Skip to main content
Viithiisys
Repetition, not judgement

Answer the questions your team answers forty times a day, without guessing at the ones that matter.

We automate the support work that is genuinely repetitive and route the rest to a person with the context attached, because the expensive failure in support is a confident wrong answer.

A question arrivesAnswered from scratch
One question
A document
A past ticket
A colleague
The answer, assembledThree hands later

Where an answer is found today, illustrative. No figure on this page is read off this drawing.

The four handoffs

Four handoffs that make support slower than the work requires.

None of these is a chatbot problem. A conversational surface on top of them makes the same retrieval failure faster and more public.

  1. The same question, answered from scratch

    An agent finds the answer in a document, a past ticket or a colleague, and that retrieval happens again the next time the question arrives.

  2. Tickets that only need routing sit in a queue

    A request that a rule could classify waits behind requests that need judgement, and both get slower.

  3. The answer exists and the agent cannot find it

    Information is spread across a help centre, a wiki, a shared drive and one person who has been there longest.

  4. Resolution needs another system

    The agent knows what to do and has to open two more tools to do it, so the handling time is mostly navigation.

What it costs

The cost is not only handling time.

  1. Response time becomes the product

    For a customer comparing suppliers, how fast you answer is often the only difference they can actually observe before buying.

  2. Senior people absorb the overflow

    Escalation is the release valve, so the most expensive people spend their day on questions that were answered last week.

  3. The knowledge stays in individuals

    When the person who knows leaves, the answer leaves. That is a business risk carried as a staffing convenience.

  4. You cannot tell which questions matter

    Volume is visible, patterns are not, so the product never learns what keeps confusing people.

Before and after

What the workflow looks like afterwards.

The same ticket, followed twice: the route it takes today and the route it takes afterwards. The numbers pair the two where you want to compare them.

The same ticket
Before
  1. Every question is triaged by a person.

  2. Answers are reconstructed per ticket.

  3. Uncertain cases are answered anyway.

  4. Resolution needs several tools.

  5. Nobody knows which questions repeat.

After
  1. Rule-classifiable requests are routed on arrival; people see the ones needing judgement.

  2. Approved answers are retrieved from named sources, with the source shown.

  3. Uncertain cases stop and reach a person with the case context already gathered.

  4. The action happens where the agent already is, within permitted boundaries.

  5. Recurring questions are visible, so the product or the help content can be fixed at source.

The split

What to automate, what to assist, and what to leave with a person.

Support automation fails when the split is drawn by volume instead of by consequence. The question is not how often something is asked. It is what a wrong answer costs.

Automate

  • Automate the answer

    Factual, stable, and answerable from an approved source

    The answer does not change, and showing its source makes it checkable.

Assist

  • Automate the retrieval, a person sends

    Repetitive but account-specific

    The lookup is the work; the judgement about this customer is not.

  • Automate with a confirmation step

    Needs a system action within a clear rule

    Reversible actions can proceed; irreversible ones should pause.

Leave with a person

  • Person, immediately

    Emotionally charged, or the customer is already unhappy

    A correct answer delivered by a machine to an angry customer is still a bad outcome.

  • Person, always

    Anything involving money moving, or a legal commitment

    The cost of being wrong is not proportional to the cost of the question.

  • Leave it, and record that you did

    Rare and complex

    Automating the long tail costs more to maintain than the time it recovers.

The last two rows are where most of the argument happens. A support automation that quietly handles refunds is not a productivity gain, it is an unmanaged liability.

How the work runs

How the work runs, step by step

  1. Read the last few hundred real tickets

    Not a summary. The actual mix, including the ones that went badly, because the exception pattern is the design input.

  2. Agree the approved answer sources

    Which documents are authoritative, who owns them and what happens when they do not cover a question. The third is the part usually missing.

  3. Draw the consequence split

    The table above, filled in against your actual request types, with a named owner for the cases that must stop.

  4. Build the narrow version first

    One request type, end to end, including the stop condition. A narrow system that is trusted beats a broad one that is checked.

  5. Feed the recurring questions back

    Into the help content and the product. The point is fewer questions arriving, not faster answers to the same volume forever.

Evidence

Where this work has been done

Customer-facing answer quality and production controls are the two things this work depends on, and both are in delivered Viithiisys work.

  1. Conscious Chemist, product-question response

    A documented 38% faster product-question response in a customer-facing product experience.

    That is a product surface rather than a support desk.

  2. Fitelo, evaluation and cost controls in production

    An AI product running with evaluation and cost controls rather than shipped and watched.

    The same discipline this page requires before an answer reaches a customer.

  3. Vizitor, in daily multi-site use

    In production at scale: 500+ workplaces across 15+ countries.

Measurement

Deflection rate is the wrong measure, and it is the one every vendor reports.

The usual advice is to measure deflection, the share of contacts resolved without a person. It is the easiest number to produce and it can rise while service gets worse.

  1. Deflection rate

    What it appears to show

    Fewer contacts reaching people

    Read it with

    Repeat-contact rate within 48 hours

    The least deceptive single choice
    How it misleads

    A customer who gave up is counted as deflected. So is one who got a wrong answer and did not realise

  2. First-response time

    What it appears to show

    Faster service

    Read it with

    Time to actual resolution

    How it misleads

    An instant automated reply that answers nothing improves this while resolving nothing

  3. Automation coverage

    What it appears to show

    Breadth of what is handled

    Read it with

    Coverage weighted by volume

    How it misleads

    Coverage of rare questions costs maintenance and recovers little time

  4. CSAT on automated interactions

    What it appears to show

    Customers are satisfied

    Read it with

    Abandonment rate inside the flow

    How it misleads

    Only the people who completed the flow are surveyed. The ones who abandoned are absent

  5. Agent handling time

    What it appears to show

    Efficiency gain

    Read it with

    Volume mix, not just the average

    How it misleads

    Falls if easy cases are removed, even when nothing improved for the customer

The pairing in the last column is the point: each measure is usable beside its counterweight and misleading alone. If only one is reported, make it repeat-contact rate.

Start here

Show us your last two hundred tickets.

That is the fastest way to tell whether this is a support automation problem, a documentation problem or a product problem. All three are common, and only the first is work this page describes.

FAQ

Questions we are actually asked

Pick a topic, or ask us directly. We answer every inbound within one business day.

Still have questions?

Talk to a senior engineer, not a bot.

Talk to us