SaaSScout: A Grounded RAG Copilot for SaaS Evaluation.

Retrieval-Augmented Generation (RAG) —

Retrieve evidence before generating a recommendation.

The pipeline retrieves product records, review snippets, and enrichment evidence before generating an answer. That gives users source material to inspect and constrains the summary to a relevant context. Generated claims still need review, especially when pricing or feature coverage is incomplete.

Evidence lane architecture —

Keep source provenance visible.

Product metadata, user reviews, and vendor enrichment answer different questions and have different limitations. Separate Chroma retrieval collections and source-aware evidence displays preserve those distinctions. TF-IDF fallback supports retrieval when the vector store is unavailable.

Multi-signal pre-generation ranking —

Rank candidates before generating the summary.

Candidate scoring combines feature fit, pricing, review evidence, category relevance, and evidence quality before generation. Keeping ranking separate from the prose makes a recommendation easier to inspect and gives the user a clearer basis for comparing tools.

Epistemic honesty in output design —

Treat missing evidence as a procurement finding, not a model failure.

When the retrieval layer returns no Wikidata record for a vendor, or no pricing data for an enterprise tier, the typical AI response is to either hallucinate a placeholder or silently omit the row. Both are wrong for procurement. SaaSScout renders missing evidence as an explicit cell in the evidence table, tagged with the lane it came from. A blank pricing cell is a procurement red flag — it usually signals "contact sales" or a non-public tier — and surfacing it as a gap gives the analyst the right signal: this is something you must verify before buying. The design rule is that absence of evidence is itself evidence, and the product makes it visible rather than papering over it.

Keep a useful fallback when an LLM is unavailable.

A provider-neutral generation layer supports Groq online, Ollama locally, and a deterministic template fallback. The fallback uses the same retrieved evidence and scoring to produce a comparison without an LLM call. This keeps the workflow usable during provider failures while leaving source quality and coverage visible.

Packaged artifact, same-origin proxy, and scheduled smoke monitor for zero-dollar reliability.

Three infrastructure decisions compound into production reliability on a free-tier stack. The processed Chroma index and normalized data are packaged as a versioned zip in a GitHub Release and pulled at backend startup via DATA_ARTIFACT_URL — dropping cold-start rebuild time from 5 minutes (Kaggle re-download plus Chroma rebuild) to roughly 30 seconds. Frontend API calls route through a Netlify /api/* edge proxy instead of cross-origin requests, collapsing CORS preflight latency and enabling same-origin caching. A scheduled GitHub Actions workflow hits /health, /api/status, and a low-cost template /api/analyze to keep the Render dyno warm during business hours and reports the first failing layer — Netlify, Render, Chroma, enrichment, or analyze — on failure. The combination delivers observable, warm, reproducible infrastructure at $0.