Intercom integration guide

How to keep Intercom up to date

Find the outdated articles in your Intercom knowledge base after a change to your product, before Fin repeats them to every customer who asks.

Book a demo Audit your help center for free →

Keeping help centers accurate at

The short answer

What Intercom offers: Your Intercom Help Center comes with features like Fin Operator, which can search for articles affected by a pasted update about your product, plus the Articles report and draft versions for staging edits.
Where it stops: Each one starts from something a person supplies, such as a pasted update, a sad reaction or a failed Fin conversation, rather than from your code changes.
Where Solo fits: Solo reads your code changes, checks them against your articles, flags what a change made wrong and drafts fixes that a person approves before anything goes live.

On this pageShort answer

Why it matters

Why an accurate Help Center matters

You ship a change, support hears about it a week later, and the article still describes the old screen. Meanwhile customers can't self-serve, Fin answers from stale content, and public articles give the wrong answer in search.

Reduce tickets with self-serve support

A current article ends the visit. A wrong one sends the reader into the Messenger, and a disappointed reaction on the article opens a reply asking how you can help.

Fin resolves more conversations

Fin answers from the published articles, snippets and internal articles you enable for it, and changes to articles update Fin automatically. A stale article is repeated as fact, and if the customer gives up, Intercom counts it as an assumed resolution.

Public articles show up correctly in search

Search engines and AI answer engines can quote public articles, so a wrong one reaches people before anyone opens a conversation. Fixing the original later doesn't update the copies already quoted.

Built-in tools

Maintaining your Intercom Help Center with built-in tools

Intercom has real tools for this. Fin Operator finds articles affected by a product change you describe, and Recommendations surfaces gaps from Fin conversations, but both start from what a person tells them or from a customer who already got a wrong answer.

Stage	Intercom's features	Missing features
01Know upcoming changes	Fin Operator, part of the Pro add-on, accepts a pasted update about your product or policy change, so a teammate who hears about a launch can start the search for the articles it affects.	Fin Operator only knows about a change someone brings to it. It can't see your code or feature flags, so a change nobody mentions never reaches it.
02Identify outdated articles	The Articles report shows views, reactions and conversations started from each article, and Recommendations (Pro add-on) flags content gaps plus contradictory or duplicate content. Intercom also suggests sorting Knowledge content by Last updated to find older pages.	The Articles report and Last updated sorting react to customers who struggled or point to pages nobody has touched, which isn't the same as articles your product has outgrown. A recently edited article can still describe an old setting.
03Draft updated copy	Fin Operator proposes edits as reviewable diffs, and Recommendations shows suggested article edits in red and green text that you can adjust before accepting.	Fin Operator and Recommendations draft from a pasted update or conversation data, so they're only as current as what a person supplied.
04Collaborate on updates	A published article can carry a saved draft version with version history, and each article records who last edited it, so teammates can review changes without unpublishing the live page.	Draft versions and version history track who edited, not what is wrong, so reviewers still need someone to tell them which articles a change to your product touched.
05Publish changes	Publishing a draft updates the live article, Fin picks up changes to published articles automatically, and you can schedule publishing for later or schedule several articles at once.	Scheduling picks a date and time, not an event in your product. Nothing publishes an update when a feature flag turns on, so a launch that slips leaves the article live too early or too late.

With Solo

Knowledge base management with Solo on top of Intercom

Intercom can't see your codebase, so it can't know a feature in your product changed unless someone says so. Solo reads your recent code changes and the feature flags tied to them, compares them with your published Help Center articles, and flags the ones a change made wrong. It drafts the fix, and a person on your team accepts, edits or rejects each one.

What Solo adds to Intercom's built-in tools

Stage	Intercom without Solo	Intercom with Solo
01Know upcoming changes	Fin Operator, part of the Pro add-on, accepts a pasted update about your product or policy change, so a teammate who hears about a launch can start the search for the articles it affects.	Solo reads your code changes and the feature flags tied to them, so nobody has to remember to announce a change or paste it in.
02Identify outdated articles	The Articles report shows views, reactions and conversations started from each article, and Recommendations (Pro add-on) flags content gaps plus contradictory or duplicate content. Intercom also suggests sorting Knowledge content by Last updated to find older pages.	Solo searches your published Help Center articles for the ones a change to your product affects and flags them, whatever their last updated date.
03Draft updated copy	Fin Operator proposes edits as reviewable diffs, and Recommendations shows suggested article edits in red and green text that you can adjust before accepting.	Solo proposes the exact old and new text for each flagged article from your code change, or flags a screenshot that may no longer match your product.
04Collaborate on updates	A published article can carry a saved draft version with version history, and each article records who last edited it, so teammates can review changes without unpublishing the live page.	Each flagged article opens as a review item with your product change behind it, where your team can edit the text, accept it, add it to a draft or reject it.
05Publish changes	Publishing a draft updates the live article, Fin picks up changes to published articles automatically, and you can schedule publishing for later or schedule several articles at once.	Accepting a suggestion applies the update to the connected Intercom article, timed to the feature flag being enabled instead of a calendar date. Publishing a draft stays a separate step your team controls.

Questions

Common questions about Intercom articles and Fin

What Intercom teams usually ask before connecting Solo, most of it about Fin.

Does Solo replace anything in Intercom?

No. Your articles, collections and Fin settings stay in Intercom. Solo suggests changes, and the ones your team approves are applied to the connected Intercom article.

Why does Intercom Fin give answers that no longer match your product?

Fin answers from the articles, snippets and internal articles you enable for it, and changes to published articles update it automatically. If an article still describes last quarter's setting, Fin repeats it. If the customer leaves without asking for more help, Intercom counts that as an assumed resolution.

Can Fin Operator tell me which Intercom articles a product launch affects?

Yes, if you paste in a description of the change. Fin Operator is included in the Pro add-on, and it proposes edits as reviewable drafts that nothing publishes until you approve. It can't see your code, so it only knows about changes someone brings to it.

How does Solo connect to Intercom?

An admin connects Intercom from Solo's account settings and authorizes the connection in Intercom. Solo then reads and indexes your published Help Center articles. When your team accepts a suggested update, Solo applies it to the connected article.

Will Solo change Intercom articles without a review?

No. Each suggested change waits for someone on your team to accept, edit or reject it. Solo also limits its suggestions to changes it is confident about, so it flags fewer articles rather than guessing.