Pi is interesting when you want more say in how a coding assistant does its work. It runs in a terminal, uses a model you choose and can read files, search, run commands and edit code. You can then adapt it with saved prompts, task instructions and extensions. A recurring incident review shows why that might help: the same kinds of files arrive each time, and the next engineer needs a report they can check. The example below starts with those files, then explains where customization becomes worth the effort.
01Fit
02Requirements
Pi is MIT licensed; the model it uses has its own costs. A provider may charge for API usage or require a subscription, while a local model uses your computing resources. Check the provider’s current prices and data terms before sending private files or committing to repeated reviews.
Check current access and pricing03Setup
The npm command below requires Node.js 22.19 or newer. If npm does not suit your setup, the quickstart also has a standalone installer for macOS and Linux. Native Windows has a separate guide. Install Pi in the environment where you intend to run the review.
npm install -g --ignore-scripts @earendil-works/pi-coding-agentRun pi --version in that environment. A version number gives you something concrete to compare if a command or setting behaves differently after an update.
pi --versionStart pi, use /login to select an approved provider, then use /model to choose an available model. The login flow can store credentials, so use the credential-handling approach approved for that environment.
piPi runs with the permissions of the account that starts it and does not ask before every tool call. Choosing a working folder or a shorter list of tools does not restrict the whole process to those files. The security guide and full Pi article explain how to run this review in an isolated environment with read-only inputs.
04Using Pi
In this hypothetical example, a checkout service becomes slower after a deployment. You have deployments.csv with rollout times, checkout.log with timestamped events and runbook.md with investigation steps. The bundle contains no evidence from downstream services. Pi’s job is to connect what is available and help you choose what to inspect next, leaving the missing information visible.
What to ask
Review deployments.csv, checkout.log and runbook.md. Explain what the files show about the slowdown, separating observations from possible explanations. Cite filenames and line numbers so I can check the findings. What is still unknown, and which checks would help answer it?
The report gives the next engineer a clearer starting point: findings they can trace to the files, unanswered questions they can recognize and checks they can actually perform. If verifying it takes more effort than reading the bundle directly, adjust the request, inputs or model before adding integrations.
05Next steps
If you are repeatedly typing the same request, a prompt template may be enough. A skill can add the instructions and supporting material a review needs. An extension becomes useful when you need code to do something new, such as retrieve an approved incident export. The full Pi guide follows these choices through the same three-file review so you can see what each one adds.
Read the guidanceWhen a script starts a review, it needs to know when Pi has finished before it forwards the report. The full guide explains the differences between plain-text output, JSON event records and the RPC interface, which lets another program send commands and receive responses. It also covers MCP, the protocol Pi can use to call tools supplied by other services.
Read the guidance06Alternatives
07Evidence and scope
Based on official documentation reviewed September 30, 2026. The example is illustrative; this guide does not report an installation, benchmark or production test.
Documentation checked