Add to Chrome
For Confluence

AI assistant for Confluence - built for the page you’re on.

Sidenote is a browser extension (Chrome, Edge and Firefox) that reads Confluence from the page DOM, on the session you're already signed into. Open a page, ask a question, click a citation: Sidenote scrolls the live page and highlights the exact passage that proves the answer. No admin install, no server-side ingestion, works on pages behind your company login.

Add to Chrome (free)See how it works

Works with Confluence Cloud, Server & Data Center · No admin install

yourteam.atlassian.net/wiki · Deploy runbookSidenote
Engineering · Deploy runbook

To roll back a bad deploy, run ./deploy rollback --to-last-green from the release runner; it repoints traffic to the previous green build in under a minute. Note that rollbacks are blocked during the Friday 16:00–20:00 UTC freeze window - page the on-call lead to override if it's urgent.

Sidenote
How do we roll back a bad deploy?

Run ./deploy rollback --to-last-green from the release runner to repoint traffic to the last green build 1. Just check the clock first - rollbacks are blocked during the Friday change-freeze window unless on-call overrides 2.

The problem

Confluence search wasn’t built for answers.

Every fast-growing team has the same dirty secret. Twelve thousand pages, half of them stale, the same five answers re-asked in standup every week. The current runbook lives somewhere between Deploy runbook (NEW) and Deploy v1 (DEPRECATED), and Confluence's built-in search ranks them roughly the same.

Sidenote doesn't replace your wiki. It teaches it to answer: in your browser, on the pages you already have open, with a citation you can verify in one click and judge for staleness yourself.

How it works

How Sidenote works on Confluence.

STEP 01

Open a Confluence page

Sidenote rides along in your browser's side panel. Open a Confluence page and the extension extracts it through a dedicated wiki extractor: clean text, headings, tables, links.

STEP 02

Ask the question you'd ask a senior

“Where do we deploy hotfixes?” “Which spec is current?” “What's the SLA for refunds?” Sidenote queries across every Confluence page you've opened - not just the one in front of you.

STEP 03

Click a citation, see the passage

Every claim is grounded in a quoted chunk of the source page. Click the chip; Sidenote scrolls the live Confluence tab to the exact paragraph and highlights it in amber.

Working across a handful of related pages? Bundle them into a collection and query the whole set in one go - citations name the source page. Prefer the head-on pitch? See chat with documents.

Use cases

What teams ask Confluence - and how Sidenote answers.

  • “Where do we deploy hotfixes?”

    Sidenote answers from the current runbook and quotes the exact step - not the deprecated v1 page two hits below.

  • “Who's on call this week, and how do they escalate?”

    It reads the rota page and the escalation matrix in the same answer, with a citation back to each.

  • “Why did we pick Postgres over DynamoDB?”

    ADRs are gold buried under a year of Slack threads. Sidenote surfaces the decision and the trade-off paragraph.

  • “How do we handle refunds for enterprise customers?”

    Support reps stop refreshing the policy page. Sidenote quotes the clause that applies and shows the date it was last reviewed.

  • “What's the rollout plan for feature X?”

    PRDs, milestone pages, and roadmap docs queried together - citations point at the row in the rollout table.

  • “I'm new - how do I get set up on day one?”

    New hires query the wiki directly instead of pinging seniors. Onboarding stops being an interrupt.

Private by design

Built for private pages - because it runs in your browser.

Server-side Confluence AI has a structural problem with restricted pages: it fetches your wiki on someone else's infrastructure, with someone else's OAuth credentials, against an API that returns whatever those credentials are allowed to see. Restricted spaces, draft pages, pages behind extra ACLs: most are invisible to that pipeline, or need an admin to grant broader scopes than the organization is comfortable with.

Sidenote sidesteps the whole question. It reads the same DOM you read, on the same session you're already signed into. If you can open the page, Sidenote can answer about it. If you can't, neither can Sidenote. Permissions stay exactly where Confluence put them.

Your wiki content stays in your account.

Each user's pages live behind row-level security in our UK (eu-west-2) Supabase region, so your content stays scoped to your account. Anthropic and Voyage AI both run with no-training defaults on the API tiers we use; we never fine-tune models on user content.

Whole-space indexing

Index a whole space, not just the page you're on.

Opening pages one at a time is fine for a quick answer. When you need the whole runbook space or every onboarding doc, open any page in the space and Sidenote shows an Index this space card that crawls it for you. Available on Pro+ and Pro Max, and for owners and admins on the Team plan.

Through your own session

The crawl runs in your browser on the Confluence session you're already signed into, so your credentials never leave the page and there is still nothing for an admin to install. It only reaches pages your account can already open, and works with Confluence Cloud, Server, and Data Center.

Its own monthly page budget

Space pages have a separate monthly allowance from your document cap, so indexing a space never spends it: 200 pages a month on Pro+, 500 on Pro Max and for Team owners and admins, with 20 included in the 7-day trial. Re-indexing a page you already have is free.

Paced, resumable, collected

Sidenote paces the crawl gently, no faster than about two pages a second, and you can stop it at any time and resume from where it left off. Every indexed page lands in a collection you can query as one grounded, cited source.

Space indexing is included on Pro+ and Pro Max, and for owners and admins on the Team plan; the free and Pro plans don't include it, and regular team members can't start a space index. See the plans and page allowances.

Compared honestly

Sidenote vs other Confluence AI tools.

Three honest framings. The shorthand each time: Sidenote is the lightweight, per-user, browser-native option, designed to coexist with heavier platforms rather than replace them.

vs Atlassian Rovo

Atlassian's own AI - tightly integrated with Cloud, sold as a per-seat add-on. Server-side, Cloud-only. Sidenote runs in your browser, so it works with Cloud, Server, and Data Center, and there's nothing for an admin to install.

vs eesel AI

Ingests your Confluence server-side via OAuth and builds a separate index. Sidenote stays per-page and opt-in: nothing is read until you open a page yourself. There's no global crawl of your wiki and no third-party-hosted copy of every doc.

vs Glean

Enterprise search across many tools - powerful, expensive, and heavyweight to deploy. Sidenote is a £10/month-per-user extension your team can try this afternoon, and the citation chips highlight the exact passage inside the live Confluence page.

FAQ

Common questions about Sidenote for Confluence.

No. Sidenote is a browser extension for Chrome, Edge and Firefox - your team installs it from the store the same way as any other extension. There's nothing to deploy in Confluence itself, no Forge app to approve, no OAuth scopes for an admin to grant. Each user signs into Sidenote with their email; Confluence is read locally from their own browser session.
Yes. And this is the part most server-side tools cannot do. Sidenote runs inside your browser, on the session that's already signed into Confluence. It reads the same DOM you can see. Pages behind your company SSO, restricted spaces, draft pages - anything you can open in your browser, Sidenote can answer questions about.
Not automatically. By default Sidenote is per-page and opt-in: a page is indexed only once you open it with the side panel active. On Pro+ and Pro Max (and as a team owner or admin on the Team plan) you can also index a whole space in one go, but you trigger that yourself, it runs inside your browser on your own signed-in session (never on our servers), and it only reaches pages your account can already open. There's no admin install and no background crawl of your wiki. Indexed pages land in a collection you can query together.
Yes, on Pro+, Pro Max, and for owners and admins on the Team plan. Open any page in the space and Sidenote offers to index the whole space through your own signed-in Confluence session, so your credentials never leave your browser and there's still nothing for an admin to install. It works with Confluence Cloud (v2 API) and Server / Data Center (v1), and only reaches pages you can already open. Space pages have their own monthly allowance, separate from your document cap: 200 on Pro+, 500 on Pro Max, and 500 for Team owners and admins, with 20 included in the 7-day trial. The crawl paces itself, can be stopped and resumed, and lands every page in a collection. The free and Pro plans don't include space indexing, and regular members on a Team plan don't get it either.
No. Anthropic (the model provider) and Voyage AI (the embedding provider) both run with no-training defaults on the API tiers Sidenote uses, and Sidenote never fine-tunes models on user content. Your wiki content is used only to answer your own questions and is stored in a UK (eu-west-2) region with row-level security isolating every account.
Rovo is Atlassian's own AI for Confluence Cloud - tightly integrated, but locked to Atlassian Cloud, sold as a per-seat add-on, and operated server-side. Sidenote is a lightweight per-user extension that works with Cloud, Server, and Data Center because it reads from your browser on your own session rather than a server-side Atlassian integration. The two can coexist; the value Sidenote adds is cross-tab, browser-native answers and citation chips that scroll the live page.
Yes: because Sidenote reads on your own browser session, not through a server-side integration. Confluence Cloud, Server, and Data Center all serve the page DOM in the same way to your browser; Sidenote's Confluence extractor works against all three, and whole-space indexing uses each one's native REST API (Cloud v2, Server / Data Center v1) from that same session. The same applies to self-hosted intranets that render HTML.
Try it on your wiki

Make your Confluence answer back.

Add Sidenote to your browser, open a Confluence page, and ask the question you keep asking your senior engineer. No admin install. Free tier forever, opt-in 7-day Pro trial, no card required.

Add to Chrome (free)See pricing

Works with Confluence Cloud, Server, and Data Center