Find why buyers leave a competitor in G2 software reviews
Pull G2 reviews of any software product as JSON to see what customers like and complain about, for positioning, battlecards and product roadmaps.
Before you write a battlecard or choose what to build, you need to know what customers of the rival product praise and what makes them look for a replacement. G2 reviews say it in their own words, spread over hundreds of pages. Lovely Router reads them for you. Send G2 product links, get one JSON object per review, pay per review from a prepaid balance. Call it from a script or an AI agent with one API key.
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.
Find why buyers leave a competitor in G2 software reviews. 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
Choose the products
Your product and the three to five competitors. A G2 product link or just the slug works.
Run the tool with a cap
Send them in
productUrlswithmodeset toproduct_reviewsandmaxReviews. The run holds its maximum cost from your balance.Compare themes
Ask a model to tag each review by theme, then count praise and complaints per product.
Get G2 reviews with one request
G2 software reviews has three modes: product_reviews, product_search and category_browse. For reviews, pass product links or slugs in productUrls; maxReviews caps reviews per product:
curl https://lovelyrouter.com/v1/tools/g2-reviews/run \
-H "Authorization: Bearer $LOVELY_API_KEY" \
-H "content-type: application/json" \
-d '{
"input": {
"mode": "product_reviews",
"productUrls": [
"https://www.g2.com/products/slack/reviews"
],
"maxReviews": 10
},
"max_results": 10
}'To find competitors first, use category_browse with a category name in searchQuery, or product_search with a keyword. 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 |
|---|---|
| Review | The G2 review of a software product, as the site lists it |
| Product search | In product_search mode, product metadata for the keyword |
| Category | In category_browse mode, the products in the category |
Run a small test, look at the rows, and then decide which fields feed your analysis.
Recipes
Pull 200 reviews of a rival and ask a model for the five most repeated complaints, each with a quote.
Use category_browse for your category, then read reviews of the top products and list what users ask for that nobody has.
Compare how customers describe you and a rival, and use their words on your site.
Tag the reviews of your own product by feature request and rank them.
Rerun monthly and compare recent reviews against the last run to see whether complaints are growing.
Prefer plain words? Connect the MCP server and tell Claude Code or Cursor: "Read 150 G2 reviews each for slack and microsoft-teams, list the top five complaints for each with one quote, and tell me where we could win. Set max_results to 300."
Pair it with other review sources
One review site is one audience. Add:
G2 reviews of a software product.
Enterprise software reviews from Gartner Peer Insights: headline, summary, rating, date, reviewer role, industry and company size.
Software reviews from Capterra for a product: title, date, overall and sub-ratings, pros, cons, comments, reviewer role and company size.
B2B software reviews from TrustRadius: heading, rating, date, use cases, pros, cons, likelihood to recommend, feature ratings, reviewer.
Trustpilot reviews of a company by domain: stars, text, date, reply.
gartner-reviewsadds enterprise reviews with reviewer role, industry and company size.capterra-reviewscovers a second software marketplace.trustradius-reviewsadds a third B2B source.trustpilot-reviewsreads customer reviews of the company rather than the product.
For the broader workflow, 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 200 reviews a month is billed as 200 reviews a month. 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 find competitors on G2?+
Yes. Use category_browse with a category such as CRM in searchQuery, or product_search with a keyword.
Do I need the full URL?+
No. A full link, a link without the protocol, or a slug such as slack works in productUrls.
How many reviews can I read?+
Set maxReviews per product; a single run returns up to 200 reviews in total with max_results.
Do I need a G2 account?+
No. You send links and an API key.
Do I need a subscription?+
No. You add credit to a prepaid balance and each run draws it down. Nothing renews automatically.
More on the same theme: review monitoring, lead generation and the tool catalog.