How long a document can it handle?

Long documents work: models with large context windows read whole reports, and subagents split anything bigger into sections that get merged.

Can it summarize many PDFs at once?

Yes: one subagent per document reads in parallel and the orchestrator merges the findings, so a folder summarizes in one run.

All use cases

Chat with your PDFs

Ask the folder, not the file.

Drop PDFs in Drive and question the whole set: cited answers, summaries, comparisons.

Try now See pricing

Drop the documents

A folder of PDFs in Drive becomes context any chat can reference: contracts, papers, reports, manuals.

More about Drive

Question the set

Ask across the folder and follow up; run the hard questions through a second model before you rely on the answer.

More about Multi-Model Chat

Summarize in parallel

Fifty documents summarize as fast as one: a subagent per file, findings merged with references.

More about Subagents

Keep what you learned

Key facts land in memory, so next month's question starts from what the corpus already said.

More about Memory

Built from these features

Drive

Folders, previews, and lightweight versioning for AI work.

Multi-Model Chat

GPT, Claude, Gemini, Grok, Llama: pick mid-conversation, cheapest-first.

Subagents

Parallel subagents, isolated context, full observability.

Memory

A durable, private memory every agent reads and updates as it works.

Frequently asked

Ready to work this way?

Create a free account and start in seconds.

Try now