AI search for your website that answers from your own articles
We build an AI search bar and reader assistant for your publication that answers questions only from your published articles, links every source it uses, suggests related posts and the newsletter, and logs questions it could not answer as ideas for the editorial calendar. It tells readers it is automated and passes corrections and complaints to an editor. Projects typically cost $2,500 to $7,500 and take five to eight weeks.
The problem
Why readers cannot find answers in your archive
Years of good articles are hard to find through a keyword search box. Readers ask a question, get ten loosely matching posts and leave, even when the answer sits in your archive.
A generic chatbot is worse: it answers from the open web, invents details and puts your name on them. A reader assistant has to stay on your own content, cite it and admit when it does not know.
What we build
What our AI search for websites includes
Archive index
Your published articles indexed with title, date and URL, refreshed when posts are added or updated.
Answers with sources
Short answers drawn only from your articles, each with links to the posts used.
Related reading and newsletter
Related posts and a newsletter sign-up suggested in context.
Clear AI disclosure
The assistant says it is automated and links to how it works.
Gap list for editors
Questions it could not answer collected weekly as story ideas.
Corrections hand-off
Readers reporting an error are routed to the editor with the article link.
Who does what
Automation does the chasing, people make the calls.
-
01
Automated
Reader asks
A reader types a question in the search bar or assistant.
-
02
Automated
Answer from archive
The assistant retrieves matching articles and answers with linked sources.
-
03
Automated
Gaps logged
Unanswered questions are logged for the editorial calendar.
-
04
Editor review
Editor reviews
The editor reviews the gap list and transcripts weekly.
-
05
Editor or publisher decides
Corrections and complaints
Reported errors and complaints are decided by an editor, never by the assistant.
How it behaves
How the reader assistant behaves
What readers see
- A note that the assistant is automated
- Short answers with links to your articles
- Related posts and a newsletter prompt
- A way to report an error to an editor
What editors see
- A weekly gap list of unanswered questions
- Corrections routed with article links
- Transcripts for review
What the automation does
- Keeps the article index current on publish
- Answers only from retrieved articles
- Logs gaps and hands off corrections
Edge cases and fallbacks
- Question outside your coverage
- The assistant says so and suggests the closest articles or none.
- Two articles disagree
- It links the newer one and flags the older one for review.
- Abuse or prompt injection
- The conversation is closed politely and logged.
- AI provider outage
- The search bar falls back to your normal keyword search.
Architecture
An AI reader assistant on your archive at a glance.
- Input
- Logic and services
- Data
- AI step
- Output
- People
How it flows
- 1 A reader asks a question and is told the assistant is automated.
- 2 The service retrieves matching articles from your index and passes them, with fixed rules, to the model.
- 3 The reader gets a short answer with source links, related posts and a newsletter prompt.
- 4 Corrections go to an editor, and unanswered questions become a weekly gap list.
Project planner
How the project runs, phase by phase.
AI search & reader assistant for your archive project plan
Typical time to launch: about 6 weeks, then support
-
01
Discovery
About 1 week
Archive size, CMS, reader questions from search logs and inbox, and what the assistant may answer.
-
02
Index and rules
About 1 week
Article index, refresh on publish, answer rules and disclosure wording.
-
03
Build
About 2 weeks
Search bar or chat widget, retrieval, answers with sources, gap log and hand-off.
-
04
Test
1 to 2 weeks
Real reader questions plus tricky prompts; editors sign off before launch.
-
05
Launch
2 to 3 days
Soft launch on one section, then site-wide.
-
06
Support
Ongoing
Weekly transcript review at first, then monthly tuning.
What it runs on
Real products only, connected through the access each vendor provides. See all integrations
Cost estimate
What it costs, line by line.
-
Discovery and rules
Reader questions, answer rules and disclosure.
$500 – $1,100
-
Build
Index, retrieval, widget, answers and gap log.
$1,300 – $4,100
-
Integrations
CMS, newsletter and alerts.
$300 – $900
-
Testing and evaluation set
Real and tricky questions tested before launch.
$250 – $1,000
-
Launch and training
Soft launch and transcript review.
$150 – $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, vector storage 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; grows with reader traffic, so we estimate it from your search volume before launch.
- Hosting and index: Your server or n8n Cloud from about €20 a month, plus any vector storage 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
Privacy and consent
Rules we design for, with the sources.
EU: tell readers 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. We add the disclosure everywhere.
Source: artificialintelligenceact.euEU and UK: reader questions are personal data
Questions can contain personal details, so logs are minimised and the AI provider works under a processor agreement under GDPR Article 28.
Source: gdpr-info.euAnswers stay on your content
The assistant cites your own articles only, so readers can check the source and the publication keeps editorial responsibility.
Free tools
Try these first, free.
How we deliver
Agile delivery, in 1 to 2 week sprints.
Every sprint
- 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 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 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 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
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
- Input
- Logic and services
- People
- Output
- Data
How it flows
- 1 A free call with the project manager and business analyst to understand the problem and whether it is worth building.
- 2 Discovery and design produce a written specification, data-flow map and a backlog with acceptance criteria.
- 3 The team builds in 1 to 2 week sprints; you review a demo at the end of each and accept or adjust.
- 4 Your team runs user acceptance testing, we launch, then monitor and improve under a support plan.
FAQ
AI search for website questions questions, answered.
It replaces or sits beside a keyword search box and answers a reader's question in plain language, using only your published articles and linking each source.
A search bar returns an answer plus the posts it came from and stops there. A chat assistant allows follow-up questions. We build either, both grounded in your archive.
It is built to answer only from retrieved articles and to say it does not know otherwise. We test it against real and tricky questions before launch and review transcripts after.
It can suggest the newsletter in context, such as when a reader asks about a topic you cover regularly. Sign-ups go through your normal consent flow.
A weekly list of questions readers ask that your archive does not answer, which is a direct source of story ideas.
Questions answered with a source, click-through to articles, newsletter sign-ups from the assistant and gaps turned into new pieces.
Free 20-minute call
Want this for your bloggers & publisher?
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.
More for bloggers & publishers
All servicesPublishing CRM & sponsor pipeline automation
Every sponsor, advertiser and partnership enquiry in one publishing CRM pipeline, with media kit replies, follow-ups, renewal reminders and a monthly view of booked and pending revenue.
From $1,000 · About 4 weeks Details
Editorial calendar & contributor workflow
Ideas, commissions, briefs and deadlines on one editorial calendar that updates itself, with house-style briefs for freelancers, reminders and a Monday summary for the editor.
From $1,000 · About 4 weeks Details
Brand deal tracker, disclosure checks & sponsor reports
Track every brand deal from booked to paid: deliverables on the calendar, disclosure wording checked before publish, sponsor approval reminders, draft reports and draft invoices.
From $1,000 · About 4 to 5 weeks Details