Chat and AI that does a job, not a demo.

Is your team still answering the same questions and retyping the same documents by hand? We build AI that takes that work off them, using your own documents and rules. We test it on your real questions before anyone sees it, and it hands over to a person when it should. Most take 4 to 14 weeks.

UnflowAI flow comparing a contract against a legal playbook

Every one of these knows when to stop talking and fetch a person. That’s the part most skip.

Knowledge-base chat

Answers from your documents, with the source cited. Hands over to a person when confidence is low or the customer asks. Logs every conversation.

On your website, portal or app
Lead capture and qualification

A conversation on the website that ends in a booked call or a dealer appointment, not a form. Qualifies by your rules, writes to your CRM.

Writes to your CRM and calendar
Document processing

Invoices, contracts, claims, applications read, fields extracted, checked against your rules, routed. A human reviews the ones it’s unsure about.

With a review queue and accuracy targets
Internal assistants

Search and answers across the wiki, the CRM, the drive and the ticket system, respecting who is allowed to see what. Drafts that start from your data.

With Google or Microsoft sign-in
AI inside your product

Summaries, suggestions, classification and drafting as features of the application you already have, with the same login and the same audit trail.

Added to an app you already have
Not sure it’s ready for customers? The demo took an afternoon. The product took the test set, the guardrails and the handover. That’s what we quote.

Product Discovery lists the questions it must answer, the ones it must refuse, and what happens when it doesn’t know. The fee comes off a build that starts within 30 days of the workshop.

See Product Discovery

Switch on the vendor’s AI when it knows your data. Build when it has to know your rules.

If your help desk’s own AI will do, we’ll tell you, and save you the build.

The vendor’s AI add-on

Choose it when your help desk, CRM or CMS ships an assistant, your content is all in that one system, and standard behavior is fine.

Watch for: It can’t see the other systems, can’t follow your handover rules, and you can’t test what it will say before a customer does.

No-code bot builder

Choose it when a single FAQ, a small audience, no integration, and you accept that nobody will know when it starts answering wrongly.

Watch for: Per-conversation pricing, a rules editor that can’t express your policy, and no test set.

Build with Studio

Choose it when it speaks to customers or handles money, it needs two or more systems, Legal wants to know what it will say, and someone will be accountable for it.

What you get: A price agreed before we start, a test set Legal can read, a handover that works, and code in your repositories with the model as a setting.

Not sure which column you’re in? Answer a few questions about how you work, and we’ll tell you which way we’d go. Take the build-or-buy check

Your documents answering questions in week two. Legal reading the test set by week six.

An example 12-week build: a chat assistant connected to your CRM, with a reviewed pilot.

  1. Week 0 Product Discovery

    The questions it must answer, the ones it must refuse, the handover rules, the sources. A first test set drafted with your team. You get a price we’ll hold and a sprint plan.

  2. Weeks 1 to 2 · Sprint 1 Foundations

    Accounts in your name: cloud, model provider, repositories. Your documents indexed with permissions, the rules it follows, the automated test run. Demo one: fifty real questions answered with citations, scored.

  3. Weeks 3 to 8 · Sprints 2 to 4 Behavior and integration

    Handover to a person, guardrails for topic and tone, the CRM or ticket system connected, the widget or panel branded. The test set grows each sprint and runs on every change.

  4. Weeks 9 to 10 · Sprint 5 Pilot with review

    Live for one segment of users or one team, with every conversation sampled in the review queue. Spend per conversation tracked. Legal and support read the transcripts.

  5. Weeks 11 to 12 · Sprint 6 Launch and handover

    Pilot findings fixed, the remaining audience switched on, the review cadence agreed. Documentation, security review with IT, every credential handed over.

Want to know what your plan would look like? We’ll sketch it with you. Book a 15-minute call

Five parts. The second is where your rules live.

By the end of sprint one, your documents are answering real questions. The AI model is a setting you can change, so you’re never tied to one provider.

Forwarding this to your IT lead? Send them the one-page security summary

Chat widget, in-app panel, Slack or Teams

Interface

What people talk to. A widget on your site or portal, a panel inside your application, or a bot in Slack and Teams. Branded, accessible, with the handover button always visible.

What we’d turn down.

A studio that builds everything isn’t telling you the truth about something.

  • A chatbot without a handover If there’s no person to hand over to, the assistant will eventually be alone with an angry customer. We won’t build that.
  • Fine-tuning for its own sake Almost every request for a “custom model” is solved by having it search your documents, for much less. We’ll show you the test set before recommending anything else.
  • Anything customer-facing without a test set If Legal or support can’t read what it will say before launch, it’s a demo. We ship products.
If yours is one of these, ask us anyway. We’ll tell you who does it well. Ask on a 15-minute call

Questions buyers ask first.

Which model do you use?

Whichever scores best on your test set within a budget you set, called through your own account. Usually Claude or OpenAI, sometimes an open model for simple or sensitive tasks. It’s a setting; we re-test when a new one arrives.

Is our data used to train anything?

No. Calls go through your own provider account under its business terms, which exclude training. Documents and transcripts stay in your own database.

What about hallucinations?

Answers are grounded in your documents and cite them. When the search finds nothing relevant, the assistant says so and offers a person. The test set measures this on every change, and the review queue catches what the tests miss.

What’s the spend per conversation?

It depends on the model and the conversation, and you’ll see it on a dashboard from sprint one. We route simple questions to cheaper models and prove on the test set that quality holds.

Which languages?

The models handle most major languages well. We add test questions in each language you serve so the scores cover them.

Can it actually do things, like book or refund?

Yes, through tools with explicit permissions and limits agreed in Product Discovery. Anything that moves money or commits you is confirmed by the user or reviewed by a person.