Output Explorer

Every prompt in the paper, and what each model wrote back.

Return exactly ten single-sentence facts as JSON. Quality was judged pairwise; here you see the raw outputs and whether the JSON parsed.

13 of 1,000 prompts

AXL · Q3 20252025-11-07 BLK · Q3 20252025-10-14 HII · Q2 20252025-07-31 HTH · Q3 20252025-10-24 OMC · Q1 20262026-04-28 MKC · Q2 20262026-06-25 EVCM · Q3 20252025-11-06 ITGR · Q1 20262026-04-30 TOMZ · Q2 20252025-08-14 BRLT · Q1 20262026-05-06 SF · Q2 20252025-07-30 ANF · Q3 20252025-11-25 KFS · Q2 20252025-08-07

Nearby prompts. All 1,000 Earnings calls prompts

PromptEVCM· Q3 2025 · call on2025-11-06· transcript 28,054 characters

Analyze the following earnings call transcript and extract the 10 most investor-relevant facts.

Each fact must:
- Be drawn only from the transcript (do not use any outside information).
- Be a single sentence capturing a specific, quantified insight relevant to investors.
- Avoid regurgitating the transcript verbatim; instead, synthesize and distill the information into investor-relevant facts.

Return only a JSON object with this exact structure (no markdown fences, no commentary):
{"facts": ["<fact 1>", "<fact 2>", ..., "<fact 10>"]}

The list must contain exactly 10 facts.

Transcript:
<transcript>
transcript redacted — the source calls are not publicly licensed
</transcript>

System prompt · identical for every setup

You are a financial analyst. You extract the most investor-relevant facts from earnings call transcripts to help investors anticipate the stock's reaction to the call.

Reference

No reference summary is published. Quality was judged pairwise by a separate model and is reported in aggregate on the main page.

Ours

10 facts · valid JSON

EverCommerce generated Q3 2025 revenue of $147.5 million, representing 5.3% year-over-year growth within the previously provided guidance range.
Adjusted EBITDA for the quarter reached $46.5 million, beating the top of guidance and resulting in a 31.5% margin that expanded 140 basis points year-over-year.
Payments revenue grew 6% year-over-year and accounted for approximately 21% of total revenue, contributing incrementally high 95% gross margins to the bottom line.
The company reported annualized total payments volume of approximately $13 billion, reflecting 5.2% year-over-year growth driven by front-book attach rates exceeding 60% in flagship verticals.
EverCommerce acquired the ZyraTalk AI Agentic platform, which has already processed over 2 million chats and voice interaction minutes, to accelerate native AI workflow automation across its service verticals.
On an LTM basis, the company generated $585.1 million in revenue with a 7.6% year-over-year growth rate and a 97% net revenue retention metric.
The company repurchased 2.6 million shares in Q3 for $29.1 million and recently increased its share repurchase authorization by $50 million to a total of $300 million.
LTM adjusted EBITDA guidance was raised to a range of $174.5 million to $179.5 million, while full-year revenue guidance was narrowed to $584 million to $592 million.
Core SaaS revenue grew over 8% in the quarter, outperforming usage-based rebate revenue which faced $1.6 million in headwinds due to macroeconomic and tariff factors.
Leveraged free cash flow for the trailing 12 months totaled more than $111 million, while total debt outstanding at quarter end stood at $528 million with a net leverage ratio of approximately 2.1x.

Aux 2015

10 facts · valid JSON

<fact 1>
<fact 2>
<fact 3>
<fact 4>
<fact 5>
<fact 6>
<fact 7>
<fact 8>
<fact 9>
<fact 10>

PiT-FT 2015

Invalid JSONshown as written

<|assistant|>
<|assistant|>
<|assistant|>

The same 14-character fragment repeats 292 times until the token limit. Showing the first three.

ChronoGPT 2015

Invalid JSONshown as written


### Outcome:

### Final Answer:

####

# Final Answer:

### Question:

**Yes, I would say that, that was probably the one space that we had any particular headwinds in the business in Q3. The reason the larger answer was really focused on that was a part of the thesis, but really kind of a smaller part of the overall thesis for the acquisition.