> For the complete documentation index, see [llms.txt](https://thecontentforge.gitbook.io/thecontentforge-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://thecontentforge.gitbook.io/thecontentforge-docs/feature-guides/forge-says.md). # ForgeSays ForgeSays (formerly Grok Says) is a live signal feed for crypto-relevant intelligence, community sentiment, market movement, and real-time events. It brings timely context into the content workflow so your team can react with hours, not days, of lead time. > **Note:** The page lives at `/forge-says`. Old `/grok-says` links continue to work and redirect here automatically. ### 12-Hour Trend Scan ForgeSays now includes a companion page at `/forge-says/trends` - the **12-Hour Trend Scan**. Every 12 hours it pulls the top 20 things trending on X, enriches each one with context, and (after personalization) attaches brand-relevant angles you can send straight into [Content Forge](/thecontentforge-docs/feature-guides/content-studio.md). Use the **12-Hour Trend Scan** card from this page to open it. See [Trend Scan](/thecontentforge-docs/feature-guides/trend-scan.md) for the full breakdown. ### What it gives you * **Signal cards** - short, specific observations about what is moving right now * **Priority badges** - `URGENT` and `TODAY` flag time-sensitive signals worth acting on first * **Viral-topic badges** - call out themes already accelerating across the network * **Category filters** - narrow the feed to one subject at a time * **Source-grounded prompts** - verified, cited context you can carry straight into Content Forge * **Recommended actions** - quick suggestions for how to respond if relevant to your brand ### Categories The category strip across the top filters the feed to a single subject at a time. Use it to keep your editorial focus narrow on busy news days. Out of the box you get six categories aimed at crypto and markets - Crypto, Political, Geopolitical, Finance, Regulation and Memecoins. **They are yours to change.** Click **Categories** in the header (editors and admins) to open the category manager, where you can: * **Rename** any category, and give it a different icon and colour * **Steer the research** - each category carries *must cover* points (the AI has to work these in whenever the 12-hour window supports them) and *nice to include* points (used when relevant, skipped when not). This is the single biggest lever on what you get back. * **Add your own**, up to 12 total - "AI & Tech", "Sports betting", whatever your brand actually posts about * **Turn one off** instead of deleting it, if you only want it out of the way for now * **Reorder** them so your most-used category sits first Two smaller options sit behind *Advanced* on each category. **News keywords** decide which incoming stories get matched to that category; leave it empty and the category's name and focus points do the matching. **Prompt name** is an optional longer name the research runs under (for example, the built-in "Crypto" category researches as "Crypto & Web3"). Changes take effect on the next run - use **Refresh** on a single category, or **Run All Categories**, to see them applied. Category names are translated into the other interface languages automatically; you can correct any of them under *Translations*. If you never open the manager, nothing changes: the original six categories keep working exactly as before. ### Verified vs fallback enrichment Cards that come back with full source citations are marked **verified**. When clean citations can't be found, the card still carries relevant URLs and context, so the feed stays useful instead of empty. Fallback-enriched cards are clearly distinguished from verified cards. ### Web3 Project orgs Web3 Project orgs see a tailored ForgeSays variant - an opportunity radar built from the sources you track under **Settings → Project Knowledge → ForgeSays**, rather than the news feed above. Instead of subject categories, opportunities are sorted into **action buckets**: Positioning, Quote post, Reply, Explainer, Fresh post and Ignore. These are editable in the same way - click **Buckets** in the header to rename them, change which tracked-source roles feed each one, add keywords that route an item into a bucket, and set which Content Forge type an item is handed off as when you hit Generate. Changes apply on the next **Rescan sources**. ### Workflow 1. Open ForgeSays at the start of your content session 2. Pick a category, or leave it on All 3. Skim the latest signals - start with `URGENT` and `TODAY` cards, then anything tagged viral 4. Pull anything relevant into [Content Forge](/thecontentforge-docs/feature-guides/content-studio.md) as a generation prompt 5. If a signal looks like a major shift, open an [Experiment](/thecontentforge-docs/feature-guides/experiments.md) ### Tips * ForgeSays is not a content calendar - treat it as input for your editorial judgment * Not every signal will be relevant to your brand, and that's expected * If the feed feels off-target, edit the category's *must cover* points rather than regenerating repeatedly - that is what actually steers the AI * Verified cards make for safer breaking-news content; fallback-enriched cards are still useful but worth a quick fact-check before publishing --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://thecontentforge.gitbook.io/thecontentforge-docs/feature-guides/forge-says.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.