Free field tool

Give your AI current knowledge

Every model has a training cutoff. The software you use every day does not. That gap is why your AI describes a menu that moved, a feature that shipped, or a price that changed, and sounds certain doing it. The fix is not a better prompt. It is a reference folder.

Works with any AI · Nothing to sign up for
01 The gap

A model does not know what it does not know

Ask about a feature released after the cutoff and most models will not stop to say so. They answer from the nearest thing they saw in training, which is usually last year's version of the same product. The answer arrives fluent, formatted and wrong, which is the hardest kind to catch.

✗ What it does

Fills the gap quietly

You ask where a setting lives. It gives you a path that was accurate eighteen months ago. You go looking, do not find it, and assume you are the problem. Nothing in the answer signalled uncertainty, so nothing prompted you to check.

✓ What you want

Answers against a source

You hand it the vendor's dated release notes first. Now it answers from that, and when something is missing it can tell you so, because it has a defined edge to bump into. You get a real answer or a real gap. Both are useful.

This is not a search replacement. Search is per-question and depends on what the model decides to look up that time. A reference folder is standing context you control: the same vetted, dated pages, loaded every time. Use both. Search fills gaps, the folder sets the baseline.
02 The move

Four steps, about fifteen minutes

Do this once per tool you actually depend on. Not every app you have logged into. The two or three where being wrong costs you something.

Step 01

Go to the source

The vendor's own release notes or changelog. Not a blog roundup, not a video summary, not a forum thread. The dated page the company publishes itself.

Step 02

Pull what changes

Release notes first, because they carry dates. Then the limits pages: privacy, licensing, what the tool will and will not touch. Skip the marketing pages entirely.

Step 03

Load it as reference

In Claude, add the pages to a project or turn them into a skill. Anywhere else, paste them at the top of the thread before you ask your first question.

Step 04

Re-pull monthly

Date-stamp the file. A stale reference folder is worse than none, because it makes the model confident about features that already changed.

03 Build yours

Pick your tool, take the file

Choose what you actually use. The sources, the paste-ready instruction and the downloadable skill all update to match.

Claude

Paste this above your notes

  

Use this in any AI tool. Open the source, copy the release notes, and drop them where the block says. The instruction is what makes the model treat your notes as authority rather than as one more opinion.

Claude skill · SKILL.md

  

A skill loads itself whenever the topic comes up, in any chat, so you are not re-pasting. Download the file, then add it to Claude as a skill. Paste your pulled notes into the Current notes section before you use it, and replace that section on every re-pull.

04 Where the docs live

Official sources, verified

Every link below is the vendor's own dated page, checked on 6 August 2026. Bookmark the ones you use. These are the pages to re-pull from, not the ones to read once.

Claude · the apps

Claude release notes

Dated updates for the Claude apps, Cowork and integrations. Start here if you use Claude to think.

support.claude.com › release notes
Claude · the platform

Claude Platform release notes

API, SDKs and console changes. Has an RSS feed, so you can watch it instead of remembering to check.

platform.claude.com › release notes
Microsoft

Microsoft 365 Copilot release notes

What actually shipped to general availability, split by platform. The single best page for Copilot currency.

learn.microsoft.com › release notes
Microsoft · the limits

Microsoft 365 Copilot docs

Privacy, data boundary, governance, licensing. Written for IT, which is exactly why the limits are stated plainly.

learn.microsoft.com › Microsoft 365 Copilot
OpenAI

ChatGPT release notes

Dated feature changes for ChatGPT across plans. Separate pages exist for Enterprise, the desktop apps and agents.

help.openai.com › ChatGPT release notes
Google

Google Workspace Updates

Weekly recaps covering Gmail, Docs, Drive, Meet and Gemini in Workspace. Pull the recaps, not the product pages.

workspaceupdates.googleblog.com
Building your own agents rather than using the tool? Then you want the platform docs too: Copilot Studio for Microsoft, and the Claude Platform notes for Anthropic. Skip both until you have outgrown what the product does out of the box.
05 Keep it honest

Three rules that keep this working

A reference folder is a small amount of maintenance that buys a large amount of accuracy. It stops buying anything the moment you stop maintaining it.

Date every file

Put the pull date in the file itself, not just the filename. When the model quotes it back, the date comes with it, and you can see how much to trust it.

Replace, do not append

Swap the old notes out. Stacking three versions of the same release notes teaches the model to blend them, which is how you get features that never existed.

Let it say it does not know

The instruction that earns its place is the one telling the model to flag gaps instead of filling them. An AI that admits an edge is more useful than one that never has one.

This is the whole Prickled posture in one file. Capability, not a crutch. You are not asking the AI to be smarter. You are giving it better inputs and keeping the judgment for yourself, which is the only version of this that compounds.
06 Questions

Reasonable objections

Why does my AI get product features wrong?

Because it has a training cutoff and the product does not. Software ships continuously. When a model is asked about something released after its cutoff, it rarely says it does not know. It answers from the closest thing it saw in training, which is often last year's version of the same product.

Is this the same as turning on web search?

No. Search is per-question and depends on what the model chooses to look up in that moment, and on which page happens to rank. A reference folder is standing context you chose: the same vetted, dated pages every time. Use both. Search fills gaps, the folder sets the baseline.

How often do I have to refresh it?

Monthly for most tools, and right away after a major release. If that sounds like too much, watch an RSS feed where the vendor offers one and refresh when something lands. The Claude Platform notes publish a feed.

What is the difference between a Claude project and a Claude skill?

A project holds reference files for the conversations inside it. A skill is a portable instruction file that loads itself whenever the topic comes up, in any chat. Use a project when the work is contained. Use a skill when you want the knowledge to follow you everywhere.

Will pasting docs use up my whole context?

It can if you paste an entire documentation site, which is why the steps say release notes first. Notes are short, dated and dense with exactly what changed. If a page is enormous, keep the last two or three months and drop the rest.

This is one file. There is a system behind it.

A reference folder fixes what your AI knows. It does not decide what you are trying to accomplish. That part is the strategy, and it is the part Prickled builds with you.

Start a build →