one you need? The Router reads a plain question and picks one; the Planner takes a goal and designs a linked sequence. Every completed scan opens onto its own follow-ups — ask it a question, re-check what has changed, red-team its judgments, or push a signal onto your watchboard.
And the Studio turns a set of sports scans into a planned, researched, edited report or book. Every format →
Open the sports workbench with a matchup, a roster, a transaction or a season. What comes back is graded, sourced, and — for Predict — scored.