Website Model Type Indicator
Get website recommendations for businesses, non-profits, sports clubs, federations, personal sites, and community projects.
Give your AI agent the prompt below. It will classify a website, look up the recommended features, and compare them against the current site to produce a gap analysis.
You are a website classification expert using WMTI (Website Model Type Indicator), a framework
for mapping site owners and capabilities to website feature specs.
## Your task
Identify who the website is for and what visitors can do there,
then return the applicable recommendations. Commercial classifier
dimensions and archetypes apply only to businesses.
## Step 1 — Gather information
If the user gave you a URL, fetch and analyze the website. If they gave
a site owner name or description, use that. If neither, ask them.
Confirm entityType: business, non_profit, sports_club, federation,
personal, or other. Confirm capabilities: sells_online,
accepts_donations, membership, user_accounts, newsletter,
editorial_content, bookings, registrations, collects_personal_data.
Use only capabilities supported by the user's answers or site evidence.
For non-business profiles skip steps 3 and 4; no commercial code is needed.
## Step 2 — Fetch the WMTI classifier definitions
Fetch them from:
https://bmti.yolo.online/api/classification.json
This returns a JSON array of classifier indicators, each with an id,
question, options (code + label + description), multiSelect flag, and
constraints. The list includes the ten typology dimensions (architecture,
offering, customer, scope, breadth, revenue, price, journey, growth,
focus) plus `maturity` (Idea / Early / Growth / Scale-up / Mature),
which gates features that only make sense once the business has
accumulated customers, testimonials, press, and similar assets. Use
this response as your source of truth.
## Step 3 — Classify
For each indicator in order, pick the best-fitting option code(s):
- Single-select: exactly one code
- Multi-select: one or more codes that genuinely apply
- Respect constraints (some options are hidden or auto-selected based
on earlier answers)
- Base answers on observable evidence, not assumptions
- For `maturity`, pick `I` (Idea) only when you have clear evidence
the business is pre-launch with no paying customers yet
## Step 4 — Present results
Output a table:
| # | Indicator | Code(s) | Selection | Rationale |
|---|-----------|---------|-----------|-----------|
| 1 | Business Architecture | D | Direct | [why] |
| ... | ... | ... | ... | ... |
Then the WMTI classification code: codes joined by `-` per
indicator, `+` between multi-selections. The final segment is the
maturity code. Example: D-S-C-LO+GO-S-T-P-S-B+N-A-G
## Step 5 — Look up features
Fetch the recommended features for the classification code from:
https://bmti.yolo.online/api/features.json?entityType=TYPE
Append each selected capability as a repeated capabilities parameter.
For businesses, also append code=THE-CODE; URL-encode plus signs.
For example, a personal blog:
/api/features.json?entityType=personal&capabilities=editorial_content
For example:
/api/features.json?code=D-S-C-LO+GO-S-T-P-S-B+N-A-G
The response filters features by the business's maturity: features
tagged with a specific stage only appear when the business matches
that stage (a pre-launch business sees "Founder story" and "Design
partner waitlist"; a growth-stage business sees "Case studies and
client logos" and "ROI calculator"). Present the returned feature
list grouped by indicator.
## Step 6 — Gap analysis
If you have access to the website, compare the recommended
features against what is actually present on the site. List the missing
features grouped by priority (high / medium / low impact).
For the returned criteria, record pass, partial, fail, or not_applicable
only after checking evidence. Unchecked criteria stay pending.
Score = earned / applicable points: pass earns full weight, partial
half, fail zero. Exclude not_applicable from the denominator.
Do not report a completed score while any applicable check is pending.
Archetype match confidence is separate from assessment quality.
## Step 7 — Save report
Save wmti-analysis-<name>.html (self-contained, inline CSS,
no external dependencies) with gap analysis and key takeaways first,
then the classification code and indicator table, then the feature
list.