Skip to content
SVENNISAIWe speak Claude.
Published case study

How Salus Controls Romania moved from GPT to Claude and cut unanswered questions by 60%

Salus Controls Romania supports more than a thousand heating controls, thermostats and connected devices, many with near-identical model codes. Its virtual assistant was answering about the wrong product, and in more than a third of conversations it was telling customers it could not find an answer at all. Svennis diagnosed the cause, repaired the retrieval layer and moved the engine from GPT (OpenAI) to Claude (Anthropic). A month of production traffic later, that failure rate had fallen by 60%.

Book a 30-minute call · with a Claude Certified Architect from our team.

The engagement at a glance
ClientSalus Controls Romania
MigrationFrom GPT (OpenAI) to Claude (Anthropic)
SectorManufacturing, heating and smart-home controls
Scale9,127 Romanian conversations in twelve months
Built withClaude Sonnet 5, Elasticsearch, Neon Postgres, Google Cloud
60%fewer conversations ending in “I could not find an answer”, measured over the first 30 days in production
01The result

Measured in production, approved by the client

60%fewer conversations ending in “I could not find an answer”, measured over the first 30 days in production
52% to 87%of the documents the assistant finds are about the product the customer asked about; tested on 50 real questions, before and after the search was fixed
Two-thirdsof conversations resolved without escalation to a human agent
“Our customers do not care which model answers them. They care that the answer is for the product in their hand. That is what changed.”
Tudor DraghiciuEuropean Technical Director, Salus Controls RomaniaPublished with written approval.
02In short

The story in short

Sally is the virtual assistant that answers product and technical questions on the Salus Controls Romania website, in Romanian, at any hour. It was answering, but too often about the wrong thing. A customer who had selected an SQ610RF thermostat could be walked through a procedure belonging to a different model, and customers were told a manual could not be found when that manual was published and indexed.

Working with Svennis Cloud Solutions, Salus rebuilt Sally on dedicated infrastructure with Claude replacing GPT (OpenAI) as its conversational engine. The fix was not only the model. Svennis diagnosed the retrieval layer, found that only 57% of the knowledge base carried a usable product code, repaired the tagging across the entire corpus, and scoped every search to the customer's own product.

03In production

What actually happened in production

The honest test of any of this is what customers experienced afterwards, so the outcome was measured against the live conversation record rather than estimated. The first 30 days on the new system, against the 30 days immediately before it:

BeforeAfter
Conversations250307
Ended in “could not find an answer”8944
Failure rate35.6%14.3%
Questions per conversation3.223.24

That is a 60% reduction in the share of customers who came to Sally and left without an answer. August, the first full calendar month on the new system, closed at 13.9%, against a baseline that had run between 34% and 45% from April to June.

Two details matter for reading those numbers honestly. Conversation volume went up across the two periods, not down, so the improvement is not the result of quieter or easier traffic. And questions per conversation stayed flat, so customers are not simply giving up earlier.

One caveat, stated plainly rather than buried: the retrieval repair and the change of engine reached production within 48 hours of each other, and nothing in the data separates their individual contributions. This improvement is the result of the whole programme, not of the model change on its own.

04The challenge

The challenge

Sally was answering, but it was too often answering about the wrong thing. Three problems sat underneath that:

  1. 01Products that look alike to a search engineSalus model codes are alphanumeric and densely similar: RT510, RT510RF, RT510TX, SQ610, SQ610RF. To a semantic search these are near neighbours, so a general question returned results drawn from six different products at once.
  2. 02A knowledge base that did not know its own productsOnly 57% of the indexed content carried a product code, and the gap fell hardest on the PDF manuals, which is exactly the material a technical customer needs. Where codes existed they were written inconsistently, the same product recorded five different ways.
  3. 03Real documents reported as missingBecause searches were not scoped to the customer's product, the correct manual often ranked below the cutoff and never reached the assistant. Separately, around 9% of the published Romanian knowledge base was never indexed at all.

The result was a support assistant customers could not fully trust, in a product category where a wrong wiring instruction is not a trivial error.

05The solution

The solution

Svennis Cloud Solutions took the whole system: the infrastructure, the retrieval layer, the conversational engine, the compliance layer and the management dashboard.

The work began with a diagnosis rather than a rebuild. Svennis reproduced the customer complaints against the live search index, established that the widely suspected cause was not in fact the problem, and identified the real one: the assistant received a mixed bag of products on every search because nothing constrained retrieval to the product the customer had selected.

The repair had three parts. Every article and every attached manual was matched against the full Salus product master and stamped with the codes it actually describes, lifting coverage from 57% to 98.5%, with manual attachments inheriting the codes of their parent article. Retrieval was then scoped to the customer's product, inferred from the conversation itself, with a deliberate fallback so general questions are not over-restricted. Finally the indexing pipeline was fixed so newly published articles are stamped correctly on arrival, and short articles stop being silently skipped.

06Why Claude

Why Claude instead of GPT

The move from GPT (OpenAI) to Claude (Anthropic) was tested rather than assumed. Svennis built a 68-case benchmark from real Salus conversations and ran GPT and Claude through it with the same test suite and the same judge.

  1. 01Better recovery of missed answersIn the cases that had previously ended in "I could not find that", Claude recovered more of them than GPT.
  2. 02The correct manual, with a working linkWhen a customer asks for an installation guide, a user manual or a wiring diagram, Claude reliably surfaces the right document rather than a plausible neighbour.
  3. 03It stays inside its briefSally advises and points to documents. It does not invent a procedure, a ticket or a status, and it answers in Romanian regardless of how the question is phrased.

Claude also works behind the scenes

Claude does more for Salus than answer customers. It runs two monthly analyses that make the assistant better without anyone writing new code.

  1. 01Content-gap analysisEach month Claude reads every Sally conversation, isolates the ones it could not resolve, and checks each against the entire knowledge base to establish whether the answer genuinely does not exist. In the first pass, covering roughly a thousand conversations, Claude identified around 20 verified content gaps accounting for about 88 customer conversations.
  2. 02Retrieval-quality analysisIn the same pass Claude reports the opposite failure: questions where the answer already existed but Sally did not surface it, naming the article that should have been used. It is a monthly feedback loop in which the assistant gets better at finding its own content, with no new content required.
  3. 03A dashboard the team actually usesBoth analyses land on a management dashboard built for Salus, with an all-months overview, per-month detail and export, so the team can see precisely where to spend its content effort.

Compliant by design

Sally speaks to Romanian consumers, so the assistant was built to meet EU and Romanian obligations rather than have them retrofitted.

  1. 01EU AI Act transparencySally identifies itself to every customer as an automated virtual assistant before the conversation starts.
  2. 02Personal data masked before storageNational identification numbers, IBANs, email addresses and phone numbers typed into free text are detected and masked before the conversation is stored or sent to the model.
  3. 03Storage limitation and data subject rightsConversation records are deleted automatically after 18 months, and a specific customer's conversation can be exported or permanently erased on request.
  4. 04EU data residencyConversation data is held within the European Union. Sally stays advisory: it can suggest opening a ticket but makes no warranty, refund or credit decision.
07How it works

How it works

  • InterfaceA chat widget on the Salus Controls Romania website, answering in Romanian at any hour, with no login required.
  • IntelligenceClaude Sonnet 5, through Anthropic's platform, deciding how to handle each question and which document to answer from.
  • RetrievalSemantic search over several hundred published articles, manuals and wiring diagrams, scoped to the customer's own product with a fallback for general questions.
  • Knowledge baseEvery article and attachment stamped with the product codes it describes, kept current by a fixed indexing pipeline rather than by manual repair.
  • InfrastructureDedicated Svennis infrastructure: Google Cloud hosting, Neon managed Postgres in the EU, Elasticsearch for retrieval.
08The impact

The impact

  1. 01Most customers never need an agentAbout two-thirds of conversations are resolved without escalation, on live Romanian traffic.
  2. 02The right documents actually surfaceWe asked the same 50 real questions, in Romanian, before and after the search was fixed, and looked at the first five documents found for each. Before, only 52% were about the product asked about; after, 87%.
  3. 03The knowledge base knows its own productsProduct coverage rose from 57% to 98.5%, with 1,508 manual and attachment sections inheriting the codes of their parent article.
  4. 04Invisible content became findableRoughly 9% of the published Romanian knowledge base was invisible to the assistant and is now indexed, including wiring diagrams and compatibility articles customers actually ask for.
  5. 05Verified against real failuresA conversation that had previously failed, an SQ610RF pairing question answered with another product's procedure, now returns the correct steps with the correct sources.
  6. 06Scale9,127 Romanian conversations in the twelve months to July 2026, within 36,467 across all six European regions.

What comes next

Romania is where this platform was designed, built and proven. Salus operates Sally across six European regions, and the same architecture, the same compliance layer and the same monthly Claude analyses are being extended to the rest of them.

09About

The two companies in this story

About Salus Controls Romania

Salus Controls Romania is the Romanian arm of Salus Controls, a manufacturer of heating controls, thermostats, underfloor heating systems, gateways and connected smart-home devices. Its product range runs to well over a thousand distinct item codes, sold to installers and to homeowners, and supported through a Romanian-language knowledge base of several hundred published articles, manuals and wiring diagrams.

About Svennis

Svennis Cloud Solutions designs and delivers AI-assisted business systems built on Claude, and is currently going through onboarding to the Claude Partner Network, Anthropic's partner programme.

For Salus Controls Romania, Svennis delivered the entire Sally platform: the infrastructure, the chat experience, the retrieval and indexing layer, the Claude integration, the EU AI Act and GDPR compliance layer, and the management dashboard, from diagnosis through to live production and ongoing support.

Free, 30 minutes

Wondering what an assistant like this would find in your own knowledge base?

Thirty minutes with a Claude Certified Architect from our team, who builds the AI agents. Bring your own process: you learn whether it is worth automating and what it costs, from the published price list.

Prefer to call? +44 7588 772736 · Not ready to talk? See it on your business first.

30 minutes · video call · free
  1. 1Time
  2. 2Details
  3. 3Booked