Skip to content
Nerdy beta

Advanced AI

Add to Space
 AI

The chat drawer is a retrieval-augmented search over the collection: your question gets matched against every published note, the best matches are fed to the model as context, and you get back an answer grounded in the material. This guide covers the controls that make it land better — structured filters, the context meter, and how conversations persist.

How search works

Your message is embedded and matched semantically against the collection’s note chunks. Frontmatter — type, tags, framework, sources, authors, key concepts — is rolled into those embeddings, so a query like “workshops about flow from Accelerate” can find the right notes even if they never use the word “workshop” in the body.

The top matches appear to the model as “Related notes from the collection” alongside the page you’re currently reading. If you’re in a workshop cohort, the search also reaches that workshop’s slides; nobody else’s chat sees them. You don’t need to ask the assistant to “search the collection” — every turn already does.

Filtering with structured queries

You can narrow retrieval by adding key=value pairs anywhere in your message. The parser pulls those tokens out; the rest of the sentence is what gets matched semantically.

IntentSyntaxExample
Equalkey=valuetype=Workshop
Equal with spaceskey="quoted value"type="Case Study"
Not equalkey!=valuetype!=Article
One of severalkey=[a, b, c]type=[Workshop, Playbook]
Has a tagtag=valuetag=team-dynamics
Links to a notekey=[[Note Name]]source=[[Team Topologies]]

Multiple filters in one message combine with AND. tag=X is sugar for “the tags list contains X.” Wikilink values are resolved against real collection pages, so the note has to exist for the filter to bind.

The filterable fields are the ones this collection indexes as structured metadata: type, framework, source, problems, workshops, related tools, key concepts, authors, author, tags, date. Filtering on anything else silently falls back to pure semantic match.

A few queries you can try:

type=Workshop how do I run a team API session
tag=flow source=[[Accelerate]] what does healthy delivery look like
type=[Case Study, Playbook] where have teams gotten 30x ROI
framework=[[Team Topologies]] stream-aligned vs platform teams

Applied filters are echoed back to the model in the system prompt, so the assistant knows you’ve narrowed scope and won’t wander off it.

The context meter

Beneath the composer is a thin bar that tracks how much of the chat’s 200k-token ceiling your current conversation is using. It measures the live chat — your messages plus the assistant’s replies — not the base system prompt or attached pages, so New resets it to zero.

BarMeaningWhat to do
GrayUnder 60% of the 200k ceilingKeep going.
Amber, “Context filling up”60–85%Wrap up the current thread. A Start fresh button appears next to the bar.
Red, “Context full — older messages will be dropped”Over 85%Start a new chat. At this point early turns are being truncated and the assistant is losing what you discussed earlier.

The model is Claude Sonnet 5.5. Its own context window is 1M tokens, but the meter runs against a 200k ceiling the chat sets for one thread, and the chat sends only the last 40 messages. In a long thread the oldest turns drop first, so the conversation quietly degrades into an assistant that’s forgotten how you framed the problem ten messages ago. Shorter, scoped chats beat one sprawling session. When the bar turns amber, land the current thread, hit New, and if you want continuity, paste the one or two conclusions worth carrying forward.

Managing conversations

Open the drawer’s sub-toolbar for history. Past conversations are listed newest first; click one to reopen it with the message thread restored. Each conversation remembers which page it started on, so it stays useful even after you navigate elsewhere in the collection.

Where history lives depends on whether you’re signed in:

  • Signed in: conversations sync to your account and follow you across browsers and devices.
  • Anonymous: conversations are stored in your browser’s local storage on this device only. Clearing site data wipes them. Sign in and the conversations already in that browser move to your account.

History is global across the collection, not per-page. You can start a conversation on one note and continue it from another — the drawer knows which page context belongs to which conversation.

Page context

The page you opened the drawer on is attached automatically. As you navigate during a chat, the last three non-home pages you visit get added to context as well, so the assistant can see where you’ve been. Every page in the collection is open, so there’s no page the drawer won’t talk about.

Tips

  • Lead with filters, finish with intent: type=Playbook how do I start a discovery sprint beats asking for “playbooks about discovery” and hoping.
  • If answers feel generic, anchor them with a tag= or source=[[...]]. Semantic search cast wide will find something; narrowing the field usually sharpens the answer.
  • Watch the meter on research sessions. One focused chat per question is worth more than one marathon chat per day.
  • Wikilink filter values must match an existing collection page title — a typo resolves to nothing and the filter drops silently.