
As a finance content creator, I know the daily struggle of turning raw market data into engaging, compliant content across multiple platforms. I built this workflow to save hours of formatting. It strictly separates observed facts from interpretation, flags missing sources, and strictly avoids investment-advice language. This is the exact system designed to generate newsletters, X threads, and video scripts safely and efficiently every single day.

Paste news (headlines, body text, multiple articles) and instantly get a clean digest structured as key points, background, impact on life/business, and what to watch next. Formats for stand-ups, internal sharing, newsletters, and social. Source text is never copied — summarized and paraphrased only; speculation and facts are kept distinct, and investment/medical/legal topics avoid advice. Turn daily news triage into seconds.

Your export says salaries came in $20k over budget. It doesn't say if that's two new hires (raise the forecast) or a one-off bonus (ignore it). This Agent closes that gap. Drop in a budget-vs-actual export (CSV or Excel) and get the variance maths — favourable vs unfavourable, a two-test materiality screen, per-period margins — plus the CFO commentary: headline, reconciling bridge, top 3 drivers, actions. It won't call an underspend a saving, and flags the favourable variance masking a bad one.

Turn Excel or CSV research data into editable Origin projects, publication-ready figures, reusable templates, and QA reports.

Personal JLPT tutor (N5–N1): generates an original daily Japanese practice quiz as interactive HTML, grades your pasted answers, tracks weak points over time, and promotes you level by level. Coaching language auto-matches yours (zh-TW / zh-CN / en / ja).

Builds a ready-to-post World Cup matchup short: the script comes first, followed by on-screen text, caption, hashtags, pre-publish checks, and supporting analysis. No betting or odds.

Paste your rough weekly bullet points and get a polished, submission-ready report in six clear sections. Internal or external tone. Built for weekly reuse.

Rebuild a spreadsheet of hardcoded numbers — the kind that breaks when you change one cell and that nobody trusts enough to take to a board or VC — into a driver-based, three-statement linked model you can actually stress. Scope by purpose, build a driver tree (price × volume × retention, not a growth rate from thin air), link P&L → Balance Sheet → Cash Flow, centralize inputs in one assumption layer, run base/bull/bear scenarios with sensitivity, and sanity-check against benchmarks.

Paste a YouTube link, get a report on the top 500 comments by likes: sentiment split, repeat questions for a pinned FAQ, next-video ideas, complaints, the 8–10 comments to answer first with draft replies, and best-comment highlights. Six weighted factors rank reply priority; every finding quotes the source comment. Raw data saves to a 10-column CSV; multiple links trigger channel cross-analysis. No API key, no login — free open-source yt-dlp, data stays local. Drafts only; never auto-posts.