What it solves
Most chatbots either recite a script or make things up. We build assistants grounded in your documents, policies and live systems — they answer with sources, take actions through your tools (book, quote, update, order) and escalate cleanly to a person with the full conversation attached.
Typical problems
- The same 20 questions answered by email every day
- Leads arriving at night with nobody to reply
- A chatbot that cannot check an order or make a booking
- Answers that sound confident and are wrong
- Support that speaks one language when customers speak three
Example workflows
Three workflows we build regularly in this service. Names and numbers are illustrative of typical outcomes; measured results are published only in case studies.
Website assistant that books
Visitors ask about availability and pricing in the chat widget; a person replies the next morning.
The assistant answers from your pricing and policies, checks live availability, books the slot and sends the confirmation — or hands over to a person with the transcript.
Typical result: bookings taken around the clock; fewer abandoned enquiries.
WhatsApp order and delivery status
Customers message to ask where their order is; staff look it up and reply by hand.
The assistant identifies the customer, reads the order system and replies with status and tracking; changes go to a person for approval.
Typical result: status questions resolved in seconds without staff.
Internal policy assistant
Staff ask managers the same HR and process questions every week.
An assistant in Slack or Teams answers from the handbook with the source paragraph and flags outdated documents.
Typical result: managers freed from repeat questions; policy gaps surfaced.
Capabilities
- Website, WhatsApp, Messenger, Slack and email assistants
- Retrieval from your docs, FAQs, policies and product data
- Actions: bookings, quotes, order status, CRM updates
- Multilingual replies
- Escalation to a human with transcript and summary
- Analytics: questions asked, gaps in your knowledge, resolution rate
What every build includes
The difference between an automation that works in a demo and one that still works in a year.
- Automatic retries when a connected app is briefly unavailable, so nothing is silently lost
- A run log for every execution — what came in, what was decided, what went out
- Failure alerts to Slack or email after repeated errors, with a pause switch you control
- Idempotent steps: running twice never creates duplicates
- Written handover: a one-page map of the workflow, its owners and how to change it
- Built in your own accounts — you keep every credential, licence and asset
How the work is delivered
Map
Current process documented with the people who run it.
Scope
Written proposal, diagram, deliverables, fixed price.
Build
Short stages in your accounts, demo at the end of each.
Launch
Monitoring, alerts and documentation before go-live.
Pricing and engagement
We review the questions you answer most, the channels people use and the actions the assistant should be able to take, and show a grounded prototype on your own content.
Scoped in writing after the audit. One price, one outcome, no hourly surprises. Half on start, half on launch.
Monitoring, fixes when an app changes its API, and a monthly improvement sprint. Cancel any month.
Deliverables
- Assistant live on your channels
- Knowledge base structure you can maintain
- Test conversations and guardrail rules
- Monthly report of questions and gaps
Questions
Will it make things up?
It answers only from your content and live systems, cites the source, and says when it does not know — then hands over to a person. We test it against a list of trick questions before launch.
Can it actually do things, not just answer?
Yes. Bookings, quotes, order status, CRM updates and ticket creation through your tools, with a confirmation step for anything that costs money.
Which platforms?
Website widget, WhatsApp Business API, Messenger, Instagram, Slack, Teams and email. One assistant, many channels.
How do we keep it up to date?
The knowledge base is your documents — update a policy and the assistant updates with it. The monthly report shows what people asked that it could not answer.
How does pricing work?
Every engagement starts with a free audit. You then get a fixed-scope proposal with one price and a delivery date, in USD. Ongoing monitoring and improvements are a monthly retainer you can cancel any month.
How quickly can something be live?
A first workflow is usually live within one to three weeks of sign-off. Larger builds are staged so something useful ships early and the rest follows in sprints.
What happens when a workflow fails?
Every build ships with retries, a run log and alerts. If an app changes its API, the retainer covers the fix; without a retainer we quote a small fix and turn it around quickly.
Who owns the automations afterwards?
You do. Everything is built in your accounts and documented, and your team is walked through it at handover. You can maintain it yourself or keep us on retainer.