Fixed quote after a free call

An AI customer support agent for SaaS that stays inside your docs

We build an AI support agent for your app, help center or chat widget that answers how-to questions from your own documentation, asks the follow-up questions engineers always need for a bug report, and hands account, billing, security and anything uncertain to a person with the conversation attached. It says it is automated and offers a human at any time. Projects typically cost $2,500 to $7,500 and take five to eight weeks.

The problem

What an AI helpdesk agent for SaaS should and should not do

A large share of SaaS support is the same how-to questions, answered in docs nobody found. An agent can take those, but generic chatbots guess, invent features and frustrate customers who then ask for a person anyway.

The other half of the value is the hand-off. When a question needs a person, the agent should have already collected the workspace, steps, browser and error message, so the support engineer starts with a complete ticket instead of a back-and-forth.

What we build

What our AI customer support agent includes

Docs-grounded answers

Answers built only from your help center, docs and changelog, with links to the source page.

In-app or help center widget

A chat widget in your product or help center, or the same agent behind Intercom or Zendesk messaging where those tools allow.

Bug report collection

Guided questions for steps, expected and actual result, browser and workspace, written into a complete ticket.

Clear hand-off rules

Billing, account access, security, data deletion and anything the agent is unsure of go to a person with the transcript.

AI disclosure and human option

The agent says it is automated and offers a person at every turn.

Unanswered question review

A weekly list of questions without a good docs answer, so the docs team knows what to write next.

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

    Customer asks

    A user asks in the app, help center or chat.

  2. 02 Automated

    Answer from docs

    The agent retrieves matching docs and answers with a link, or asks a clarifying question.

  3. 03 Automated

    Ticket if needed

    Bugs and requests become complete tickets with the transcript attached.

  4. 04 Team review

    Support takes over

    A support engineer picks up hand-offs and checks a sample of answered conversations.

  5. 05 Account owner or team lead decides

    Account and policy calls

    Refunds, access changes, security and data requests are decided by the owning team.

How it behaves

How the AI support agent behaves

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

What the customer sees

  • A clear note that the agent is automated
  • Short answers with a link to the docs page
  • A person whenever they ask, with no need to repeat themselves

What support sees

  • Complete tickets for bugs and requests
  • Hand-offs with the full transcript
  • A weekly list of questions the docs do not answer

What the automation does

  • Retrieves docs and answers within fixed rules
  • Refuses account, billing and security actions
  • Logs every conversation for review

Edge cases and fallbacks

Question about an unreleased feature
The agent says it cannot discuss the roadmap and offers a person.
Customer reports an outage
Immediate hand-off to support and a link to your status page.
Prompt injection attempt
Rules sit outside user input and the agent has no tools that change data.
Model provider outage
The widget falls back to search over the docs and a contact form.

Architecture

An AI support agent for a SaaS product at a glance.

The setup we usually start from. We adapt it to the phone system and practice software you already use.
Customer App or help center Agent service Rules and memory Language model Claude, Gemini, GPT Docs index Help center, docs Answer with link Or clarifying ask Help desk ticket With transcript Support engineer Hand-offs, review
  • Input
  • Logic and services
  • AI step
  • Data
  • Output
  • People

How it flows

  1. 1 A customer asks a question and is told they are chatting with an automated agent.
  2. 2 The agent service retrieves matching documentation and passes it, with fixed rules, to the model.
  3. 3 How-to questions get an answer with a link; bugs and account questions become complete tickets.
  4. 4 Support engineers pick up hand-offs and review a sample of answered conversations each week.

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 customer support agent for SaaS project plan

Typical time to launch: about 6 weeks, then support

  1. 01

    Discovery

    About 1 week

    Ticket sample, docs coverage, hand-off rules and where the agent should live.

  2. 02

    Docs preparation

    About 1 week

    Fill the biggest gaps, structure the index and agree topics the agent must never answer.

  3. 03

    Build

    About 2 weeks

    Agent service, retrieval, widget, bug collection, hand-off and logging.

  4. 04

    Test

    1 to 2 weeks

    An evaluation set of real, tricky and out-of-scope questions; support signs off.

  5. 05

    Launch

    2 to 3 days

    Soft launch to a share of users or out of hours, then widen.

  6. 06

    Support

    Ongoing

    Weekly review at first, then monthly evaluation runs as the product changes.

What it runs on

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

Claude, Gemini or OpenAI models Laravel, Node or Python agent service Vector search over your docs Zendesk or Intercom API for tickets Your product's authentication for in-app use Evaluation set run on every docs or prompt change

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 docs preparation

    Ticket sample, docs gaps, hand-off rules.

    $500 – $1,200

  • Build

    Agent service, retrieval, widget, bug collection and logging.

    $1,200 – $4,000

  • Integrations

    Help desk, authentication and status page.

    $300 – $1,000

  • Testing and evaluation set

    Real, tricky and out-of-scope questions.

    $300 – $900

  • Launch and training

    Soft launch and support team handover.

    $200 – $400

  • Total project estimate

    $2,500 – $7,500

Optional monthly care after launch is quoted with your proposal. Fixed quote after a free call. Model usage and hosting are billed to your accounts directly. If Intercom Fin or Zendesk AI agents already fit, we help configure them instead.

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; we estimate it from your conversation volume and use caching to keep it down.
  • Hosting: Your own cloud account, or n8n Cloud from about €20 a month for lighter setups.

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: tell users they are talking to AI

Article 50 of the EU AI Act requires AI systems that interact with people to inform them, from 2 August 2026. The agent says so at the start in every market.

Source: artificialintelligenceact.eu

Processor contracts for chat data

Chat transcripts hold personal data of your customers' users, so the model provider and hosting are sub-processors under Article 28 GDPR and belong on your sub-processor list.

Source: gdpr-info.eu

No account changes by chat

The agent never changes billing, access or data on request; those actions need a verified person on your team.

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 customer support agent for SaaS questions, answered.

A chat agent that answers product questions from your documentation, collects details for bug reports and hands everything else to your team. It is narrower and more reliable than a general chatbot.

Not always. If those platforms fit your stack, configuring them is often the fastest route, and we can help. A custom agent makes sense when you need it inside your app, across several tools or with rules those products do not support.

It answers only from retrieved docs, links to the source and says it does not know when nothing matches. We test it on an evaluation set of tricky and out-of-scope questions before launch and after every major change.

Only if you choose, and only read access to what the answer needs, through your own authentication. Many teams start with docs only and add account context later.

Yes. It says so at the start and offers a person at every turn. The EU AI Act requires this from 2 August 2026, and we treat it as good practice everywhere.

Conversations resolved without hand-off, hand-offs with complete details, customer ratings on agent answers and the unanswered-question list shrinking as docs improve.

Free 20-minute call

Want this for your software & saa?

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