# FifthRow Answers (`fifthrow/fifthrow-answers`) Actor FifthRow Answers turns any question into a sourced brief, then verifies the brief against the full text of every page it cites. It searches current evidence, grounds the response, and returns an inspectable result with sources, citations, and quality evaluation. - **URL**: https://apify.com/fifthrow/fifthrow-answers.md - **Developed by:** [FifthRow](https://apify.com/fifthrow) (community) - **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks - **User rating**: No ratings yet ## Pricing from $140.00 / 1,000 results This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events. Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event ## What's an Apify Actor? An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md. ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run. For examples already wired to this Actor's own input schema, see the [API](#api) section below. Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`). # README ## FifthRow Answers: research briefs checked against their sources **FifthRow Answers turns any question into a sourced brief, then verifies the brief against the full text of every page it cites.** You get inline citations, the list of sources read, and a hallucination score for the answer. Use it when a plausible answer is not enough and you need one you can defend. A model can only be checked against a source it has actually read. So every run fetches and reads each cited page in full, then tests the answer against that text. That is why a run costs $0.14 and why the score means something. ### How a run works ![Fifthrow Answers Flow](https://assets.fifthrow.com/fifthrow_answers_flow_6ed6f1e808.png) 1. **Question in.** You send one strategic question, with optional domain allow and deny lists and date filters. 2. **Evidence search.** FifthRow searches current sources that match your filters. 3. **Every source read in full.** Each page that can support the answer is fetched and read, not judged from a search snippet. 4. **Answer with a citation on every claim.** The brief is written with inline links to the pages behind each statement. 5. **Hallucination check.** The answer is evaluated against the text that was actually read. Relevance and hallucination scores are returned with it. 6. **Output.** A readable `REPORT.md`, structured JSON, and one dataset row. ### What you get back | Output | Where | Use | |---|---|---| | `REPORT.md` | Key-value store | Brief to read and share | | `OUTPUT` (JSON) | Key-value store | `id`, `status`, `query`, `answer`, `sources`, `cited_sources`, `evaluation` | | Dataset row | Dataset | One row per run: question, answer, status, sources | `sources` lists every page that was read. `cited_sources` lists the ones the answer relies on. The gap between the two shows what was checked and set aside. ### Example: a real brief with sources and evaluation **Question** ```json { "query": "Competitors to The RealReal US luxury resale marketplaces list (Vestiaire Collective, Fashionphile, Rebag, StockX, Poshmark, Tradesy, TheRealReal competitors)" } ``` **Answer** (unedited output) The primary competitors to **The RealReal** in the U.S. and global luxury resale market include **Vestiaire Collective**, **Fashionphile**, **Rebag**, **Tradesy**, **Poshmark**, **Grailed**, **Luxury Garage Sale**, **Chrono24**, **Sotheby's**, and **eBay** [The RealReal Strategy and Business Model - Umbrex](https://umbrex.com/resources/company-profiles/the-realreal/)[The RealReal Competitors: Complete List - Distill Intelligence](https://www.distillintelligence.com/competitors/the-realreal). #### Direct Luxury Resale Specialists These platforms compete directly for authenticated pre-owned supply and luxury buyers, often specializing in handbags, watches, and accessories: - **Vestiaire Collective**: A major global luxury resale marketplace with strong presence in Europe and cross-border reach; one of The RealReal's clearest category peers [The RealReal Strategy and Business Model - Umbrex](https://umbrex.com/resources/company-profiles/the-realreal/)[Battle Of Luxury Resale Business Models: The RealReal Vs. Reflaunt](https://www.forbes.com/sites/pamdanziger/2022/10/07/battle-of-luxury-resale-business-models-the-realreal-vs-reflaunts-resale-as-a-service/). - **Fashionphile**: U.S.-focused authenticated resale player best known for handbags, accessories, and watches; competes directly for premium supply [The RealReal Strategy and Business Model - Umbrex](https://umbrex.com/resources/company-profiles/the-realreal/)[The RealReal Competitors: Complete List - Distill Intelligence](https://www.distillintelligence.com/competitors/the-realreal). - **Rebag**: Luxury resale specialist concentrated in handbags, accessories, and watches, with a stronger emphasis on instant offers and trade-in experiences [The RealReal Strategy and Business Model - Umbrex](https://umbrex.com/resources/company-profiles/the-realreal/)[The RealReal Competitors: Complete List - Distill Intelligence](https://www.distillintelligence.com/competitors/the-realreal). - **Tradesy**: Acquired by Vestiaire Collective, it is a key U.S. luxury resale platform; Farfetch's pre-owned section also intersects here [The RealReal Strategy and Business Model - Umbrex](https://umbrex.com/resources/company-profiles/the-realreal/)[Luxury Resale Market Research Report 2034 - Dataintelo](https://dataintelo.com/report/global-luxury-resale-market). - **Luxury Garage Sale**: Curated designer consignment service offering high-end luxury goods [The RealReal Competitors: Complete List - Distill Intelligence](https://www.distillintelligence.com/competitors/the-realreal). #### Category-Specific or Premium Substitutes These platforms focus on specific luxury categories or high-value collectibles: - **Chrono24**: Specialist marketplace for luxury pre-owned watches; matters most in the watch category rather than across all of The RealReal's assortment [The RealReal Strategy and Business Model - Umbrex](https://umbrex.com/resources/company-profiles/the-realreal/)[The RealReal Competitors: Complete List - Distill Intelligence](https://www.distillintelligence.com/competitors/the-realreal). - **Sotheby's** and **Christie's**: Auction houses for high-end watches, jewelry, handbags, art, and collectible luxury items; compete in very high-value segments [The RealReal Strategy and Business Model - Umbrex](https://umbrex.com/resources/company-profiles/the-realreal/). - **Grailed**: Community marketplace for curated menswear and luxury streetwear [The RealReal Competitors: Complete List - Distill Intelligence](https://www.distillintelligence.com/competitors/the-realreal). #### Broader Resale and Marketplace Substitutes These platforms are broader, less curated, or social-driven but still serve as substitutes for apparel and accessory resale: - **Poshmark**: Social commerce marketplace for buying and selling fashion; acquired by Naver in 2023 for ~$1.2B and expanding into luxury authentication [The RealReal Competitors: Complete List - Distill Intelligence](https://www.distillintelligence.com/competitors/the-realreal)[Luxury Resale Market Research Report 2034 - Dataintelo](https://dataintelo.com/report/global-luxury-resale-market). - **eBay**: Large marketplace with authentication programs in some categories; competes for price discovery [The RealReal Strategy and Business Model - Umbrex](https://umbrex.com/resources/company-profiles/the-realreal/). - **thredUP**: Managed resale platform with lower-price, less luxury-focused profile; relevant more for closet cleanout than high-end hard luxury [The RealReal Strategy and Business Model - Umbrex](https://umbrex.com/resources/company-profiles/the-realreal/). - **StockX**: Strong in sneakers, streetwear, and collectible categories; overlaps where luxury and collectible fashion converge [The RealReal Strategy and Business Model - Umbrex](https://umbrex.com/resources/company-profiles/the-realreal/). #### Key Market Context - The RealReal is the most prominent dedicated luxury resale platform in North America, operating a consignment model with in-home pickup and physical authentication locations [Luxury Resale Market Research Report 2034 - Dataintelo](https://dataintelo.com/report/global-luxury-resale-market). - The global secondhand luxury market was valued at ~$32B in 2021, growing five times faster than the primary market [Battle Of Luxury Resale Business Models: The RealReal Vs. Reflaunt](https://www.forbes.com/sites/pamdanziger/2022/10/07/battle-of-luxury-resale-business-models-the-realreal-vs-reflaunts-resale-as-a-service/). - **Vestiaire Collective** is the global leader in peer-to-peer luxury resale across 80+ countries and now owns Tradesy [Luxury Resale Market Research Report 2034 - Dataintelo](https://dataintelo.com/report/global-luxury-resale-market). - The top five players (including The RealReal, Vestiaire Collective, Farfetch, Poshmark, and Richemont) collectively account for ~42% of global market revenue as of 2025 [Luxury Resale Market Research Report 2034 - Dataintelo](https://dataintelo.com/report/global-luxury-resale-market). The RealReal's closest competitive set is made up of platforms that compete for **authenticated pre-owned supply**, with traditional retailers acting as indirect competitors [The RealReal Strategy and Business Model - Umbrex](https://umbrex.com/resources/company-profiles/the-realreal/). **Sources read (7)** 1. https://umbrex.com/resources/company-profiles/the-realreal/ (cited) 2. https://www.forbes.com/sites/pamdanziger/2022/10/07/battle-of-luxury-resale-business-models-the-realreal-vs-reflaunts-resale-as-a-service/ (cited) 3. https://www.distillintelligence.com/competitors/the-realreal (cited) 4. https://dataintelo.com/report/global-luxury-resale-market (cited) 5. https://www.facebook.com/TheRealRealPage/posts/the-worlds-most-trusted-and-beloved-source-for-authenticated-luxury-resale/1447062914127677/ (read, not cited) 6. https://circularfashionnews.substack.com/p/the-state-of-luxury-resale-how-new (read, not cited) 7. https://www.tiktok.com/@therealreal/video/7622834758938053902 (read, not cited) **Evaluation** ```json { "evaluation": { "relevance": 1, "hallucination": 1, "notes": "Quality: Good, well-structured list with useful category grouping and source links, but it lacks strategic depth and some up-to-date specifics. Improve by: 1) Adding quantitative comparators (revenue, GMV, active buyers/sellers, market share and geography) to show relative scale and threat level. 2) Including missing relevant players and services (e.g., Reflaunt, Farfetch's pre-owned offering, resale tech providers) and clearly distinguishing consignment vs buy-now vs peer-to-peer models. 3) Providing a short competitor-positioning matrix (business model, category focus, strengths/weaknesses) and a 2–3 line strategic implication (where The RealReal should prioritize defense or partnerships).\nRelevance: Direct, focused, and on-topic — lists the key competitors and groups them usefully. To improve relevance further: 1) Clarify whether the user wanted strictly US-only competitors (this answer mixes US and global players); 2) Add a few other relevant peers that some users expect (e.g., Farfetch pre-owned, Reflaunt, GOAT for certain luxury streetwear overlaps) and note acquisition dates where stated; 3) Update or timestamp market figures and market-share claims so the reader knows the data vintage.\nHallucination: No fabricated or unsupported specific factual claims detected — the named competitors and market facts in the response are supported by the provided Umbrex, Distill Intelligence, Dataintelo, and Forbes sources. Minor notes: the response repeats "Tradesy" twice (typo/redundancy) and mixes multiple sources for some items (e.g., Sotheby's is cited via Umbrex whereas Distill's excerpt omits it) — you may want to harmonize source attributions for clarity.\nPublication-date transparency for cited sources (01/01/2020 to 12/31/2026):\n- 4/4 cited sources are within the requested time window." } } ``` ### Who it is for - **Analysts and consultants** who need a first draft they can defend, with every claim one click from its source. - **AI agents and workflows** that need a checked answer as a tool call, with a score they can gate on. - **Teams in regulated or high-stakes work** where an unsourced answer cannot be used. ### How it compares | | SERP scraper | RAG web browser | FifthRow Answers | |---|---|---|---| | Returns | Search results | Page text | A written brief | | Reads full pages | Sometimes | Yes | Yes, every cited page | | Citation on each claim | No | No | Yes | | Checks the answer against sources | No | No | Yes, with a score | | Best for | Lists of results | Feeding your own LLM | Answers you must be able to prove | ### Input | Field | Required | Description | |---|---|---| | `query` | Yes | The strategic question | | `search_domain_allowlist` | No | Up to 20 domains to search | | `search_domain_denylist` | No | Up to 20 domains to exclude | | `search_after_date_filter` | No | Only sources after this date | | `search_before_date_filter` | No | Only sources before this date | The FifthRow API key is configured on the Actor. You only provide the question and constraints. ### Pricing **$0.14 per run.** The price covers searching, fetching and reading every cited page in full, writing the cited brief, and running the hallucination check. Reading full pages is the costly step, and it is what makes the check possible. | Runs | Cost | |---|---| | 10 | $1.40 | | 100 | $14 | | 1,000 | $140 | ### Use it from an agent Call it through the Apify API or the Apify MCP server. ### FAQ **How is the answer checked?** The answer is evaluated against the pages that were read. The `evaluation` object returns relevance and hallucination scores. **What is the difference between `sources` and `cited_sources`?** `sources` are all pages read. `cited_sources` are the pages the answer relies on. **Can I limit where the evidence comes from?** Yes. Use the allowlist for trusted domains, the denylist to exclude others, and the date filters to keep evidence current. **What if the evidence is thin?** The brief says so. When sources do not cover a question directly, the answer states the closest evidence it found and where the gap is. **What happens if a run fails?** The run stops with a FifthRow error. Report issues in the Issues tab. # Actor input Schema ## `query` (type: `string`): The strategic question for FifthRow Answers to ground, source, and return as a brief. ## `search_domain_allowlist` (type: `array`): Optional domain allowlist for web evidence. Maximum 20 domains. ## `search_domain_denylist` (type: `array`): Optional domain denylist for web evidence. Maximum 20 domains. ## `search_after_date_filter` (type: `string`): Optional lower bound for source recency, for example 2026-01-01. ## `search_before_date_filter` (type: `string`): Optional upper bound for source recency, for example 2026-12-31. ## Actor input object example ```json { "query": "What changed in European battery recycling policy this year?" } ``` # Actor output Schema ## `markdown` (type: `string`): Grounded Answers brief stored as KVS REPORT.md. ## `OUTPUT` (type: `string`): Complete Answers JSON result stored as KVS OUTPUT. ## `overview` (type: `string`): Finished Answers run as a default dataset item. # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = {}; // Run the Actor and wait for it to finish const run = await client.actor("fifthrow/fifthrow-answers").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = {} # Run the Actor and wait for it to finish run = client.actor("fifthrow/fifthrow-answers").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}") for item in client.dataset(run.default_dataset_id).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{}' | apify call fifthrow/fifthrow-answers --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "type": "http", "url": "https://mcp.apify.com/?tools=fetch-actor-details,fifthrow/fifthrow-answers" } } } ``` The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer ` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations). ## OpenAPI specification Download the OpenAPI definition: https://api.apify.com/v2/actors/qgVJe0j32DqHZJVgB/builds/aLumRyQ0gZlV4LYeg/openapi.json