Fixed quote after a free call

An AI helpdesk for web agency support requests

Care-plan clients email small requests all day: change this text, why is the form not sending, how do I add a blog post. We build an AI helpdesk that reads each request, sorts it into bug, content edit, how-to or new work, answers how-to questions from your own client guides, checks the care-plan allowance and drafts replies and tasks for developers to approve. Projects typically cost $2,500 to $7,000 and take five to seven weeks.

The problem

Why support requests keep interrupting web developers

Support requests interrupt developers in the middle of project work. Each email has to be read, understood, matched to the right client site and care plan, and either fixed, explained or quoted. Many are how-to questions already answered in a guide the client lost.

The commercial risk is the same as in projects: small requests that are really new work get done for free because nobody checks them against the care plan. An assistant that sorts and drafts, while a person decides, protects both response times and margin.

What we build

What our AI helpdesk for web agencies includes

Request intake

Support emails, portal forms and chat messages turned into tickets matched to the client and site.

Sorting

Each request classified as bug, content edit, how-to question or new work, with urgency.

How-to answers from your guides

Drafted answers from your client guides and videos, with links, for the developer to send.

Care-plan check

Requests compared with the client's plan allowance and inclusions, with new work flagged for a quote.

Developer-ready tasks

Bugs and edits created as tasks with the URL, screenshot and site details.

AI disclosure and escalation

If any reply is sent automatically, it says so; urgent outages go straight to the on-call developer.

Who does what

Automation does the chasing, people make the calls.

Every step is marked: what runs on its own, what a member of staff reviews and what stays with a person who decides.
  1. 01 Automated

    Request arrives

    An email, form or chat creates a ticket matched to the client site.

  2. 02 Automated

    Sorted and checked

    The request is classified and checked against the care plan.

  3. 03 Automated

    Draft and task

    A reply is drafted and a task created where work is needed.

  4. 04 Project manager review

    Developer approves

    A developer edits and sends the reply and picks up the task.

  5. 05 Project lead or agency owner decides

    Quotes and outages

    New work is quoted by the owner, and outages are handled by the on-call developer.

How it behaves

How the AI helpdesk behaves

What each person sees and what runs in the background, including what happens when something goes wrong.

What the client sees

  • A faster, clear reply to each request
  • Links to the right guide for how-to questions
  • A quote before new work starts

What developers see

  • Requests sorted with drafts ready
  • Tasks with URL, screenshot and site details
  • Fewer interruptions for simple questions

What the automation does

  • Matches requests to client and plan
  • Classifies and drafts from guides
  • Flags new work and escalates outages

Edge cases and fallbacks

Client reports the site is down
Escalated to on-call immediately, with an uptime check attached.
Request from an unknown sender
Held for a person to match to a client.
Care-plan hours used up
Flagged so the project lead can talk to the client before work starts.
AI provider outage
Tickets flow into the help desk unsorted and the team handles them as before.

Architecture

An AI helpdesk for a web agency at a glance.

The setup we usually start from. We adapt it to the phone system and practice software you already use.
Client request Email, form, chat Helpdesk service Match to site Language model Sort and draft Client guides Approved how-tos Care plans Allowance, scope Ticket and task With draft reply Developer Approves and fixes
  • Input
  • Logic and services
  • AI step
  • Data
  • Output
  • People

How it flows

  1. 1 A client request arrives and is matched to the client, site and care plan.
  2. 2 The model sorts the request and drafts a reply from your client guides.
  3. 3 The care-plan check flags new work, and a ticket with task and draft is created.
  4. 4 A developer approves the reply and does the work; the owner quotes new work.

Project planner

How the project runs, phase by phase.

Typical durations for a first version. Your proposal lists the exact phases, dates and what you sign off at each step.

AI helpdesk for client support requests project plan

Typical time to launch: about 5 weeks, then support

  1. 01

    Discovery

    About 1 week

    Request samples, care-plan terms, client guides, help desk and escalation rules.

  2. 02

    Guides and rules

    About 1 week

    Organise how-to guides, define categories and what is never answered automatically.

  3. 03

    Build

    About 2 weeks

    Intake, matching, classification, drafts, care-plan check and task creation.

  4. 04

    Test

    About 1 week

    Replay past requests and compare with how the team handled them.

  5. 05

    Launch

    2 to 3 days

    Switch on with developers approving every reply.

  6. 06

    Support

    Ongoing

    Guide updates, new categories and monthly accuracy review.

What it runs on

Real products only, connected through the access each vendor provides. See all integrations

Claude, Gemini or OpenAI models Laravel or n8n helpdesk service Help Scout or Freshdesk API Asana, ClickUp or Jira API Vector search over client guides Slack for on-call escalation

Cost estimate

What it costs, line by line.

Estimates to plan with. Your fixed quote follows a free call, once we have seen your systems and volumes.
  • Discovery and guides

    Request samples, care plans, guides and rules.

    $600 – $1,300

  • Build

    Intake, classification, drafts, care-plan check and tasks.

    $1,100 – $3,500

  • Integrations

    Help desk, task tool and Slack.

    $300 – $1,000

  • Testing and evaluation set

    Past requests replayed and compared.

    $300 – $800

  • Launch and training

    Live start and developer handover.

    $200 – $400

  • Total project estimate

    $2,500 – $7,000

Optional monthly care after launch is quoted with your proposal. Fixed quote after a free call. Help desk seats, AI usage and hosting are billed to your accounts directly.

Monthly running costs you pay directly

Estimates from the vendors' published pricing, checked November 2026. Billed to you by each vendor, never marked up.

  • AI model usage: Billed by the provider per use; scales with request volume and stays small for most agencies.
  • Help desk: Your Help Scout, Freshdesk or chosen desk plan.

What pushes cost up

  • Systems without an API, or with integration access that must be requested from the vendor
  • Writing data back into your core system rather than only reading from it
  • Several locations, brands or very different processes to support
  • Custom apps, dashboards or a voice line on top of the workflows

What keeps cost down

  • One location and one clear process to start with
  • Cloud software with a documented API
  • Using tools you already pay for instead of adding new ones
  • Approved wording and sample data ready at the start
Get a fixed quote

Privacy and consent

Rules we design for, with the sources.

General information to plan with, not legal advice. Your counsel or data protection adviser confirms what applies to your practice.

EU: AI disclosure

If replies are ever sent without a developer, Article 50 of the EU AI Act requires informing people they are interacting with an AI system from 2 August 2026. Our default keeps a person on every reply.

Source: artificialintelligenceact.eu

Support data and processors

Requests often include client customer data and screenshots; help desk and AI vendors need Article 28 processor terms.

Source: gdpr-info.eu

No credential handling by the assistant

If a client sends a password, the assistant asks them to use the password manager route and flags the ticket.

How we deliver

Agile delivery, in 1 to 2 week sprints.

We deliver in short Agile sprints using Scrum, so you see working software every one or two weeks instead of waiting for a big reveal at the end.

Every sprint

  1. 1 Sprint planning. At the start of each sprint we agree which backlog items we will finish, each with written acceptance criteria you can check.
  2. 2 Daily stand-up. A short internal check-in on progress and blockers. You get a written update in your Slack or Teams channel, not another meeting.
  3. 3 Sprint review and demo. At the end of each sprint we demo what was built on test data or in a shadow run, and you accept it or ask for changes.
  4. 4 Retrospective. The team looks at what went well and what to change in the next sprint, and we share anything that affects you.

How scope stays under control

Product backlog
Every feature, fix and question in one prioritised list you can see at any time.
Acceptance criteria
Plain-language conditions for "done" on each item, agreed before work starts.
Change requests
New ideas go into the backlog with an estimate. Nothing changes scope or price without your written approval.
User acceptance testing (UAT)
Before launch your team tests the real workflow against the acceptance criteria and signs off.

Tools we use

Jira, ClickUp or Trello for the backlogSlack or Microsoft Teams for updatesGitHub for code and version historyLoom or a live call for demos

Project manager / Scrum master

Runs the sprints, keeps the backlog and timeline honest, and is your single point of contact.

Business analyst

Maps how the work runs today, writes the workflow specification and acceptance criteria with your team.

Automation engineer

Builds the n8n workflows, integrations, AI steps and error handling.

Backend developer

Writes custom code where a no-code step is not enough: APIs, data sync, secure storage.

Frontend / mobile developer

Builds forms, booking pages, dashboards, web apps or Android apps when the project needs them.

QA engineer

Tests every workflow against the acceptance criteria, including edge cases and failure paths.

DevOps engineer

Sets up hosting, access, backups, monitoring and alerts, and the deployment pipeline.

Who does what at each phase

Free call
Project manager, business analyst
Understand the problem, check it is worth automating and outline a rough range.
Discovery
Business analyst, automation engineer
Map the current process, systems and data, and agree success measures.
Design
Business analyst, automation engineer, backend developer
Write the workflow specification, data flows, compliance notes and backlog with acceptance criteria.
Sprints
Automation engineer, developers, QA
Build, test and demo in 1 to 2 week sprints; you accept or adjust after each demo.
UAT and launch
QA, DevOps, project manager
Your team tests and signs off, we switch on, monitor closely and train the team.
Support
Automation engineer, DevOps
Stabilisation window, then optional monthly care with monitoring and changes.

A point of contact

One person who can answer questions and approve decisions, with about an hour a week during the project.

Access

Admin or API access to the systems involved, created as separate accounts with the least access needed.

Sample data

Real but non-sensitive records (or de-identified ones) so we can design and test against reality.

Approved wording

Message templates, policies and consent wording (for SMS, your opt-in and opt-out text) reviewed by you.

Vendor agreements

Signed agreements with the software vendors that will handle personal data, such as a BAA or processor contract.

Time for testing

A few hours from the people who will use the system, for the demos and user acceptance testing.

Working system

Workflows, integrations and any apps running in your accounts, under your keys.

Documentation

Workflow specification, data-flow map, run book and exported workflow files.

Training

A walkthrough for the team and a short recorded video for new starters.

Handover

All access, credentials and code handed over; you can keep us or take it in-house.

Stabilisation window

Fixes for anything that does not meet the agreed acceptance criteria after launch.

Support options after launch

  • No plan

    You run it yourselves after the stabilisation window and contact us when you need a change.

  • Monthly care

    Monitoring, error alerts, small changes and updates each month, with an agreed response time.

  • Priority care

    Faster response times for business-critical workflows and a monthly review call.

How a project moves through our team

Free call PM and analyst Discovery Process and data Design Spec and backlog Sprints Build, test, demo Your review Accept or adjust UAT and launch Sign-off, go live Support Monitor and improve
  • Input
  • Logic and services
  • People
  • Output
  • Data

How it flows

  1. 1 A free call with the project manager and business analyst to understand the problem and whether it is worth building.
  2. 2 Discovery and design produce a written specification, data-flow map and a backlog with acceptance criteria.
  3. 3 The team builds in 1 to 2 week sprints; you review a demo at the end of each and accept or adjust.
  4. 4 Your team runs user acceptance testing, we launch, then monitor and improve under a support plan.

FAQ

AI helpdesk for client support requests questions, answered.

An assistant that reads support requests, sorts them, drafts answers and creates tasks inside your help desk, so your team responds faster and spends less time on triage. People still approve replies and do the work.

By default no; a developer approves every reply. Once you trust it, you can let it send how-to answers from approved guides, with AI disclosure.

It helps. We connect to Help Scout, Freshdesk or your existing desk, or set up a simple one if requests currently live in email.

We load each plan's inclusions and hours, and the assistant checks requests against them. It flags new work; the owner decides whether to quote.

Yes. The models handle most languages, and drafts come back in the client's language for the developer to check.

First response time, requests sorted correctly, how-to answers sent from guides, new work flagged and quoted, and developer interruptions per day.

Free 20-minute call

Want this for your web developer?

Book a free 20-minute call. We will look at how the work runs today, tell you honestly whether it is worth building and give you a fixed quote if it is.

Book a free 20-minute call