What step formats are detected?

Numbered (1. / 1) / Step 1:), lettered (a. / A)), bulleted (- / * / •), and prose markers like First, Next, Then, Finally. When no explicit markers exist, it falls back to splitting on blank lines so you still get a readable trace.

How is the final answer separated?

The tool looks for a trailing segment introduced by phrases like \"Final answer\", \"Answer:\", \"Therefore\", or \"In conclusion\" and lifts it into its own section below the numbered steps. If none is found, the last step is shown as the conclusion.

Will it lose any text?

No. Every line of input lands in either a step or the final-answer section — nothing is dropped. The tool only reorganises and renumbers; it never paraphrases or summarises your reasoning.

Does it send my reasoning anywhere?

No. All parsing runs locally in your browser. The chain-of-thought text never leaves the page, so sensitive reasoning stays private.

Chain-of-Thought Trace Formatter

Chain-of-thought trace formatter

Chain-of-thought output is invaluable for debugging a model’s reasoning, but raw CoT is a wall of prose with inconsistent step markers — sometimes numbered, sometimes “First… then… finally”, sometimes just paragraphs. This tool detects whatever structure is there, normalises it into a clean numbered trace with step IDs, and separates the final answer so you can scan the logic at a glance.

How it works

The formatter scans the text for step boundaries using a priority of marker styles: explicit numbering (1., Step 2:), letters (a), B.), bullets (-, *, •), and prose transitions (First, Next, Then, Finally). It splits the text at those boundaries into discrete steps and renumbers them sequentially with S1, S2, S3 IDs. It then searches the tail for a conclusion marker — Final answer, Answer:, Therefore, In conclusion — and lifts that segment into a dedicated final-answer panel. When no markers exist at all, it falls back to splitting on blank lines so even unstructured reasoning becomes a readable list. Nothing is paraphrased; every character of input is preserved in its new home.

Tips and notes

Great for eval review. A clean numbered trace makes it obvious where a model’s reasoning diverged, which is hard to spot in raw prose.
Prose-style works too. “First I considered… then I checked…” is detected even without numbers.
The final answer is highlighted. Use it to confirm the conclusion actually follows from the listed steps.
Everything is local. No network calls; copy the formatted trace with one button.