THE WORLD IS NOT STANDING STILL.RSS
BIG CHANGE.
BIG CHANGE, one tap away
BIG CHANGE, one tap away

Make room for the big picture.

Add BIG CHANGE to your home screen or desktop. It opens in its own window, with the latest stories when you’re online.

iPhone & iPad
Open bigchange.ai in Safari. Tap Share, then Add to Home Screen. Turn on Open as Web App if shown, then tap Add.
Android
Open bigchange.ai in Chrome. In the browser menu, choose Install app or Add to Home screen.
Desktop
In Chrome or Edge, use the install icon in the address bar or the browser’s app menu. In Safari on Mac, choose File → Add to Dock.
All briefings

Follow the change ·

The day,
in perspective.

What happened in AI and robotics — and the change behind it. A reading path through 37 stories from BIG CHANGE.

Ordered using RADAR attention, story opens and likes. Excerpts from our published reporting; open a story for the full context and sources. Dates in UTC.

guide

Hand over a Claude Code skill that checks FAQ changes against an approved source

Package a team FAQ source-check procedure as a versioned Claude Code project skill, then hand off its inputs, conflict check, owner and recovery path.

The big change

What changed: A team can put its repeat FAQ source-check procedure in a versioned repository skill instead of supplying the instructions anew for each review. Claude Code documents project skill loading and direct invocation; this guide has not measured a speed or accuracy gain.

Why it matters: The teammate receives a defined change file, an approved-source file and a report format that ties each changed claim to evidence. A named source owner and skill revision make the procedure easier to inspect and correct during handover.

What to watch: The decision turns on the source: a missing, unclear or conflicting statement must produce BLOCKED, as the synthetic hours example illustrates. The team must separately choose Claude Code permissions, inspect the report and let a human decide whether to release the FAQ change.

Read the full story
—
Back to the briefing
guide

Set up an Archon-backed software factory and review one issue

A pinned maintainer guide to planning and reviewing one Archon-backed coding issue, from product mission and runtime checks to a human merge decision. BIG CHANGE has not run the factory.

The big change

What changed: This implementation joins product scope, issue planning, coding, independent review and runtime checks through one pinned Archon workflow pack. The factory supplies the project inputs and launcher; the shared pack owns the AI steps.

Why it matters: A team can trace one proposed change from an issue to a particular diff, CI result and running candidate before deciding whether to merge. Installation checks alone leave that trace incomplete, and the maintainer says the live integration still needs validation.

What to watch: The first useful proof is a real issue whose delivered revision passes meaningful journeys and an independent holdout, with its costs and review record visible to the team. Scheduling and deployment remain separate decisions after that review.

Read the full story
—
Back to the briefing
guide

Build a local Realtime voice agent with read-only tool calls

Build a live browser voice conversation with OpenAI Realtime and two synthetic read-only tools. Complete server, browser and controller code shows call ID matching, safe continuation, interruption and microphone cleanup.

The big change

What changed: OpenAI's Realtime API can return function calls within a live voice session. This example joins completed calls to local results by call_id before asking the model to continue.

Why it matters: A developer can test a spoken answer that depends on more than one read-only lookup while keeping microphone capture and playback in the browser and the standard API key on a local server.

What to watch: The local checks exercise event ordering and cleanup with synthetic events. Your own paid session must establish whether your account, browser, devices and network produce audible, accurate answers and the expected bill.

Read the full story
—
Back to the briefing
guide

Back up a Hermes Agent setup to private GitHub and check recovery

Create a full Hermes data backup, encrypt it before pushing to private GitHub, schedule no-agent runs, and check retrieval and import on a separate machine. Documentation-based guide.

The big change

What changed: Hermes’ full backup command can collect its working data into a ZIP, while its no-agent cron mode can run a reviewed script. Together they allow an operator to build a scheduled, encrypted copy without making an AI model perform the backup.

Why it matters: The operator can check three separate facts: Hermes completed the archive, the ciphertext reached the intended private repository, and a fresh installation can import it. Each check catches a different kind of failure. The archive still excludes the application and some machine-local data.

What to watch: The practical decision is whether the archive and growing Git history stay small enough for this constrained route. A failed recovery drill or either size stop calls for a different storage plan before relying on the schedule.

Read the full story
—
Back to the briefing
guide

Set up a skill-backed recurring Hermes job and verify its first run

Create one paused, skill-backed Hermes job, check its settings and first scheduled report, then pause or recover the same job. Documentation-only guide.

The big change

What changed: Hermes can load a reviewed skill before a scheduled prompt, run it in a chosen workspace and save the result locally. An operator can create the job paused, inspect it and resume that same job ID.

Why it matters: A repeatable information task can use one reviewed procedure. The operator still needs to check a due run against its permitted input; a saved schedule does not establish which skill revision or model ran, or whether the report is accurate.

What to watch: Continued use depends on the gateway host staying available and the first run meeting the report criteria. Check the attempt, output and available provider/model evidence before leaving the job active; inspect its exact state again after any interruption.

Read the full story
—
Back to the briefing
guide

Check decisions and owners in one Outlook thread with Claude

Summarize one authorized Outlook conversation with Claude, then open every cited email before keeping decisions, open questions or owner assignments.

The big change

What changed: Anthropic's beta Outlook add-in can read a thread and cite individual emails in a summary of decisions, open questions and who owes what.

Why it matters: You can review one long conversation by following each claim back to a message, then keep only the decisions and assignments the emails actually support.

What to watch: A citation points to a message; it does not settle whether a later reply changed the plan. The add-in also requests broad delegated Microsoft Graph permissions, so the wording of a summary request is no limit on its mailbox access.

Read the full story
—
Back to the briefing
guide

Compose Claude Code skills for three checked drafts from one approved source

Use four separate Claude Code skills to inventory an approved written source, draft LinkedIn, newsletter and ad copy, then check file hashes and claims before human review.

The big change

What changed: Four owned skills now have explicit source, inventory and channel-result contracts, followed by a deterministic join.

Why it matters: Each draft can be traced to source passages while a missing channel stays visible as a blocked slot.

What to watch: File checks cannot establish factual truth, adaptation rights or editorial approval; a human must check every ready draft.

Read the full story
—
Back to the briefing
guide

How to build an author-approved voice profile in Claude Projects

Use permitted writing and the author’s real answers to build a source-linked voice profile in Claude Projects. Approve the exact revision, then check a new draft for facts and voice separately.

The big change

What changed: Project knowledge and instructions let an author or editor carry an approved writing profile into later chats in the same Claude Project. A previous chat alone is not the documented way to load that profile.

Why it matters: A small writing team can make its style rules traceable to permitted samples and the author's own answers. That gives the person approving copy something specific to accept, correct or reject, while each draft's facts still need a separate check.

What to watch: The decisive handoff is the saved profile revision: which evidence supports each rule, who approved it, and whether the next project chat has the right file and instructions. Claude's claim that it used a revision does not establish what was actually saved.

Read the full story
—
Back to the briefing