> For the complete documentation index, see [llms.txt](https://gaffa.dev/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://gaffa.dev/docs/changelog/2026/readme.md).

# October

### AI Tools

#### Gaffa AI skills and Gaffa CLI, now available

Your coding agent can now write and review Gaffa code, find information on a live website, debug a failing request, and prepare a support report when something goes wrong. The AI skills work in Claude Code, Codex, Cursor, GitHub Copilot, Antigravity, and Pi. Install them with one command using the Gaffa CLI, which also sets up the Gaffa docs MCP server for you:

```shellscript
npx @gaffa-dev/cli install
```

[Read the docs.](https://gaffa.dev/docs/ai-tools/)

### Platform Improvements

#### Improved reliability on complex sites

We've been working on the browser infrastructure behind Gaffa's scraping browser. This means fewer failed requests and more reliable access to complex public sites, with no changes needed to your existing requests.

### Samples, Blog & Tutorials

#### Why AI Adoption Is Fueling Demand for Better Web Data Extraction

We wrote a piece for SourceForge on how AI has changed the economics of web scraping. LLMs can now generate and fix selectors in seconds, but bot detection has evolved just as fast, and keeping a scraper running in production now means managing fingerprinting, proxies, sessions, and constant detection changes. The article covers why asking your agent to rebuild that infrastructure tends to make things worse, and why giving agents a dedicated retrieval layer keeps that complexity out of your codebase. [Read the article.](https://sourceforge.net/articles/why-ai-adoption-is-fueling-demand-for-better-web-data-extraction/)

#### Scrape Twitter (X) Without an Account

We published a tutorial on scraping public tweets with Python and Gaffa’s `capture_dom` action, with no X login, developer credentials, or local browser. It walks through using `wait` to load the profile, collecting tweet URLs from the captured HTML, and saving each post’s text, timestamp, and engagement counts as JSON. It also covers how to get an exact UTC timestamp from the tweet ID itself. The full code is on GitHub. [Read the blog.](https://gaffa.dev/blog/how-to-scrape-twitter-without-authentication-using-gaffa)


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://gaffa.dev/docs/changelog/2026/readme.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
