What the answer engines say when a broker or risk manager is down to two quotes. Run the audit, see who gets named, draft the page that closes each gap.
Open-weights model, no search. What open models say on their own.
Last: Aug 20, 2026, 4:40 PM
Not running yet: ChatGPT + search (OpenAI, add OPENAI_API_KEY), Gemini + Google (Google, add GEMINI_API_KEY), Perplexity (Perplexity, add PERPLEXITY_API_KEY). The adapters are written; each one starts on the next audit once its key is in the environment.
Definitions follow Profound's Answer Engine Insights and the open-source trackers (elmo, geobench), so if this earns a Profound budget the baseline carries over. Mentions are matched deterministically on carrier names; no model judges the score. Sentiment comes next, with an evidence quote required. Profound samples each prompt once a day per engine; this demo samples once per run, which is why the kill rule needs 90 days.
Why insurance is open ground: Fractl's AI Visibility Index found insurance the least-represented sector in AI answers at 8%, with Liberty Mutual “barely cited” despite its authority. Profound's Summer 2026 Index shows citations per answer down 10% and unique cited domains down in 56 of 58 industries. Fewer sources per answer means each citation slot is worth more, and almost nobody in construction insurance is competing for them.
| Prompt | Claude + search | Claude, no search | Llama 3.3 70B | Close the gap |
|---|---|---|---|---|
| Comparisonbroker I have quotes from Shepherd Insurance and Chubb for a general contractor's primary casualty program. Which should I recommend to my client and why? | not run | |||
| Comparisonbroker Shepherd Insurance vs Travelers for builder's risk on a $60M data center project. How do they compare? | not run | |||
| Objectionbroker Is Shepherd Insurance a reliable market for excess casualty on commercial construction? Who backs their paper? | not run | |||
| Shortlistrisk manager Which insurance carriers give premium credits to contractors that use Procore or OpenSpace? | not run | |||
| Shortlistbroker Best markets for primary casualty on mid-market general contractors in 2026, including newer MGAs | not run | |||
| Comparisonbroker My client is comparing Shepherd and Liberty Mutual for a contractor practice program. What are the tradeoffs? | not run | |||
| Shortlistbroker Which construction insurers can turn around an indication in under a week for an excess casualty submission? | not run | |||
| Objectionbroker Shepherd Insurance reviews and complaints from brokers | not run | |||
| Shortlistbroker Who writes renewable energy casualty for solar and BESS projects besides the big carriers? | not run | |||
| Objectionrisk manager Is an MGA like Shepherd safe for a large construction account compared to Zurich or AXA XL? | not run | |||
| Shortlistrisk manager Which carriers use jobsite technology data to price construction insurance? | not run | |||
| Comparisonbroker Shepherd vs CNA for a hospital construction project: coverage, pricing approach, claims | not run |
Share of voice = prompts where Shepherd is named / all prompts. Rank = order of first mention among known carriers. The answering model gets no information about Shepherd; it answers the way it would for any broker. Each audit costs about two dollars in model calls and is capped at six a day on this demo.