Remove before summarizing
The safest token reduction is deletion of irrelevant material. Remove generated files, repeated drafts, logs, and tangential background before compressing useful files.
Summarizing a bad source set still leaves you with a bad source set.
Minify structured noise
Code, JSON, CSV, and other structured files often contain whitespace or formatting that costs tokens without adding meaning.
Minification is useful when structure remains readable enough for the model and the task does not depend on formatting.
Summaries need labels
If you summarize a long source, label it as a summary and keep a reference to the original file. The model should know it is not seeing the full source.
Riflet workflow
Use token counts and filters first. Then apply minification or summaries only when the remaining material is genuinely needed.
Build better AI context with Riflet
Collect the files, notes, websites, and docs that matter. Export one portable bundle for any AI.
Download Riflet freeFrequently asked questions
Is context compression and minification only useful for developers?
No. The same context principles apply to research, writing, legal review, client work, product planning, and any workflow where the AI needs project-specific source material.
Does more context always produce better AI output?
No. Relevant, well-structured context usually beats a large dump of loosely related files. Large context windows make preparation more important, not less important.
Where does Riflet fit in this workflow?
Riflet is the assembly step. It helps gather source material, filter it, estimate the token budget, and export one portable file for the AI tool you choose.
Does Riflet replace RAG or AI project features?
Not always. RAG is useful for large retrieval systems. AI project features are useful inside one platform. Riflet is best when you want explicit, portable context you can inspect before using.