Automation

AI Automation Services in Nepal

AI automation services are worth paying for when a model does a job inside a workflow you already run: reading an enquiry and deciding who handles it, pulling fields out of a PDF, drafting the first reply, summarizing a call. I build those, with the approval steps and logging that keep them safe. This is the parent page for AI work under marketing and business automation services.

  • Internal AI-assisted ops tools built for an agency in Kathmandu
  • n8n, Make, Apps Script plus model APIs
  • Human approval by default

Who this is for

Businesses with a repeated task that needs judgement but not much of it: sorting 200 enquiries a week by service and urgency, turning supplier invoices into sheet rows, answering the same 30 customer questions, writing first drafts of proposals from a call transcript. If a competent new hire could do the task after a one-page instruction, a model can usually do it with the same instruction and a person checking the output. If the task needs relationships, negotiation or accountability, it stays with people.

This page is the overview. Specific builds have their own pages: AI chatbot development for website and WhatsApp bots, AI agents for business for multi-step agents, custom GPT and AI assistant development for team assistants on your documents, and AI consulting and tool setup for choosing and rolling out tools. Ranking in AI answers is a different job and lives under AI search optimization.

What I automate with AI

TaskWhat the model doesWhat stays with a person
Enquiry triageReads the form, email or WhatsApp message; tags service, urgency, language and location; routes to the right person; drafts a replySends the reply, or edits it first
Data extractionPulls names, amounts, dates and line items from PDFs, invoices, CVs and screenshots into a sheet or CRMApproves rows flagged as low confidence
SummariesTurns call recordings, meeting notes and long email threads into a summary with actionsConfirms actions and owners
DraftingWrites first drafts of proposals, quotes, job descriptions, captions and ad variants from a template and the recordEdits and sends
Classification and QAChecks content against a brand or compliance checklist; scores leads; flags reviews that need a responseHandles the flagged items
Customer answersAnswers questions from your own documents on the website or WhatsApp, and hands off when unsureTakes the hand-off

What an AI automation engagement includes

  • Task selection: a short review of your repeated work to pick the one or two tasks where AI pays back fastest.
  • Prompt and instruction design written from your real examples, with a test set of past cases to measure accuracy before launch.
  • Workflow build in n8n, Make or Apps Script connecting the model to your forms, inbox, CRM, sheets and messaging.
  • Guardrails: confidence thresholds, an approval step, a “do not answer” list, and logging of every input and output.
  • Model and provider choice based on cost, language quality in Nepali and English, and where the data may be stored.
  • Cost estimate per month from expected volume, so there are no surprise API bills.
  • Usage policy for the team: what may be sent to the model, what may not, and who reviews.
  • Documentation, training and an optional monthly review of accuracy and cost.

How I build an AI workflow

  1. Collect 50 to 100 real examples of the task with the correct outcome. Without them there is nothing to test against, and I will not ship a workflow that has only been tried on made-up data.
  2. Write the instruction the way you would brief a new employee, then test it on the examples and record the error rate.
  3. Decide the threshold. Above a confidence level the workflow acts; below it, a person decides. Early on the threshold is high and almost everything is reviewed.
  4. Build the workflow around the model call: trigger, data gathering, model step, checks, action, log, alert.
  5. Run in shadow mode for one to two weeks: the model produces output, a person still does the task, and we compare.
  6. Go live with review and lower the review rate only as the measured accuracy justifies it.

What to decide before automating with AI

  • Data. Which customer data may leave your systems and reach a model provider, and whether that is acceptable for your industry, especially healthcare and finance.
  • Accountability. Who is responsible when the model is wrong. The workflow must make that person’s review easy, not hide the output.
  • Language. Nepali quality varies by model; I test with your actual Nepali and romanized Nepali messages before choosing.
  • Cost ceiling. A monthly API budget and an alert when it is approached.
  • What not to automate. Complaints, medical advice, legal commitments and pricing exceptions are routed to people by rule, not by model judgement.

What breaks, and how I prevent it

  • Confident wrong answers: the “do not answer” list, retrieval from your own documents only, and a hand-off when the question is outside them.
  • Drift after a model update: the test set is re-run on every provider change and the workflow is pinned to a model version.
  • Runaway cost from loops or long inputs: token limits, retries capped, daily spend alerts.
  • Prompt injection from customer messages: instructions and data are separated, and the model cannot trigger actions the workflow does not expose.
  • Silent failures: every run logged, every error alerted.

Proof

I use AI steps in my own reporting, lead triage and content workflows, and I have built AI-assisted operations and task tools for an agency in Kathmandu and for a Nepali financial-services company’s tool rollout. Screenshots and a walkthrough are available on a call.

Pricing pointer

Setup is quoted on request; a single AI workflow with one model step and an approval queue sits in the middle of the range because of the testing involved, and an agent that reads several systems and takes actions sits at the top. Maintenance and accuracy reviews are quoted on request, and model API usage is billed to your own account. For the general non-AI version of these builds, see workflow automation; for sheet-heavy work, document and data automation.

Next step

Bring one task and twenty real examples of it to a call and I will tell you whether a model can do it, at what accuracy, and what it would cost per month. The rest of the automation services are on the automation hub.

Frequently asked questions

What is the difference between AI automation and regular workflow automation?

Regular automation follows fixed rules: if the form says 'dental', send to the dental team. AI automation lets a model make the judgement from unstructured input: a WhatsApp message in mixed Nepali and English saying 'my tooth hurts and I am in Pokhara'. I use rules wherever they work and a model only where judgement is needed, because rules are cheaper and never hallucinate.

Is my customer data safe with AI tools?

It depends on the provider and settings. I use providers whose business terms exclude training on your data, minimize what is sent (for example, no ID numbers), and write a usage policy for your team. For regulated data I can route to providers with the required data-handling terms or keep the step out of the workflow.

How accurate is AI automation?

It is measured, not promised. Every workflow is tested on a set of real past cases before launch, and the accuracy figure decides how much output a person reviews. Typical first-pass accuracy on well-defined triage or extraction tasks is high enough to save most of the manual time; anything below the threshold is reviewed.

Does it work in Nepali?

Current models handle Devanagari Nepali and romanized Nepali reasonably for classification, extraction and summaries, and less consistently for polished customer-facing writing. I test with your actual messages and choose the model accordingly, and Nepali replies usually go through an approval step at first.

How much does AI automation cost per month?

Two parts: my maintenance fee, quoted on request, and the model API usage billed to you. API cost depends on volume; a few thousand short enquiries a month typically costs a small fraction of the staff time saved. I estimate it before build and set a spend alert.

Can you train a model on our data?

Usually you do not need to. Most business tasks work with a well-written instruction plus retrieval from your own documents, which is cheaper and easier to update than fine-tuning. Where a team assistant on your SOPs and pricing is the goal, that is the custom AI assistant service.

Ready to talk about your project?

A free 30-minute call, a straight answer about what would move the numbers, and a written proposal within 48 hours if we are a fit.