Weekly Briefing 6 min read
Build an AI Roster, Then Make Every Model Earn Its Place
Grok Bot and Hermes Bot Mode make persistent specialists practical, while Gemini Flash and GPT-5.6 Sol turn AI speed into a cost decision.
Read moreEverything published
The Archive
The full PromptHacker library grows with Weekly Briefings, Deep Dives, Courses, Skills, and Benchmarks.
Weekly briefings Deep Dives Courses Skills Benchmarks
Browse by type
Browse by date
Weekly Briefing 7 min read
AI Teammates Stay on the Job After You Log Off
Grok Bot keeps cloud work moving, Claude Tag gives teams a shared Slack teammate, and Hermes profiles make a tuned agent portable.
Read more
Weekly Briefing 8 min read
Slackbot Can Build the Dashboard Now
Slackbot builds live dashboards and runs code, Gemini drafts presentations and videos, and Grok 4.5 gets a measured coding test.
Read more
Weekly Briefing 8 min read
ChatGPT Work power tips, AI memory, and GPT-Live for business
Four advanced guides to ChatGPT Work, dependable AI memory, GPT-Live, and an expert ChatGPT workspace.
Read more
Weekly Briefing 6 min read
ChatGPT desktop, Sonnet 5, and Gemini Spark: what to test now
A practical workflow-testing issue for Executives: run one ChatGPT desktop workflow, add Claude review rules, and pilot Gemini Spark on one Mac task.
Read more
Weekly Briefing 6 min read
Claude Joins Your Slack Channel. Fable 5 Comes Back Online.
Anthropic's biggest week of the year: Sonnet 5 ships at daily-use pricing, Fable 5 returns after a 19 day shutdown, and Claude Tag joins Slack. Plus a real cost breakdown for a multi-model AI council.
Read more
Weekly Briefing 6 min read
The Week AI Moved Into the Work Itself
ChatGPT got better at decisions, Grok moved into Word, Google shipped role-based Gemini training, and Perplexity made research easier to branch.
Read more
Weekly Briefing 7 min read
Claude Joins Your Team. Grok Moves Into Word. Copilot Cowork Goes Live.
Three products worth acting on this week: Claude Tag joins Slack as a working teammate, Grok moves into Microsoft Word free, and Copilot Cowork reaches general availability.
Read more
Weekly Briefing 6 min read
Anthropic's Best Models Went Dark. Copilot Cowork Took Over the Work.
Fable 5 went dark three days after launch, Copilot Cowork now finishes the task instead of drafting it, and Grok learned to make video. Here is what is worth your Wednesday.
Read more
Weekly Briefing 9 min read
Anthropic's Most Powerful Model Ships to Everyone, and ChatGPT Memory Starts Updating Itself
A Mythos-class Claude is now in your plan, ChatGPT learned to keep itself current, and Grok plugged into your work apps. Here is what is worth your Wednesday.
Read more
Weekly Briefing 6 min read
Opus 4.8 Works Longer On Its Own, and Copilot Got a Faster Redesign
Two flagship launches on the same day, plus the desktop agent that operates your Windows apps. Here is what is worth your Tuesday.
Read more
Weekly Briefing 7 min read
Google I/O Just Changed the Game.
Gemini Spark, free Deep Research, and Grok connectors gave executives several practical moves during Google I/O week.
Read more
Weekly Briefing 8 min read
PromptHacker Weekly -- Issue #125
This week the big platforms stopped waiting for you to ask. ChatGPT now connects to your bank, brokerage, and card accounts and turns a 40-minute spreadsheet review into a 10-minute conversation about where your money actually goes.
Read more
Weekly Briefing 9 min read
The Week AI Agents Moved Into Your Tools
This was the week AI agents stopped living in a chat window and moved into the tools you already run your business on. Anthropic launched Claude for Small Business, which drops agents straight into QuickBooks, HubSpot, and PayPal to chase invoices and close out month-end, with your approval before anything sends.
Read more
Weekly Briefing 7 min read
GPT-5.5 is your new default. Here is what changed.
GPT-5.5 Instant is now your default ChatGPT model, memory sources are editable, and ChatGPT has landed inside Excel and Google Sheets. These three launches alone reshape how you work with AI.
Read more
Weekly Briefing 12 min read
ChatGPT Generates Images Inline, Copilot Finance Agents Hit Excel, and Claude Cowork Lands on Windows
Three things actually moved this week. ChatGPT now generates and edits images inline using DALL-E 4, which means the Tuesday social asset no longer needs a separate design tool or a paid Midjourney seat.
Read more
Weekly Briefing 11 min read
Claude Design Just Made Your Freelance Designer Nervous
Three AI platforms shipped major updates this week. Anthropic launched Claude Design on April 17 -- a conversational design studio bundled into every paid Claude plan at no extra charge. xAI released Grok 4.3 Beta on the same day with native video input and direct PowerPoint export.
Read more
Weekly Briefing 13 min read
Anthropic's Mythos Finds Zero-Days at Scale, Meta Launches Its First Frontier Lab Model, and ChatGPT Becomes a Cross-Platform Research Engine
Three major launches this week reshaped the AI landscape. Anthropic announced Claude Mythos Preview on April 7 - a frontier-class model purpose-built for cybersecurity research that identified thousands of zero-day vulnerabilities across every major OS and browser within days of launch.
Read more
Weekly Briefing 11 min read
Claude Launches Its Agent Platform, ChatGPT Gets a Filing Cabinet, and Copilot Rewires Office
Three things changed this week that matter more than the headlines suggest. Anthropic launched Claude Managed Agents in public beta - a hosted platform that gives any Claude user the infrastructure to build and run autonomous agents without writing their own backend. Notion, Rakuten, and Asana are already live.
Read more
Weekly Briefing 6 min read
PromptHacker Weekly Issue 118 (April 2, 2026)
This week, AI took another giant leap, as Anthropic's Claude gained remote control over Macs, Shopify's Agentic Storefronts enabled direct sales in AI assistants, and Google opened Gemini 3 Pro to all executives.
Read more
Weekly Briefing 9 min read
AI Agents, Thinking Plans, and Automated Workflows
This week's standout story is NVIDIA's Vera Rubin platform and NemoClaw agent stack - a free, open-source governance layer that makes enterprise AI agents production-ready without a team of engineers. If your organization is building internal agents, this is the first thing worth testing.
Read more
Weekly Briefing 4 min read
Small Models, Faster Chips, and Enterprise Data Agents
GPT-5.4 Mini and Nano ship. Vera Rubin specs land. Snowflake runs AI on your data.
Read more
Weekly Briefing 5 min read
1 Million Tokens, a Physical AI Box, and a Federal Deadline
Six days ago, OpenAI shipped the model that makes the 1 million token context window a standard working tool for executives, not a benchmark number.
Read more
Weekly Briefing 4 min read
The Week OpenAI Split the AI World in Two
The same 24 hours that saw 2.5 million people quit ChatGPT also saw OpenAI raise $110 billion at an $840 billion valuation.
Read moreWant the next issue instead of hunting for it?
Get the weekly brief every Thursday, then use the archive when a topic needs more context.
Privacy protected. Cancel anytime.