Mine TrustRadius reviews for competitor strengths and weaknesses
Get B2B software reviews from TrustRadius with pros, cons, use cases and feature ratings as JSON, for competitive and product research.
If you build or sell business software, the reviews of your competitors tell you what buyers value, where they get stuck and what made them switch. TrustRadius holds long, structured reviews, but they are spread over many pages. Lovely Router collects them. Send a product link, get one JSON object per review, pay per review from a prepaid balance. Call it from a script, a research notebook or an AI agent.
Hand it to your AI agent
Copy this prompt into Claude Code, Cursor, Codex or any coding agent. It tells the agent where the docs are and how to use your API key.
Mine TrustRadius reviews for competitor strengths and weaknesses. Use the Lovely Router data tools: each returns JSON and is billed per result.
- Docs (read first): https://lovelyrouter.com/docs/tools/find.md and https://lovelyrouter.com/docs/tools/run.md
- Plan first: POST https://lovelyrouter.com/v1/tools/suggest with `{"task": "<my task in plain words>"}` (free). It returns the tools to run in order, each with an example `input`, the `input_required` fields, an estimated cost and a ready-made `run` request. Replace the example values with my task's; if a field is unclear, read the tool with GET https://lovelyrouter.com/v1/tools/<id>. To browse instead, POST https://lovelyrouter.com/v1/tools/discover searches the catalog.
- Show me the plan and its estimated cost (`total_est_cost_usd`) before running anything large.
- Run: POST https://lovelyrouter.com/v1/tools/<id>/run with `{"input": {...}, "max_results": N}`. A 200 has the finished run with `items`; a 202 means it is still running, so poll the `poll` path until `status` is `succeeded`, `failed`, `timed_out` or `stopped`.
- Only delivered results are billed. Keep max_results small on the first run, check the output, then scale up.
- If you support MCP, connect https://lovelyrouter.com/mcp instead (Streamable HTTP, same key; https://lovelyrouter.com/docs/tools/mcp.md) and use suggest_tools, get_tool and run_tool.
- Auth: read my API key from the LOVELY_API_KEY environment variable and send it as `Authorization: Bearer $LOVELY_API_KEY`. Never print or commit the key. If it is not set, ask me to create one at https://lovelyrouter.com/app/keys.
- Billing is prepaid: every call is charged to my balance, so test with a small request before running anything large.
- Every docs page is plain Markdown; the full index is https://lovelyrouter.com/llms.txt.
My task: <the inputs (links, keywords or accounts) and how many results you need>How it works
Pick the products
Find the TrustRadius reviews page of your product and of each competitor you compare.
Run the tool with a cap
Send the product link to
POST /v1/tools/trustradius-reviews/runwithmaxResultsin the input andmax_resultson the request. Sort byrecent,positive,criticalorrelevant.Compare the products
Collect the pros and cons into one table per product, and ask a model to extract the strengths, the complaints and the use cases that repeat.
Get the reviews of a software product with one request
Get TrustRadius reviews takes one product page in productUrl. maxResults caps the reviews, and sort chooses the order:
curl https://lovelyrouter.com/v1/tools/trustradius-reviews/run \
-H "Authorization: Bearer $LOVELY_API_KEY" \
-H "content-type: application/json" \
-d '{
"input": {
"productUrl": "https://www.trustradius.com/products/zendesk-support-suite/reviews",
"maxResults": 5
},
"max_results": 5
}'The tool reads one product per call. To compare several products, start one run per product with the same cap. A run still going after 60 seconds returns 202; Run a tool shows how to poll.
What each review holds
| Field group | What you get |
|---|---|
| Summary | Heading, rating and date |
| Content | Use cases, pros and cons |
| Sentiment | Likelihood to recommend, plus feature ratings |
| Reviewer | The reviewer's details |
starRating and companySize filter the reviews. Leave them empty for everything. The description lists reviewer details without saying exactly which, so check one run before you rely on specific fields.
Recipes
Run sort: critical on a competitor with a cap of 100. Ask a model for the five complaints that come up most, with a quote for each, and hand the sheet to sales.
Read the critical reviews of the leader in your category and note which gaps you can fill.
Run your own product and read the cons. If the same feature gap appears more than five times, put it on the roadmap.
Filter by companySize to see whether small teams and large ones value different things in the same product.
If you are the buyer, read the use cases and cons for each shortlisted product before the demos.
Prefer plain words? Connect the MCP server and tell Claude Code or Cursor: "Read 80 critical TrustRadius reviews for this product link, group the cons by theme, and give me the top five with quotes. Set max_results to 80."
Pair it with other review sites
One review site is one slice of the buyers. Add the others:
B2B software reviews from TrustRadius: heading, rating, date, use cases, pros, cons, likelihood to recommend, feature ratings, reviewer.
G2 reviews of a software product.
Software reviews from Capterra for a product: title, date, overall and sub-ratings, pros, cons, comments, reviewer role and company size.
Enterprise software reviews from Gartner Peer Insights: headline, summary, rating, date, reviewer role, industry and company size.
Trustpilot reviews of a company by domain: stars, text, date, reply.
g2-reviewsadds software reviews from G2.capterra-reviewsadds reviews from Capterra, which skew to smaller buyers.gartner-reviewsadds reviews from Gartner.trustpilot-reviewsshows the customer-service side of the same company.
For a view across many sources, see review monitoring.
What you pay
You pay per review: starting a run holds its maximum cost, the per-call fee plus the per-review fee times max_results, and the run settles to what it returned. The rest of the hold goes back to your balance. A run that fails or times out pays only for the reviews it delivered, and a run refused at the start costs nothing.
Reading 100 reviews is billed as 100 reviews. There is no subscription and no monthly minimum: top up from $5, and one balance pays for tools and models. The card above shows today's price; pricing lists every tool.
Frequently asked questions
Can I compare several products in one run?+
No. The tool takes one product page per run in productUrl. Start one run per product and compare the results yourself.
Can I read only the critical reviews?+
Yes. Set sort to critical. The other values are recent, positive and relevant.
Can I filter by company size or stars?+
Yes. starRating and companySize take lists of values. Leave them empty for all reviews.
How many reviews can one run return?+
maxResults caps the reviews, and the tool's maximum is 500 per run.
Do I need a subscription?+
No. You add credit to a prepaid balance and each run draws it down. Failed runs pay only for the reviews they delivered, and nothing renews automatically.
Looking for more? See the rest of the tool catalog and the pricing page.