▼ WHAT THIS PAGE DOES — TWO JOBS ON YOUR TEXT FILE ▼

Raquel — compress a text file and count tokens

Job 1: Your whole file (English) → count inbound tokens (what the LLM would receive).
Job 2: Same file after compression → compressed text in the output box → count inbound tokens again.
Product goal: Job 2 should be about 30% fewer inbound tokens than Job 1. This page shows whether you hit that on your file.

1

Load your .txt file

File contents go in the input box (full English).

No file chosen yet.

Optional:

2

Run both jobs

Compress into the output box and fill the token table.

3

Output + token counts

Output area = compressed file (Job 2 text).

Inbound tokens — same file, two jobs
Job 1 — full fileJob 2 — compressed file
Characters in box
Inbound tokens
Job 2 vs Job 1
~30% product goal

Load a file, then click RUN JOB 1 + JOB 2.

Token counts: estimated here (chars÷3.8). Measured Claude counts when server API is connected.

Lab reference (Run 01 — not this automatic engine)

One essay, hand-built notation: 1,661 → 548 inbound tokens (~67%). That is a separate Demonstration test, not what Job 2 produces today.