How Perch works
Perch reads your material first, grounds its answer in what it found, and shows the source behind every claim.
Perch follows one principle on every turn: read first, then answer, and keep the source attached. This page explains the loop behind that principle so you know what is happening when you ask Perch to do something.
Read first
When you ask a question, Perch does not answer from memory of its training data. It first gathers the material that is relevant to your request:
- The documents in your workspace, whether those are uploaded files or local folders.
- Any curated knowledge your team has added.
- What Perch has learned about you and your work over time.
This step is called retrieval. It is the reason Perch can answer about your March invoices or your case file rather than about the world in general.
Do the work
Once Perch has the relevant material, it does the task. The shape of the work depends on the surface and the working style:
- On the web, a turn is a single grounded answer with its sources attached.
- On the desktop and CLI, Perch acts as an operator. It can read files, search across a folder, and run analysis in a sealed sandbox to check numbers and produce results rather than estimating them.
For larger tasks, Perch can plan a sequence of steps and use focused workers for parts of the job. The driving model is chosen at the start of a task and stays fixed for that task, so the work stays consistent from beginning to end.
Keep the source attached
The output is only half the job. Perch attaches the source behind each claim so you can verify it rather than trust it. Grounded answers cite the passage they came from, and unsupported claims are marked rather than presented as fact.
This is the difference that matters for professional work. You are not asked to take the answer on faith. You can follow any claim back to the material it came from. The mechanics of that are covered in Citation verification.
One account across surfaces
The web chat, the desktop app, and the CLI are one product. They share:
- One account. Sign in once; your access carries across surfaces.
- One memory. What Perch learns on one surface is available on the others. See Memory.
- One usage allowance. A single allowance covers all three surfaces.
The result is that you can start a question in the browser and continue the work in the desktop app without re-explaining yourself.