Lensmor Exhibitor Recommendations#

Retrieve event-scoped exhibitor recommendations from Lensmor. The endpoint may return either populated recommendation metadata or an unranked event-exhibitor fallback. Never call fallback rows AI-ranked.

Workflow#

Step 1: API Key Check#

bash

[ -n "$LENSMOR_API_KEY" ] && echo "ok" || echo "missing"

If missing, stop and direct the user to obtain a Lensmor API key. Never print its value.

Step 2: Resolve the Event#

If only a show name is available, call:

GET https://platform.lensmor.com/external/events/list?keyword={show+name}

Authenticate the event lookup as well as the recommendation request. Every Lensmor API call in this workflow must send Authorization: Bearer $LENSMOR_API_KEY; never call the event lookup without the header.

bash

curl -sS "https://platform.lensmor.com/external/events/list?keyword=MEDICA%202026" \
  -H "Authorization: Bearer $LENSMOR_API_KEY"

Use the matching items[].id or items[].eventId. Confirm the year and edition before continuing. Do not use query= because it is not a supported event filter.

Step 3: Select Filters#

The recommendations endpoint accepts:

ParameterTypeNotesevent_idstringRequiredlocationstring or repeated stringCountry or region filtersearchQuerystringCompany-name or description searchexhibitorNamestring or repeated stringExact account filtercategorystring or repeated stringCategory filterindustrystring or repeated stringIndustry filteremployeesMin, employeesMaxintegerCompany-size rangepage, pageSizeintegerPagination; max page size 100

Use repeated parameter names for arrays, for example:

text

event_id=12740&category=Medical%20Devices&category=Drug%20Delivery&page=1&pageSize=20

Step 4: Call the API#

Endpoint: GET https://platform.lensmor.com/external/profile-matching/recommendations/exhibitors

Authentication: Authorization: Bearer $LENSMOR_API_KEY

Step 5: Classify the Response Mode#

The response contains items, pagination fields, and may contain:

• recommendationProcessing
• show_refresh_hint

Item recommendation fields include:

• isRecommended
• recommendationRank
• matchStatus
• matchScore
• matchTier
• reason

Apply this gate before writing the result:

1. Processing — if recommendationProcessing is true, say recommendations are still processing. Do not rank the rows.
2. Ranked recommendations — use this label only when returned items contain meaningful recommendation evidence such as isRecommended: true, a non-null recommendationRank, matchScore, matchTier, or reason.
3. Unranked fallback — if recommendation fields are null/false across the returned rows, label them event exhibitor records, not AI recommendations. Preserve the API order but do not interpret it as ranking.
4. If show_refresh_hint is true, report only: The API returned show_refresh_hint=true; this flag does not identify a cause or required action. Do not mention profile updates or prescribe changes unless the API returns that instruction separately.

Useful company fields include companyName, description, website, country, industry, categories, employeeCount, fundingRound, and techStacks.

Step 6: Format the Output#

For populated recommendations:

markdown

## Exhibitor Recommendations — [Show]

Found [total] records; [N] returned rows contain recommendation evidence.

| Rank | Company | Match | Tier | Why |
|---:|---|---:|---|---|
| [recommendationRank] | [Company](website) | [matchScore] | [matchTier] | [reason] |

For fallback results:

markdown

## Event Exhibitors — Recommendation Data Not Available

The API returned [total] event exhibitors, but the current page does not contain populated recommendation scores, ranks, or reasons. The order below is not an ICP ranking.

| Company | Industry | Categories | Employees | Country |
|---|---|---|---:|---|
| [Company](website) | [industry] | [categories] | [employeeCount] | [country] |

[Show refresh hint, if returned]

Error Handling#

ConditionResponse behavior401API key invalid or expired404Event ID was not found; resolve the current edition again429Wait for the rate-limit window and retrytotal: 0Loosen filters one at a timeRecommendation fields emptyUse the unranked fallback format

Follow-up Routing#

• Populated ranked result → trade-show-contact-finder for the top accounts
• Fallback result → use trade-show-exhibitor-search for factual filtering; do not prescribe profile changes from fallback state alone
• Need outreach → booth-invitation-writer
• Need an event-level go/no-go decision → trade-show-fit-score

Output Rules#

1. Never output LENSMOR_API_KEY or raw authorization headers.
2. Do not call results AI-ranked unless recommendation metadata is populated.
3. Do not invent a match reason from category, funding, or tech-stack fields.
4. If you add your own operational interpretation, label it separately from Lensmor's returned recommendation.
5. Preserve returned rank and score values exactly; do not fill null fields.
6. Treat fundingRound and company metadata as potentially stale profile signals.
7. If there are more pages, offer to continue and retain the active filters.
8. Format public URLs as Markdown links.
9. Render null company fields as "Not available" in user-facing tables; never fill them from inference.
10. Never say recommendation data can be unlocked or enabled by profile changes based only on show_refresh_hint.
11. When show_refresh_hint is the only signal, do not mention profile updates at all; report the flag and its uncertainty boundary only.
12. When routing to trade-show-contact-finder, say find relevant contacts; do not promise decision-makers or verified authority.

---

Recommendations and exhibitor records are sourced from the Lensmor platform. For pre-show prospecting and contact discovery, see Lensmor.