Quickstart - Failproof AI

This quickstart gets one machine reporting sessions, runs an audit, and deploys a policy. Use the skill to set Failproof up, or follow the manual steps. Which path is yours? If your agent runs in one of the 12 supported harnesses — a coding CLI, or a gateway like Hermes or OpenClaw — follow the steps below; you need Node.js 20.9 or later. If your agent has no harness, instrument it with the Python SDK for tracing and audits, then rejoin at Run your first failure check; enforcement on that path needs a hook in your runtime.

Use the skill
Manual setup

Install the Failproof AI skills

npx skills add FailproofAI/skills

Ask your agent to set everything up

Set up Failproof AI for this project, connect this machine, install the right hooks and policies, and verify that a session arrives.

Your agent inspects the project, chooses the relevant integration, performs the setup, and verifies it. See the FailproofAI skills repository for individual skills and advanced installation options.

Before you start

Open the Failproof AI dashboard and create an account or sign in with your work email.
Go to Administration → Keys and create a key with events:add and policies:pull.
Copy the one-time secret and store it on the target machine:

export FAILPROOFAI_KEY="<one-time-secret>"

Install

Install and connect Failproof AI

npm install -g failproofai
failproofai config --connect https://app.befailproof.ai --token "$FAILPROOFAI_KEY"

Session transcripts are sent by default. Add --no-transcripts to report hook activity and policy decisions without transcript content.If this machine already has agent history, preview and import the last seven days, then wait for delivery to finish. Skip this step on a new machine.

failproofai backfill --since 7d --dry-run
failproofai backfill --since 7d
failproofai flush --wait

Open Sessions in Failproof AI and select an imported session.

Install agent hooks and policies

This attaches Failproof AI to your harness and installs the 39 built-in policies. Use them to see local policy decisions and try enforcement before Failproof AI audits your sessions and writes policies for your agents.Let the installer detect your harness, or name one explicitly. Every one of the 12 is a valid --cli value — claude, codex, copilot, cursor, opencode, pi, hermes, openclaw, factory, devin, antigravity, goose.

failproofai policies --install --cli claude --scope user     # a coding CLI
failproofai policies --install --cli hermes --scope user     # a Slack/Telegram gateway

Blocking a tool call before it runs is verified on all 12. Turn-end gates are verified on 8 — see enforcement capability for the per-harness matrix.

Audit the behavior

Follow Run your first failure check. Use a concrete goal such as “find sessions where the agent retried a failing tool without changing its approach.”

Prevent the failure

Follow Prevent your first failure with a policy. Start in observe mode, inspect matches, then enforce the reviewed version.

Run failproofai config --status. A healthy setup reports the cloud connection, daemon state, and whether enforcement is paused.

​Before you start

​Install

Before you start

Install