Ashlr cover: the Phantom ghost with orbiting dots, with the headline A guide to how Phantom works, inside the app.

The briefingAgentic AI

Phantom adds a "How Phantom works" guide to the app

By Ashlr.AIAI-assisted briefingPublished Oct 8, 2026, 8:19 PM UTC3 min read

On October 8, Ashlr merged an in-app guide and new docs that explain how Phantom uses your accounts, routes work and reports results.

What changed

On October 8, 2026, Ashlr merged two pull requests that explain Phantom to new users. One is a guide inside the app. The other updates the written docs. Both descriptions say the goal was to make the relationship between chat routing, fleet work, the Manager and the Leader clearer.

The in-app guide is a "How Phantom works" section in Settings. The pull request says it covers connected command-line accounts, API credits and local models, the two work modes called "Work with me" and "Work for me", routing, the Manager and Leader, reported evidence, and how Phantom connects to Phantom Secrets and Locus. It is a keyboard-accessible section you open and close, and the description says it adds no network requests, no new routes and no saved state.

Browse all stories

General editorial illustration for Agentic AI.

The briefingAgentic AI

Topic illustration

Meta Muse Wonder Matches Fable 5.1 on Agent Tasks

The first-run welcome now uses the real work-mode names. The description says it avoids promising free or guaranteed local fallback work.

The docs pull request updates the README, quickstart, the Automatic guide and the website. It explains how supported resources work together, how to read readiness and results, and where account, billing and credential boundaries stay. It says there are no runtime or permission changes.

These are Ashlr's own descriptions of its own work. The pull request says installed-app acceptance is a separate step, so this story does not claim it has been checked on an installed app.

What it means for your work

For builders

If your product has a lot of moving parts, explain them in the product, in the order a new user meets them. This change adds no requests or saved state, so the explanation costs nothing at run time.

For business

A tool that sends work to several accounts and models needs a clear explanation of who pays and who can see what. Ask any vendor in this space to show you that page before you buy.

Put it to work

Open the linked pull request and read the list of what the guide covers. Then open Settings in the app and see whether a new colleague could follow it without help.

Explore the project

Ashlr tools connected to this story. Review their source and setup requirements.

Phantom

Work with eligible coding-agent accounts and local models in one workbench; review fleet proposals under signed authority.

Visit website View source

Go to the source

Source material behind this briefing. Our practical implications are Ashlr’s interpretation.

Explain Phantom resources, routing and work modes in onboarding (pull request) (opens in a new tab)
Ashlr.AIOct 8, 2026
Explain Phantom resources, routing and work modes (pull request) (opens in a new tab)
Ashlr.AIOct 8, 2026

This briefing was prepared with AI assistance from the linked sources. The analysis may include interpretation; consult the original sources for complete context. Cover artwork is illustrative.

Editorial approach Suggest a correction

Oct 17, 2026

2 min read

Meta released Muse Wonder with two versions and lower token pricing than Claude Fable 5.1. Independent tests showed comparable results on bug fixing and incident investigation but higher token use.

Field noteAgentic AI

Phantom: one workbench for all your coding agents

Oct 17, 20265 min read

Most engineers now use several AI coding tools. Phantom puts them in one place, so you can work with an agent or hand it a goal and check the results.

Ashlr cover: a sound wave and the corrected word Ashlr.AI, with the headline Dictate to your agent. Keep your spelling.