Show HN: How we use AI agents for our million-user SaaS (seafile)
The author describes creating SeaTicket, an AI‑driven support tool for their open‑source SaaS. It consolidates context from platforms such as GitHub, Discord, email, and forums to suggest appropriate actions. The goal is to reduce duplicate resolutions, track new bugs, and preserve community trust.
- ▪SeaTicket was built to help a small team manage support issues more efficiently using AI agents.
- ▪The system pulls live knowledge from GitHub, Discord, email, and forum sources to provide action recommendations.
- ▪It aims to eliminate duplicate resolved issues, enable one‑click resolutions, and track new bugs via tickets.
- ▪After internal success, the tool was released to the broader open‑source community to improve support workflows.
Hacker News (AI / LLM) files mainly under ai. We currently carry 2,846 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Ycombinator |
| Canonical URL | https://news.ycombinator.com/item?id=49105561 |
| Publication time | Thu, 30 Jul 2026 02:40:21 +0000 |
| Retrieval time | 2026-07-30T02:53:23.675Z |
| Last seen | 2026-07-30T02:53:24.359Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | wRfkC4QWiRl- · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Hi HN, i want to share my experience of using AI agents.Background: Running an open-source project is no easy task. With a small team handling every issue means valuable time spend on searching for context and doing the right action.Vision: I believe that well-designed software can revolutionize the way we approach work, enabling us to streamline processes, eliminate redundancies, and unlock new levels of creativity and focus.What happened: SeaTicket was created for our own use, so my team can manage the support issues, easily and effectively.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Ycombinator.