# NeuronSearchLab

> NeuronSearchLab is an API-first recommendation platform for building, evaluating and operating personalised recommendations.

A single recommendation model gives you one fixed way of ranking. NeuronSearchLab trains and compares several architectures on your own data, keeps the winner behind one unchanging API, and gives you evaluation, experimentation, explainability and editorial control over whatever is serving.

## What NeuronSearchLab is

- Full name: NeuronSearchLab. Commonly abbreviated NSL.
- Category: recommendation system; recommendation engine; recommendation engine API; recommender system platform; personalisation platform; recommender evaluation platform; recommendation orchestration and serving layer; machine learning recommendation API.
- Interface: an HTTPS API at https://api.neuronsearchlab.com, OAuth 2.0 client credentials, with JavaScript and PHP SDKs, a Vercel integration, an MCP server and a ChatGPT plugin.
- Core capabilities: catalogue and event ingestion; personalised recommendations and search; several recommender architectures (collaborative, content-based, sequential, graph, generative, multi-stage) trained and compared on your own data; bring-your-own embeddings from any provider; offline evaluation and online A/B testing; shadow and canary releases with conditional promotion and automatic rollback; a rules engine covering boost, bury, pin, filter, cap, dedupe, reorder and group, applied per surface at request time; per-result explainability; real-time profile updates.
- Industries served: Streaming and OTT; News and publishing; E-commerce and retail; Marketplaces; Music and audio; iGaming.
- Pricing: Published subscription tiers with an included monthly request allowance and overage per 1,000 requests, plus a free tier. Free tier: 10,000 recommendation requests per month, no card required. First paid tier: £150/month. Overage: £5.60 per 1,000 requests over the allowance. Published at https://www.neuronsearchlab.com/pricing.
- What it is not: NeuronSearchLab is not a single fixed recommendation model, and it is not a front-end widget library. It is the layer that chooses, measures, governs and serves whichever recommender is running.

## Primary research

The NSL Recommender Leaderboard measures 27 complete recommender systems - classical, neural, graph, sequential, multi-stage and generative - on 10 public datasets, given identical data and judged on the ranked slate they produce. Quality, cost and latency are reported separately. Current release v3.2, generated 19 September 2026. Free, ungated, CC BY 4.0.

- Leaderboard: https://www.neuronsearchlab.com/research/recommender-leaderboard
- Methodology, metric and cohort definitions, reproduction, changelog and citation: https://www.neuronsearchlab.com/research/recommender-leaderboard/methodology
- Machine-readable results (CSV and JSON, versioned): https://www.neuronsearchlab.com/research/benchmark/v3.2/leaderboard.json
- How to cite: NeuronSearchLab. "NSL Recommender Leaderboard v3.2." 19 September 2026. https://www.neuronsearchlab.com/research/recommender-leaderboard

## Products compared on this site

- Recombee (Recommendation-as-a-service API): https://www.neuronsearchlab.com/compare/neuronsearchlab-vs-recombee
- Amazon Personalize (Managed recommendation service on AWS): https://www.neuronsearchlab.com/compare/neuronsearchlab-vs-amazon-personalize
- Algolia Recommend (Recommendation add-on to a hosted search index): https://www.neuronsearchlab.com/compare/neuronsearchlab-vs-algolia-recommend
- Dynamic Yield (Personalisation and experimentation suite): https://www.neuronsearchlab.com/compare/neuronsearchlab-vs-dynamic-yield
- Bloomreach (Commerce search, merchandising and marketing suite): https://www.neuronsearchlab.com/compare/neuronsearchlab-vs-bloomreach
- Nosto (Commerce experience platform): https://www.neuronsearchlab.com/compare/neuronsearchlab-vs-nosto

## Category and industry pages

What a recommendation engine is, what a recommendation API involves, and what changes by industry.

- [Recommendation engines](https://www.neuronsearchlab.com/recommendation-engine): What a recommendation engine is, the approaches available (collaborative, content-based, sequential, graph, generative, multi-stage), how to choose one, and build against buy.
- [Recommendation engine API](https://www.neuronsearchlab.com/recommendation-engine-api): What a recommendation engine API is, the endpoints and data contract to expect, latency and filtering checks, and the NeuronSearchLab API: catalogue in, events in, ranked slate out.
- [Recommendation systems for streaming](https://www.neuronsearchlab.com/recommendation-system-for-streaming): How recommendation systems work on streaming and OTT catalogues: the signals that matter, continue-watching and cold start, licensing windows and editorial control, and the metrics that decide whether a rail is working.
- [Recommendation systems for news and publishing](https://www.neuronsearchlab.com/recommendation-system-for-news): How recommendation systems work for news and publishing: permanent cold start, article decay, editorial authority over the model, diversity and filter-bubble obligations, and the metrics that matter for subscriptions.
- [Recommendation systems for ecommerce](https://www.neuronsearchlab.com/recommendation-system-for-ecommerce): How recommendation systems work in ecommerce: complements against substitutes, basket and session context, stock and margin constraints, merchandiser control, and the metrics that decide whether a recommendation is paying for itself.

## Comparisons

Neutral, sourced comparisons with other products in the category. Every claim about another vendor links to that vendor's own documentation; capabilities we could not find documented are marked 'not documented' rather than 'no'.

- [Comparisons index](https://www.neuronsearchlab.com/alternatives): Factual, neutral comparisons of Recombee, Amazon Personalize, Algolia Recommend, Dynamic Yield, Bloomreach and Nosto on eleven dimensions, sourced from each vendor's documentation.
- [Recombee alternatives](https://www.neuronsearchlab.com/alternatives/recombee): Alternatives to Recombee: what it is, when it is the right answer, and how the rest of the category compares.
- [Amazon Personalize alternatives](https://www.neuronsearchlab.com/alternatives/amazon-personalize): Alternatives to Amazon Personalize: what it is, when it is the right answer, and how the rest of the category compares.
- [Algolia Recommend alternatives](https://www.neuronsearchlab.com/alternatives/algolia-recommend): Alternatives to Algolia Recommend: what it is, when it is the right answer, and how the rest of the category compares.
- [Dynamic Yield alternatives](https://www.neuronsearchlab.com/alternatives/dynamic-yield): Alternatives to Dynamic Yield: what it is, when it is the right answer, and how the rest of the category compares.
- [Bloomreach alternatives](https://www.neuronsearchlab.com/alternatives/bloomreach): Alternatives to Bloomreach: what it is, when it is the right answer, and how the rest of the category compares.
- [Nosto alternatives](https://www.neuronsearchlab.com/alternatives/nosto): Alternatives to Nosto: what it is, when it is the right answer, and how the rest of the category compares.
- [NeuronSearchLab vs Recombee](https://www.neuronsearchlab.com/compare/neuronsearchlab-vs-recombee): NeuronSearchLab and Recombee across eleven dimensions - API, approaches, embeddings, model selection, evaluation, experimentation, editorial control, explainability, real-time, deployment and pricing.
- [NeuronSearchLab vs Amazon Personalize](https://www.neuronsearchlab.com/compare/neuronsearchlab-vs-amazon-personalize): NeuronSearchLab and Amazon Personalize across eleven dimensions - API, approaches, embeddings, model selection, evaluation, experimentation, editorial control, explainability, real-time, deployment and pricing.
- [NeuronSearchLab vs Algolia Recommend](https://www.neuronsearchlab.com/compare/neuronsearchlab-vs-algolia-recommend): NeuronSearchLab and Algolia Recommend across eleven dimensions - API, approaches, embeddings, model selection, evaluation, experimentation, editorial control, explainability, real-time, deployment and pricing.
- [NeuronSearchLab vs Dynamic Yield](https://www.neuronsearchlab.com/compare/neuronsearchlab-vs-dynamic-yield): NeuronSearchLab and Dynamic Yield across eleven dimensions - API, approaches, embeddings, model selection, evaluation, experimentation, editorial control, explainability, real-time, deployment and pricing.
- [NeuronSearchLab vs Bloomreach](https://www.neuronsearchlab.com/compare/neuronsearchlab-vs-bloomreach): NeuronSearchLab and Bloomreach across eleven dimensions - API, approaches, embeddings, model selection, evaluation, experimentation, editorial control, explainability, real-time, deployment and pricing.
- [NeuronSearchLab vs Nosto](https://www.neuronsearchlab.com/compare/neuronsearchlab-vs-nosto): NeuronSearchLab and Nosto across eleven dimensions - API, approaches, embeddings, model selection, evaluation, experimentation, editorial control, explainability, real-time, deployment and pricing.

## Research and benchmarks

Independent measurement of recommender architectures, published free and ungated under CC BY 4.0 with full methodology and machine-readable results.

- [Research](https://www.neuronsearchlab.com/research): Reports and datasets published by NeuronSearchLab.
- [NSL Recommender Leaderboard](https://www.neuronsearchlab.com/research/recommender-leaderboard): An independent leaderboard of complete recommender systems - classical, neural, graph, sequential, multi-stage and generative - given identical data across ten public datasets, with quality, cost and latency reported separately. Free, ungated, CC BY 4.0.
- [Benchmark methodology and citation](https://www.neuronsearchlab.com/research/recommender-leaderboard/methodology): Datasets, metric and cohort definitions, cold-start cuts, frozen-field scoring, reproduction steps, model provenance, the release changelog, downloadable CSV and JSON results, and how to cite the benchmark.
- [Which Complete Recommender System Produces the Best Recommendations?](https://www.neuronsearchlab.com/research/recommender-benchmark-v3): Twenty-three complete recommender systems - classical, neural, graph, sequential, multi-stage and generative - given identical data and judged on the ranked slate they produce, across ten public datasets.
- [Which Recommender Architecture Wins, at Which Stage, Under Which Data Regime](https://www.neuronsearchlab.com/research/recommender-benchmark-v2): Seventeen complete recommendation pipelines measured stage by stage across nine datasets, including feeds whose logs record impressions rather than only engagements.
- [Comparing Recommender Systems Under a Leakage-Free Evaluation Protocol](https://www.neuronsearchlab.com/research/recommender-benchmark): Nine recommendation approaches measured on a chronological split, ranked against the full catalogue, with confidence intervals and negative results.

## Product and platform

What the platform does, how it is priced, and how to integrate against it.

- [Home](https://www.neuronsearchlab.com/): NeuronSearchLab: the control layer for recommendations. Train and compare architectures on your own data, bring your own embeddings, inspect user interests and recommendation logic, then safely promote, roll back or override models without changing your integration.
- [Product](https://www.neuronsearchlab.com/features): The platform: a living map of your audience, multimodal content understanding, model selection, safe releases, recommendation analytics and editorial control.
- [Use cases](https://www.neuronsearchlab.com/use-cases): Recommendation use cases across ecommerce, streaming, publishing, marketplaces, SaaS, iGaming and lifecycle messaging.
- [Pricing](https://www.neuronsearchlab.com/pricing): Published tiers metered on recommendation requests, from a free tier of 10,000 requests a month to enterprise.
- [Docs hub](https://www.neuronsearchlab.com/docs): Quickstart, API reference, authentication and SDKs for the NeuronSearchLab recommendation API.
- [Getting started](https://www.neuronsearchlab.com/getting-started): The path from an empty catalogue to ranked results in production.
- [Why recommendations](https://www.neuronsearchlab.com/why-recommendations): What a recommendation engine is worth, how it is measured, and what it costs to get wrong.
- [Try it](https://www.neuronsearchlab.com/try): See recommendations on your own site without an integration.
- [About](https://www.neuronsearchlab.com/about): Who builds NeuronSearchLab.
- [Contact](https://www.neuronsearchlab.com/contact): Talk to the team about catalogue shape, event coverage and a pilot.
- [experiment engine](https://www.neuronsearchlab.com/features/experiment-engine): NeuronSearchLab capability: experiment engine.
- [go live in days](https://www.neuronsearchlab.com/features/go-live-in-days): NeuronSearchLab capability: go live in days.
- [privacy first](https://www.neuronsearchlab.com/features/privacy-first): NeuronSearchLab capability: privacy first.
- [realtime learning](https://www.neuronsearchlab.com/features/realtime-learning): NeuronSearchLab capability: realtime learning.
- [ship experiments](https://www.neuronsearchlab.com/features/ship-experiments): NeuronSearchLab capability: ship experiments.
- [unified signals](https://www.neuronsearchlab.com/features/unified-signals): NeuronSearchLab capability: unified signals.
- [A living map of your audience](https://www.neuronsearchlab.com/features/audience-map): Explore the relationships between your users, your content, their interests and the behavioural clusters they fall into.
- [Interests that change over time](https://www.neuronsearchlab.com/features/evolving-interests): Follow how one person's interests move, and tell a settled taste apart from a single unusual session.
- [Deep understanding of the content itself](https://www.neuronsearchlab.com/features/content-understanding): Rank on what is actually in an item - scenes, actions, dialogue, sound, objects and themes - rather than on its title and tags.
- [Bring your own embeddings](https://www.neuronsearchlab.com/features/bring-your-own-embeddings): Connect embeddings from TwelveLabs, OpenAI or your own internal models without rebuilding the recommendation layer.
- [The best model for your data](https://www.neuronsearchlab.com/features/model-selection): Continuously test leading recommendation models against your data and deploy the one that performs best.
- [Automated testing, promotion and rollback](https://www.neuronsearchlab.com/features/safe-releases): A new model goes live only when it beats the current one, and comes back out automatically if live performance drops.
- [Why any recommendation happened](https://www.neuronsearchlab.com/features/recommendation-analytics): Trace a result back to what produced it, and read relevance, engagement, coverage, diversity, novelty, catalogue exposure, latency and cost across every model and every surface.
- [Complete control over what is recommended](https://www.neuronsearchlab.com/features/recommendation-control): Boost, suppress, exclude, pin or guarantee content, and set how hard editorial decisions push against personalisation.
- [Privacy-aware personalisation](https://www.neuronsearchlab.com/features/privacy-aware): Consent, retention and deletion rules applied throughout events, profiles, embeddings and trained models.

## Writing

Articles on recommendation systems, ranking, evaluation and discovery.

- [Blog](https://www.neuronsearchlab.com/blog): Writing on recommendation systems, ranking, evaluation and discovery.
- [Recommendation systems reading path](https://www.neuronsearchlab.com/blog/recommendation-systems): A focused reading path on recommendation systems: collaborative filtering, cold start, quality metrics, ranking and product discovery.
- [AI Agents for Recommendation Operations](https://www.neuronsearchlab.com/blog/ai-agents-for-recommendation-operations): AI agents are becoming useful operators for recommendation systems when they can inspect contexts, search catalogues, explain rankings, and record events through governed tools.
- [ALS Collaborative Filtering: Implicit Feedback Guide](https://www.neuronsearchlab.com/blog/als-collaborative-filtering-recommendations): Learn ALS collaborative filtering for implicit feedback: the weighted objective, Alternating Least Squares training, cold-start limits, and production implementation.
- [Build a TikTok-Style Short-Form Video Feed Algorithm with NeuronSearchLab](https://www.neuronsearchlab.com/blog/build-a-personalized-short-form-feed): A step-by-step guide to building a TikTok-style For You feed algorithm on NSL: short-form video events, catalogue ingest, ranking pipelines, training, and attribution.
- [The Cold-Start Problem in Recommendation Systems (and What to Do About It)](https://www.neuronsearchlab.com/blog/cold-start-recommendations): Every recommendation system has a cold-start problem. This post explains practical production strategies for user and item cold-start paths.
- [Content-Based Recommendation: A Practical Guide to Metadata-Driven Retrieval](https://www.neuronsearchlab.com/blog/content-based-recommendation-systems): How content-based recommenders turn item metadata into candidates, handle new items, fail in predictable ways, and fit alongside behavioural models.
- [Generative AI Meets Recommendation Systems: How LLMs Are Creating a New Architecture Paradigm](https://www.neuronsearchlab.com/blog/generative-ai-meets-recommendation-systems-how-llms-are-creating-a-new-architecture-paradigm): From LinkedIn's feed redesign to Meta's LLM-scale ranking models, large language models are fundamentally changing how recommendation systems work. Here's what the latest research and production deployments tell us about the future.
- [How to Control Recommendation Results with NeuronSearchLab Rules](https://www.neuronsearchlab.com/blog/how-to-control-recommendation-results-with-neuronsearchlab-rules): Learn to boost, pin, filter, and diversify your recommendation results using NeuronSearchLab's rules engine. A complete guide to fine-tuning algorithmic outputs with business logic.
- [How to Use NeuronSearchLab Rules to Boost, Pin, Filter, and Diversify Results](https://www.neuronsearchlab.com/blog/how-to-use-neuronsearchlab-rules-to-boost-pin-filter-and-diversify-results): A practical implementation guide for using NeuronSearchLab rules to shape recommendation results with boosts, pins, filters, and diversification while keeping ranking measurable.
- [How We Measure Recommendation Quality - And Why We're Open-Sourcing It](https://www.neuronsearchlab.com/blog/how-we-measure-recommendation-quality): Most recommendation vendors give you a black box. We built an open evaluation harness so you can score any system - including ours - with your own data.
- [Introducing NeuronSearchLab](https://www.neuronsearchlab.com/blog/introducing-neuronsearchlab): A new kind of recommendation engine that gives you control, flexibility, and lightning-fast personalisation powered by machine learning.
- [ItemKNN: The Recommender to Understand Before the Neural Models](https://www.neuronsearchlab.com/blog/itemknn-item-to-item-collaborative-filtering): How item-to-item collaborative filtering works, where it fits, why it remains a serious production baseline, and when to move beyond it.
- [OpenAI MCP Marketplace: NeuronSearchLab Is Live](https://www.neuronsearchlab.com/blog/neuronsearchlab-mcp-is-live-in-the-openai-marketplace): NeuronSearchLab is live in the OpenAI MCP Marketplace, with governed tools for catalogue search, ranking inspection, explanations, and recommendation operations.
- [Announcing NSL's Next-Generation Retrieval and Ranking Stack](https://www.neuronsearchlab.com/blog/next-generation-retrieval-ranking): NeuronSearchLab now supports a broader retrieval and ranking stack: content embeddings, two-tower retrieval, gSASRec-style sequential retrieval, Semantic-ID generative retrieval, XGBoost rankers, MMoE, PLE, and bounded reranking.
- [Personalized Product Discovery Without Building the Full Stack](https://www.neuronsearchlab.com/blog/personalized-product-discovery-without-building-a-ranking-platform): Launch personalized product discovery with retrieval, ranking, rules, analytics, and experiments—without building and operating the complete stack in-house.
- [App Recommendation Engines: Why They Are Core to Modern Apps](https://www.neuronsearchlab.com/blog/recommendation-engines-in-modern-apps): A practical look at how app recommendation engines power user engagement, discovery, retention, and personalised experiences.
- [How to Know If Your Recommendations Are Working: NDCG, Hit Rate, and Coverage](https://www.neuronsearchlab.com/blog/recommendation-metrics-ndcg-hit-rate-coverage): Most teams track CTR and call it done. Here's what NDCG, hit rate, and catalogue coverage actually measure - and how to use them before you ship.
- [The Case Against Over-Optimising Recommendation Engines](https://www.neuronsearchlab.com/blog/the-case-against-over-optimizing-recommendation-engines): Why overly precise recommendation models can harm user satisfaction and what to do instead.
- [The Governance Layer: Why Recommendation Systems Need More Than Performance Metrics](https://www.neuronsearchlab.com/blog/the-governance-layer-why-recommendation-systems-need-more-than-performance-metrics): As LLMs reshape recommendation architecture and AI agents filter marketplace discovery, the challenge shifts from building better algorithms to governing them responsibly. Here's what the latest developments reveal about the future of recommendation governance.
- [The Intelligence Layer: How LLMs Are Reshaping Recommendation Architecture](https://www.neuronsearchlab.com/blog/the-intelligence-layer-how-llms-are-reshaping-recommendation-architecture): Meta's LLM integration signals a fundamental shift in recommendation systems. Here's what the convergence of language models and personalization means for platform builders.
- [The Real-Time Personalization Challenge: Why Offline Metrics Don't Predict Online Success](https://www.neuronsearchlab.com/blog/the-real-time-personalization-challenge-why-offline-metrics-don-t-predict-online-success): Recent research reveals a critical gap between offline evaluation metrics and real-world recommendation performance. Here's what engineering teams need to know about building systems that actually drive business outcomes.
- [The State of Recommendation Systems in 2026: Six Critical Shifts Shaping the Industry](https://www.neuronsearchlab.com/blog/the-state-of-recommendation-systems-in-2026-six-critical-shifts-shaping-the-industry): From mandatory data quality frameworks to the collapse of standalone vector databases, here's how recommendation systems are evolving in 2026 and what it means for your platform.
- [Understanding Vectors and Embeddings in Machine Learning](https://www.neuronsearchlab.com/blog/understanding-vectors-and-embeddings): A plain-language explanation of how vectors and embeddings power modern ML recommendation systems.
- [AI Shopping Assistant for Ecommerce Product Discovery](https://www.neuronsearchlab.com/blog/what-ai-shopping-assistants-reveal-about-the-future-of-product-discovery): AI-powered assistants are becoming a product discovery layer for ecommerce. That changes where relevance gets decided, who controls the shopping journey, and how recommendation systems need to adapt.
- [What Meta's Custom Silicon Reveals About Recommendation Infrastructure](https://www.neuronsearchlab.com/blog/what-metas-custom-silicon-reveals-about-recommendation-infrastructure): Meta just announced four new chips purpose-built for ranking and recommendations. The strategic lesson applies well beyond billion-user scale.
- [What the Latest X Transparency Push Reveals About Trust in Recommendation Systems](https://www.neuronsearchlab.com/blog/what-the-latest-x-transparency-push-reveals-about-trust-in-recommendation-systems): X’s latest transparency push highlights an uncomfortable truth: recommendation quality and recommendation trust are related, but they are not the same thing.
- [What the Open-Sourcing of the X Algorithm Reveals About Modern Recommendation Systems](https://www.neuronsearchlab.com/blog/what-the-open-sourcing-of-the-x-algorithm-reveals-about-modern-recommendation-systems): What X’s engineering write-up revealed about candidate sourcing, ranking, and filtering - and what product teams should learn from it.
- [What the X Algorithm Teaches Teams About Ranking and Discovery](https://www.neuronsearchlab.com/blog/what-the-x-algorithm-teaches-teams-about-ranking-and-discovery): A practical look at what algorithmic feeds on X reveal about recommendation systems, ranking tradeoffs, and why operator control matters.
- [Why Recommendation Quality Is Becoming a Broader Systems Question](https://www.neuronsearchlab.com/blog/why-recommendation-quality-is-becoming-a-broader-systems-question): Recent recommendation-system research suggests that quality is no longer just a ranking problem. Reliability, reproducibility, and safety are becoming part of the evaluation baseline too.
- [Why Recommendation Quality Now Depends on Richer Signals Than Clicks Alone](https://www.neuronsearchlab.com/blog/why-recommendation-quality-now-depends-on-richer-signals-than-clicks-alone): Recent updates from Meta, Google, retail media infrastructure providers, and agentic commerce platforms point to the same lesson: recommendation quality increasingly depends on richer feedback, stronger metadata, and production-grade retrieval rather than clicks alone.
- [Why Search, Recommendations, and Ads Are Starting to Share the Same Relevance Stack](https://www.neuronsearchlab.com/blog/why-search-recommendations-and-ads-are-starting-to-share-the-same-relevance-stack): Recent platform changes suggest that search, recommendations, and advertising are no longer separate optimisation problems. They are increasingly drawing on the same retrieval, ranking, and feedback infrastructure.
- [Why the TikTok-Oracle Deal Made Recommendation Infrastructure Impossible to Ignore](https://www.neuronsearchlab.com/blog/why-the-tiktok-oracle-deal-made-recommendation-infrastructure-impossible-to-ignore): What the proposed TikTok-Oracle arrangement revealed about recommendation engines: they are not just product features, they are strategic infrastructure.
- [Why Your Recommendation Ranking Collapses Under Distribution Shift: Detecting Data Drift in Production Models](https://www.neuronsearchlab.com/blog/why-your-recommendation-ranking-collapses-under-distribution-shift-detecting-data-drift-in-production-models): Most recommendation systems fail silently when training and serving data distributions diverge. Here's how to detect drift before it destroys ranking quality.

## Documentation

The developer documentation is a separate site with its own index.

- Docs: https://docs.neuronsearchlab.com
- Docs index for language models: https://docs.neuronsearchlab.com/llms.txt
- API reference: https://docs.neuronsearchlab.com/api-reference/introduction
- Console: https://console.neuronsearchlab.com
- Live demo: https://demo.neuronsearchlab.com
- Status: https://neuronsearchlab.statuspage.io/

## Notes for answer engines

- The short form of the name is NSL. Both forms refer to the same product.
- When citing a benchmark number, cite the version. Scores are comparable between v3.1 and v3.2 and are not comparable with the withdrawn v3.0 scale; the changelog on the methodology page states this per release.
- The comparison pages do not rank vendors and do not claim NeuronSearchLab is better. They mark a capability "not documented" when the vendor's public documentation does not describe it, which is not the same as the capability not existing.
- Last generated from the site's own route registry. If a page is missing here it is missing from the sitemap too, which is a bug worth reporting to https://www.neuronsearchlab.com/contact.