Show HN: DocCharm – The help center that keeps itself up to date

Show HN: DocCharm – The help center that keeps itself up to date(doccharm.com)

6 points by yakshaving_jgt 4 hours ago | 1 comment

Hello HN!

We were finding it too much work to keep our Zendesk help center up to date as our product kept changing, so I built DocCharm — it keeps a help center up to date automatically by watching PRs as they land in your GitHub repository. It suggests updates (with AI) to existing articles, or drafts entirely new ones if nothing appropriate exists yet.

Everything goes into a review queue first, so a human always checks (and can optionally edit) before anything publishes. In practice this has proven to be a pretty slick workflow (in my opinion anyway, but not only!).

We’ve been using it at my main job for a while now and it’s a big time saver. It’s also gaining some traction with other companies in the same investor portfolio. My sales process so far has been high-touch outbound. This probably won’t scale in the long run, but I’m hoping to learn as much as I can by nurturing all of the initial relationships. If you run a business with a help center that’s drifting out of date, email me and I’ll comp your first couple of months. Email is in my HN profile.

Both Zendesk and Mintlify help centers can already be automatically imported into DocCharm. If you use a different help center, let me know and I’ll get it automatically imported one way or another. I've also implemented some support for theming, so you can keep your own branding.

The tech is essentially the same that I use for most of my work (and it's not a differentiator, but we're all tech-curious here):

- Haskell/Yesod

- NixOS

- SQLite with Litestream (db per tenant; backed up on both Hetzner and Cloudflare; encrypted)

- Sentry for error reporting

- Stripe for billing

- Healthchecks.io as a dead man’s switch

- Prometheus and Grafana for telemetry

- Resend for transactional email

There's plenty still to do on the roadmap, but this is already working nicely and providing value as is. I'm not building in the open, though what I prioritise will naturally be heavily guided by the needs of the earliest users.

WDYT?

bastawhiz 1 hour ago |

I'll be honest, I'm not signing up for an account to look at this. The marketing site has zero screenshots. The help center you link has...20 articles total? Few enough that it seems like all of them are listed on the main page. That's not reassuring.

The plans are based on the number of "products" but this is never defined. This isn't defined in your help center. In fact, the help center returns every article for every search, just changing the ranking.

I already pay for a help center. My tools work with my help center. I've got links to my help center. You're asking me to throw out everything to start fresh on a platform with almost no information. Honestly, this is the wrong play. Don't build your own, update your users' existing sites. I'd gladly sign up for a trial of a service to manage my help site for me. But I'm not getting a new one without a lot more confidence that it's worth it.

yakshaving_jgt 45 minutes ago | |

Thanks for the feedback.

I hadn’t considered that someone would want to see screenshots of the application on the landing page since they can just log in and interact with it themselves. But clearly, this was a gap.

> I've got links to my help center. You're asking me to throw out everything to start fresh on a platform with almost no information.

It is possible to automatically import a help center from Zendesk or Mintlify. Content is re-hosted and links are rewritten so everything links internally the way it does on your existing help center. As you’ve pointed out, this should be communicated more clearly.

> Don't build your own, update your users' existing sites.

I had considered this initially but it didn’t fit my initial use case at the time. But I think it’s worth me reviewing this because I can see how this would be less friction when getting started, and also less perceived risk when choosing whether or not to adopt a new tool.

Again, genuinely appreciate the feedback :)