

Field note
Phantom: one workbench for all your coding agents
AI-generated illustration
A task in Claude Code, a review in Codex. Phantom brings coding agents into one workbench, with a place to steer the work and review what changed.
What is changing in AI, and what we are building with it. Follow the wider industry, go behind the scenes at Ashlr, or read both.
Products, releases and field notes from the people building them.


Field note
AI-generated illustration
A task in Claude Code, a review in Codex. Phantom brings coding agents into one workbench, with a place to steer the work and review what changed.


Field note
AI-generated illustration
A coding agent can read a key stored in .env. Phantom Secrets replaces it with a local placeholder and supplies the real credential to supported API requests.

Field note
AI-generated illustration
Speech-to-text gets common words right and your names wrong. Lexicon is one file of the words you say, fixed before your agent reads them.


Field note
AI-generated illustration
Why read a whole file for one function? ashlr-plugin offers compact reading and search tools, with benchmarks you can repeat on your own code.


Field note
AI-generated illustration
On a laptop used for several clients, the active account can be the wrong one. Locus scopes commands and agent tools to an explicitly pinned identity.


Field note
AI-generated illustration
The agent finished its plan. Now someone has to read it. Ashlr MD turns Markdown files into formatted documents that teammates can review, edit and export.


Field note
AI-generated illustration
A new app can mean a database, hosting and several more setup screens. Ashlr Stack helps configure backend services from the terminal or an AI agent.


How Ashlr runs on agents, part 1 of 3
AI-generated illustration
Four bots give our CEO a manageable view of the work. Behind them are specialist agents, clear responsibilities and decisions that still stop with a person.


How Ashlr runs on agents, part 2 of 3
AI-generated illustration
Writing a change is only the start. Our agents follow pull-request checks, a one-at-a-time merge rule and a separate human decision to publish packages.


How Ashlr runs on agents, part 3 of 3
AI-generated illustration
Which agent is working, and what needs approval? Phantom is our workbench; coordination for proactive agents is still being built.

BusinessField note
We set up a booth at the JMU Gilliam Center to show what we build. Here are the photos and what we put on the table.


Ashlr release
ashlr-plugin 1.36.5 replaces its 57 percent savings headline with per-call figures and fixes extra overhead on tiny edits. This is an Ashlr release.


Ashlr release
AI-generated illustration
A working connection can still have an expired quota reading. Our Phantom 3.29.15 release makes that distinction clearer and keeps cleanup changes behind a dry run.


Ashlr release
Phantom 3.29.14 adds opt-in sleep prevention on Mac, a Devin dashboard reading that expires in two minutes, and a small coffee animation for Ash.


Ashlr release
Phantom 3.29.11 to 3.29.13 stop treating unknown usage as zero and hold some unattended runs without billing proof. These are Ashlr releases.


The briefing
On October 12, Phantom merged its 3.29.12 and 3.29.13 releases, and Phantom Secrets closed a race in device approval expiry.


The briefing
On October 11, Phantom added one required check that blocks a merge if any expected test job is missing, failed, canceled or skipped by surprise.


The briefing
On October 10, Phantom published versions 3.29.6 to 3.29.10. Pull requests describe a resource sidebar, a Mac installer command and faster CLI startup.


The briefing
AI-generated illustration
On October 10, Phantom Secrets merged two fixes so a failed GitHub sign-in no longer leaves the dashboard or device approval stuck on an old account.

The briefing
Lexicon merged a guided way to build your vocabulary from sources you pick, plus previewed community packs. It is in the code but not yet in a numbered release.


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

EngineeringField note
AI-generated illustration
Two small changes reduced repeated work in Phantom. The useful part is how we measured them, preserved the checks and kept a local result in perspective.


Ashlr release
ashlr-plugin 1.36.4 renames its npm command to ashlr-plugin so it no longer overwrites the ashlr command from Ashlr Hub. This is an Ashlr release.


The briefing
AI-generated illustration
Between September 28 and 30, five Ashlr repositories added issue templates, runnable examples and clearer install notes. Boring work that helps new users.
Your week, in perspective.
A weekly email with the developments worth understanding, what they mean for your work, and a practical next step.
Built by Ashlr, a team working on the systems and workflows behind these stories.
Original sources, clear publication dates, and an explanation of what is reporting and what is our interpretation.
Our editorial approachExplore our engineering tools, practical guides, and longer essays from Ashlr Insights.