Use case
Flocci Chat for SaaS products
Short answer
For a SaaS, Flocci Chat turns the content you already maintain — landing pages, docs, pricing, changelog — into a grounded assistant that deflects repetitive tickets with cited answers, verifies logged-in users cryptographically, and executes account actions (subscription status, usage) against your own API.
The SaaS support loop, automated where it should be
Most SaaS tickets are answered somewhere already — the docs page nobody found, the pricing FAQ, the changelog entry. Flocci Chat closes that loop: the widget learns every page (docs sites and SPAs included, since it reads rendered DOM), answers with citations to the exact doc, and its unanswered-intents report tells your team precisely which questions your docs still don't cover. Support volume becomes a documentation roadmap.
Logged-in users get real answers, not deflection
With the one-call identity integration (flocciChat.identify(user, hmac) — HMAC-SHA256-signed, so identity can't be spoofed), the assistant knows who it's talking to. Configure actions against your own API and "what plan am I on?", "how many seats do I have left?", "where's my invoice?" get answered from live data, with the verified identity attached in signed headers. Escalations open tickets in the built-in inbox with the whole transcript — your engineers see what was tried before they're pinged.
Fits how SaaS teams already work
- Context API: your app can push the user's current screen state so answers reflect what they're looking at.
- Private surfaces stay private:
data-passive-ingest="off" on the logged-in app keeps in-app DOM out of the knowledge base.
- Quality ops: answer evals, reliability metrics and a launch checklist — the same gates Flocci runs before its own products go live.
- Proof: Flocci Chat is the support layer for 13+ Flocci SaaS products, including this page.
Frequently asked questions
Can the chatbot answer questions about a user's own account?
Yes — after your app verifies the user with an HMAC-signed identify call, the assistant can call your API (order status, subscription, usage) with signed end-user headers and answer from the live result.
Will it learn our docs site if it's a separate subdomain?
Embed the same widget on the docs site — one workspace can learn every surface you put it on, and the onboarding crawl can target the docs sitemap directly.
How do we stop it answering questions about unreleased features?
It only knows published content. Staging and internal pages simply aren't ingested — and passive learning can be disabled per surface with data-passive-ingest="off".
What does it cost for a SaaS with a few hundred questions a month?
Often nothing for the first month — 500 free signup credits cover ~500 answered messages. After that, 1 credit per answered message; ticket handling, ingestion and analytics stay free.
Try it on your own website
One script tag. 500 free credits — roughly 500 answered visitor messages. Every feature on, no card. The widget in the corner of this page is the product, running on its own site.
Create your workspace — free