Next Project Contacts
A quiet support desk at night, a headset on the table beside a monitor lit with a column of message bubbles.

AI

Chatbots that know when to stop.

Support and sales assistants grounded in your own content, with a clean handoff to a person. Measured on resolution and CSAT, never on deflection alone.

Contacts Technology map

A chatbot that answers confidently and wrongly costs more than no chatbot. The whole design problem is knowing where the assistant’s knowledge ends.

An old patch-panel switchboard on a dark desk with two cables seated and the rest of the sockets empty.

How we approach it

  1. Grounded in your content, not the internet

    The assistant answers from your help centre, your product docs and your past tickets. Every answer carries a link to the passage it came from, so a user can check it and an agent can correct it. Content it has never seen is a handoff, not a guess.

  2. The handoff is the feature

    We build the escalation path first: when confidence drops, when the user asks twice, when the topic is billing or cancellation, the conversation goes to a person with the full transcript attached. Nobody has to repeat themselves.

  3. Sales assistants are a different job

    Support wants resolution. Sales wants qualification. A pre-sales assistant asks the three questions your team would ask, books the call and writes the summary into the CRM. That last part is where the value is, and it is CRM work as much as model work.

  4. What we measure

    • Resolution rate, not deflection rate
    • Satisfaction on assisted conversations against unassisted ones
    • Handoff quality: how often the human has to start over
    • Cost per conversation, tracked from day one

    Deflection alone is a vanity number. It counts people who gave up.

  5. Voice, tone and the brand

    The assistant is a public surface. It gets the same tone rules as the rest of the site, which come out of strategy and branding rather than out of a default system prompt.

  6. Launch and after

    We ship behind a flag, to a slice of traffic, with a kill switch. Then we read the transcripts weekly and fix the top failure. That loop is support and evolution, applied to a feature that changes every time the underlying model does.

    Next: LLM development services, or the whole AI map.

Discuss the next step

Tell us what you want to build or improve. We reply with a plan, an indicative budget and a start date.

Contacts Browse the service map