Wall Street PromptBrand
All briefs
Wall Street Prompt · Brand

The Prompt That Separates Fact, Inference and Opinion

Static post — the exact copy + visual structure. This is a post, not a video script.

Static Post
Instagram + XInstagram static
References & validationReference missing

No specific creator reference resolved. Add an observed post before production.

Reference creator: Research methodology creators

No reference links resolved.

On-image text

What goes ON the image

3 THINGS YOUR AI RESEARCH KEEPS MIXING

FACT -> what the filing actually says
INFERENCE -> what you concluded from it
OPINION -> what you think it's worth

Mix them and the memo reads true while being wrong.

The fix: make AI label every line.

[F] = stated in the source, page cited
[I] = derived, assumption named
[O] = your view, no source

No label = not usable.

Save this. Run it before you trust the memo.

Caption

Paste under the post

Most AI research fails for one boring reason. It blends three things that should never share a sentence.

Fact: what the source literally says. Inference: what you concluded by connecting facts. Opinion: what you believe it means or what it's worth.

When they blend, the memo sounds confident and reads clean. That is the trap. A confident sentence built on a hidden assumption is how a thesis goes wrong quietly.

The fix is a labeling pass. Make the AI tag every line before you read it:

-> [FACT] only if it is stated in the filing, the transcript, or the comp set, with a page or timestamp. -> [INFERENCE] when it connects facts into a conclusion, and the assumption gets written down next to it. -> [OPINION] when it is a judgment about quality, direction, or value, carrying no source.

Then read in that order. Facts you verify. Inferences you stress-test against the named assumption. Opinions you own, because that is the part AI is not allowed to hand you as truth.

AI builds the labeled draft. You judge what survives. A line with no label does not get used.

Save this and run it before you trust your next memo.

Educational content only. Not investment advice, and not a recommendation to buy, sell, or hold any security. Wall Street Prompt. Always verify against the primary source.

Layout

Single 4:5 reference tile. Top: two-line title block, heavy condensed headline ("3 THINGS YOUR AI RESEARCH / KEEPS MIXING"). Middle: three stacked definition rows, each a bold label in the accent color followed by an arrow and a short plain-text gloss (FACT / INFERENCE / OPINION). A thin rule, then the one-line warning in lighter weight. Lower-middle: the three bracket-tag rules ([F] / [I] / [O]) set as a tight monospace-style list to read like a spec. Footer: the rule line "No label = not usable." plus the save prompt, with the @WallStreetPrompt handle bottom-left and a small "Educational only" tag bottom-right.

Design notes

WSP palette: near-black background, off-white body type, single green accent reserved for the three labels (FACT/INFERENCE/OPINION) and the bracket tags. Heavy condensed sans for the headline (tight tracking, all caps), clean grotesque for body. Generous line spacing in the definition rows so each is one scannable unit. Bracket tags in a mono or mono-styled face to signal "prompt spec." One accent color only, no gradients, no second hue. Arrows are simple ->. Keep ample margin; the tile should feel dense but ordered, like a lecture slide.

CTA

Save this and run it before you trust your next memo.

Wall Street Prompt
Wall Street Prompt — internal