At checkts.gpa.at, an AI legal chatbot that GPA, the Austrian trade union for private-sector employees, launched with Honeyfield and Studio C, 88 percent of users open the cited paragraph beneath each answer and 12 percent click through to the Federal Legal Information System (RIS), according to an April 2026 blog post by the agency Honeyfield.
"You don't need a better model, you need a better loop," the post says (translated from German), summing up the central design decision: the model is not trusted to recall citations from memory, so the chatbot cannot name a paragraph until it has searched the RIS and matched each reference against the search results. Citations that do not match are flagged and logged.
GPA wanted low-threshold first-tier legal information — not formal legal advice — for both members and non-members, sitting between a web search for notice periods in Austria and a booked lawyer appointment. Production analytics show the use case landed on hard topics: 27 percent of topic clicks are about overtime, 17 percent about termination, 16 percent about mobbing, 15 percent about salary questions, with roughly three quarters of usage in those four areas.
Rather than a single end-of-project acceptance, the team ran continuous calibration with GPA's in-house legal experts throughout the test phase: where the agent's RIS research was too shallow, the response was deeper pre-answer searching, not better prompt wording.
In the agent, every content question triggers a live RIS search before any paragraph can be cited, and each citation is verified against the search results. The legal integration was extracted into ris-mcp, an open-source MCP server (github.com/Honeyfield-Org/ris-mcp-ts) wrapping the Bundeskanzleramt's public RIS API with 13 tools — federal law, all nine federal states' law, and jurisprudence from 16 court jurisdictions. Honeyfield's AgentHub orchestrates the loop with auto-rollback on a failed health check; an AI Gateway adds PII detection, per-IP rate limits and content security policy. More than 80 governance rules are wired as structured code: mandatory disclaimers on notice-period questions, mandatory handoff on mobbing, prohibition of concrete legal recommendations, and the citation rule.
Under each answer sits a thumbs-up/down button, an expandable cited paragraph and a one-click path to the original RIS page. On termination, mobbing and insolvency topics the bot is structurally prevented from continuing without offering a transfer to GPA legal experts, and analytics show two thirds of handoffs originate from the sidebar, the rest from mobile and widget. The disclaimer UX — modal on first visit, persistent banner at top, warning emoji at the end of each answer — keeps the product from claiming to be legal advice. Asked how long the notice period is after eight years in a job, it returns a structured list of statutory notice periods, cites section 20 of the Salaried Employees Act and adds a note that three legal sources were checked.
The post describes the system as finished in the sense of production-ready, not in the sense of having stopped learning, and says the same pattern of RIS-grounded citation, structured governance and expert calibration could apply to other regulated fields such as insurance, HR and tax advice. The ris-mcp server is publicly available on GitHub for any team building on the RIS.