# Blog: Introducing Prempti: Falco meets AI coding agents

DevFeed: [Blog: Introducing Prempti: Falco meets AI coding agents](<https://devfeed.tech/articles/blog-introducing-prempti-falco-meets-ai-coding-agents-32520.md>)

Original publisher: [Read original article](<https://falco.org/blog/introducing-prempti/>)

Author: Rule authoring

Published: 2026-05-12T00:00:00Z

Content type: release

Language: en

Sources: [Falco - Falco](<https://devfeed.tech/sources/falco-falco.md>), [Falco - The Falco blog](<https://devfeed.tech/sources/falco-the-falco-blog.md>)

Topics: [Falco](<https://devfeed.tech/topics/falco.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [Authorization](<https://devfeed.tech/topics/authorization.md>), [Command-line interface](<https://devfeed.tech/topics/cli.md>), [file](<https://devfeed.tech/topics/file.md>)

Tags: [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [falco](<https://devfeed.tech/tags/falco.md>), [file](<https://devfeed.tech/tags/file.md>), [network](<https://devfeed.tech/tags/network.md>), [permissions](<https://devfeed.tech/tags/permissions.md>), [prempti](<https://devfeed.tech/tags/prempti.md>), [shell](<https://devfeed.tech/tags/shell.md>)

## AI overview

Falco introduces Prempti, an experimental user-space service for monitoring and enforcing AI coding-agent tool calls. Prempti intercepts file reads, file writes, and shell commands, evaluates them against Falco rules, and returns allow, ask, or deny verdicts.

## Source excerpt

Today's developer workflow is increasingly reliant on AI coding agents. Tools like Claude Code sit in your terminal, read your files, run shell commands, make network requests, and write code, all on your behalf. They are fast, capable, and increasingly trusted with real tasks on real machines. But with that trust comes a question worth taking seriously: what exactly is your coding agent doing on your machine? Today, we're introducing an experimental project that brings Falco to this new frontier: Prempti. Agents are a black box at runtime When a coding agent runs a bash command, writes a file, or reads a configuration, those actions happen inside your user session, with your permissions, in your filesystem, against your credentials. Most developers using these tools have no structured visibility into that activity. You see the agent's chat output, but you don't see what's happening under the hood. Here's a simple scenario: you ask your coding agent to refactor a module. It reads your source files. It makes edits. Then, perhaps prompted by a malicious dependency or an unexpected instruction in a file it just parsed, it attempts to read ~/.ssh/known_hosts or write a file to ~/.aws/. Should it be allowed to? Would you even know if it tried? The demo below captures exactly this situation: To run this asciicast without javascript, use asciinema play https://asciinema.org/a/857572.json with Asciinema The agent tried to both read and write to sections it's not allowed to, and both were blocked. The agent itself received a structured message explaining why, and showed that to the user. This is detection and enforcement working together at the tool-call level. How Prempti works Prempti runs as a lightweight user-space service alongside your coding agent. It does not require root, kernel modules, or containers. When your agent makes a tool call such as a file write, a shell command, or a file read, Prempti intercepts it before it executes, evaluates it against Falco rules, a