AI and workflow automation
Plan assistants and connected workflows around the tasks your team actually needs help with. Explore knowledge-based chatbots, voice agents, CRM and WhatsApp automation, content operations and a readiness audit before choosing a build.
So that is how we scope it. A two-week readiness audit lists the tasks worth automating, the ones that are not, and what each would cost to build and to run. Then fixed-scope builds on tools that exist today: Claude and GPT for language work, Gemini where Google Workspace is already the system of record, n8n or Make for orchestration, the WhatsApp Business API or your CRM for the handoff to a person.
Everything ships with evaluation attached. We score answers against a set of real questions from your inbox, watch the escalation rate, and count the hours saved. When the numbers say a workflow should stay manual, that is what the report says.
AI & Automation: what we do
AI search optimisation (GEO)
Review how your website can support AI-assisted search. We examine crawl access, entity information, answer-focused content and citations, then track a defined set of prompts and sources as the work changes.
AI chatbot & knowledge assistant
Help customers find answers from your documents, prices and policies. We build website and WhatsApp assistants with retrieval, approval rules and a clear handoff when a person needs to take over.
AI workflow automation
Reduce repeated handoffs between the systems your team already uses. We map the workflow, build integrations in n8n or Make, add suitable AI steps and agree approvals, error handling and monitoring.
AI voice agents
Plan a voice assistant for the calls your business can support responsibly. We scope knowledge-based answers, calendar and CRM connections, escalation, recording requirements and reviewable transcripts before a pilot.
AI CRM & WhatsApp agents
Connect the CRM and communication steps your team uses. We map enquiries, record updates, follow-ups and meeting bookings, then agree the integrations, approval rules and maintenance needed for the workflow.
AI content operations
Give editors a repeatable way to use AI for research, briefs, drafts, translations and channel variants. We design the workflow, review sources and keep people responsible for accuracy and publication.
AI for ecommerce
Help shoppers find suitable products and give your team better tools for catalogue work. We scope search, recommendations and support assistants around product data, existing integrations, review controls and measurement.
AI readiness audit
Find where AI could help before committing to a build. We map your processes, review the available data and tools, assess risks and prepare a prioritised roadmap with scope and cost assumptions.
AI & Automation, answered
What can an AI assistant actually do for a small business?
It can answer questions from approved business information, collect enquiry details and, where integrations allow, check an order or request an appointment. The first scope should define supported tasks, permissions and the handoff to a person. We do not assume a fixed share of your enquiries can be automated before reviewing them.
Which models and tools do you use?
Claude, GPT and Gemini are options for language work; n8n or Make can connect the steps to your existing systems. The task, required integrations, data handling and evaluation determine the choice. Platform subscriptions, hosting and model usage are scoped separately rather than described as a universal flat API cost.
How much does an AI chatbot or automation cost?
A business assistant starts at USD 2,499/project. A defined workflow or content-workflow setup starts at USD 1,499/project. Voice-agent setup starts at USD 1,999/project. The AI readiness audit starts at USD 999 and is credited against the first build under the proposal terms. Platform subscriptions, hosting and usage are separate.
What happens when the AI gets something wrong?
We define fallback and escalation rules, log the supported interactions and test representative questions before launch. Confidence checks cannot catch every mistake. Staff review failures and customer handoffs so the workflow can be corrected, restricted or kept manual when needed.
Is our data safe?
Data handling is part of the scope: which systems receive which information, who has access, where it is stored, retention and deletion arrangements, and the provider terms that apply. Any confidentiality agreement and controls are confirmed before access. We do not promise that every tool or provider has the same training, hosting or retention policy.
Tell us what is not working in ai & automation.
One reply from the person who would do the work, within a business day, including if we are the wrong fit.