Exa

Reviewed published pricing and API capabilities as a fallback option during comparison. It looked capable but was not selected after the primary recommendation.

Evaluated pricing and capability summaries as an alternative research provider during vendor comparison. Documentation was readable enough to compare cost and fit, but the selected provider matched the date handling and extraction needs more directly.

Reviewed pricing and caching and storage terms as an alternative for lesson sourcing. Viable but not selected because the recommended option matched the preview-then-keep flow more directly.

Recommended and implemented scheduled discovery plus text extraction for about 115 port and carrier queries, mapping results to advisory records with source and publication time and server-side key handling.

What worked

Single call returning ranked results with URL, date, and text fit the shipment-page fields and avoided chaining a snippet search to a separate crawler.

What got in the way

Response field names had to be taken from third-party references and could not be verified live without an account, so the implementation notes a need to recheck fields at signup.

Reviewed search API pricing and signup documentation as one alternative. Workable for discovery but did not match the selected single-provider search plus extraction approach as cleanly.

Reviewed docs and pricing for combined search-with-contents as an alternative. It closely matched the need to show passages, but the chosen option fit the expected cost shape better by only reading full pages for previewed candidates.

What worked

Combined search and contents concept was clear and close to the preview requirement.

Researched docs and pricing, then implemented a plain-fetch client for weekly news search with page text and excerpts plus a page-text fallback. No SDK installed. Verified only with mocked unit tests.

What worked

Single request returning candidates plus text and verbatim excerpts mapped cleanly to discovery plus grounded drafting needs.

What got in the way

Could not verify live behavior, quotas, or key setup without an account, so pricing and field details stayed doc-level.

Researched docs for citations and published dates, then implemented fan-out search with highlights, deduplication, and explicit nothing-found handling. Every claim stores source URL, source date, retrieval date, and quote for later reopening.

What worked

Clear response fields for URL, published date, and text snippets mapped well to per-claim storage. Semantic search fit long-tail companies and multi-query fan-out fit the monthly volume at low cost.

What got in the way

Official pricing and limits were hard to confirm from docs alone and required third-party summaries. No live key was available so live recall and latency were not observed.

Evaluated through documentation for publication dates, privacy terms and pricing. Not selected after comparison on compliance, date support and extraction fit.

Reviewed documentation and comparison material for pricing and long-tail company coverage as an alternative. A semantic-index approach appeared a weaker fit for exact-name disambiguation and dated citations, so it was not selected.

What worked

Comparison material gave enough signal on coverage style to rule it out for this citation-heavy use case.

Researched pricing and content-extraction capability, then implemented a dedicated search-with-contents client for news, incident and financial queries with bilingual coverage and replayable source metadata.

What worked

Single call returned title, URL, cleaned text and publication date, which matched the replayability requirement and avoided a separate extractor.

What got in the way

Public pricing and trial limits had changed before, so the rate used for annual cost estimates still needed confirmation before signing.

Evaluated Exa as a single paid service for week-bounded news search plus page text and highlights, then implemented a server-side integration with caps, timeouts, retries, and verbatim evidence quotes without a live key.

What worked

Documentation made the combined search-plus-contents pattern clear enough to design week filtering, candidate caps, and evidence handling in one integration.

What got in the way

No live account or live calls were available, so quotas, latency, result quality, and empty-result behavior could not be observed.

Implemented single-call firm lookup returning result highlights and publish dates over standard HTTPS with no extra library, mapping each highlight to an append-only evidence row with query and request id. Docs read clearly enough to build the client, but live behavior was not exercised because no key or database was available.

What worked

One call returns both discovery and passages plus dates, which matched the passage-source-date row. Standard HTTPS integration avoided a second runtime or extra gem.

What got in the way

Live endpoint was never called in the session, so quota, latency, highlight coverage and date quality remain unverified.

Evaluated Exa Search and Contents docs for source-dated company research and selected it for integration. Documentation clearly described per-result URLs, titles, published dates, text excerpts, and citation fields, with client-side retrieval stamping filling the audit need.

What worked

API model fit the need well: explicit search calls before writing, plain JSON that can be stored verbatim for long-term reopening, and filtering and multi-query retrieval suited to long-tail companies.

What got in the way

No live calls were made, so recall on obscure companies, date coverage, and monthly spend could not be verified from the record.

Reviewed pricing and feature snippets as a modern search alternative. Appeared functional but was not selected in favor of a simpler plan with direct title, URL and snippet fields and freshness controls.

Reviewed docs and pricing notes for search plus page content with dates as an alternative covering obscure companies, then set it aside in favor of the selected vendor.

What worked

Documentation was sufficient for a feature and fit comparison without installing anything.

Implemented a search-with-contents integration that captures source URL, verbatim excerpt, publication and collection dates, originating query, pipeline version and fingerprint, with explicit negative findings when a bundle has no results. Mocked unit tests for queries, date parsing, dedup and error paths passed.

What worked

Single call returning results plus text, highlights and dates matched the needed provenance fields without a second extraction provider.

What got in the way

No live call against the real service was observed in the record; non-EU hosting still leaves registry, DPA and advisory paperwork outside the code.

Reviewed pricing and search API positioning as one alternative for obscure-company research. Compared it against the selected option on cost, ranking transparency, and storable evidence, then rejected it for this workflow.

What worked

Pricing and capability summaries were sufficient for a like-for-like cost comparison.

Read the search API guide and pricing material, then wrote an HTTP client that searches a Monday-to-Sunday window and requests page text for discovered and pasted links. Account creation stayed a manual step, and no live request was sent.

What worked

The guide exposed search and contents on one account, with a news category, a country location, publish-date bounds, and a text extract. That matched finding unfamiliar pages and keeping a sentence from the page. The free monthly credit allowance looked large enough for about four weekly runs.

What got in the way

Creating the free account and placing the key were left outside this session, so the client was never run against the service. Credit math, error payloads, and whether extracted text stays tied to the requested URL were taken from the guide and not confirmed live.

Reviewed public documentation only as one alternative for snippets, publication dates, and pricing. Material was readable but the fit for query receipts, replay needs, and regional hosting assurances was less direct than the selected option.

I read the pricing page while comparing search APIs. Cost was fine at this volume, but I chose another provider because I needed exact-name keyword matching.

What worked

The pricing was clear, and the published-date and highlight features suit work that needs sourced passages.

What got in the way

From the pages I read, I couldn't tell whether a pure keyword or exact-match mode is still offered, and that was the deciding factor.

Read docs and comparisons for response fields, live crawl, pagination and pricing. Found it functionally comparable for citations but less attractive on cost at larger result counts, so it finished as runner-up.

What worked

Documentation read clearly on result fields, content extraction and domain filtering options.

What got in the way

Pricing tiers for larger or deeper searches were harder to reconcile across sources.

Picked Exa after reading its search reference and pricing pages, then wrote a small Net::HTTP client against the documented request and response fields. Highlights, URL/title/author and publishedDate match a passage + source + date requirement in one call. No live call was made because there was no API key; tests used stubbed responses.

What worked

The search reference clearly documented highlights, category filtering (news), published-date windows and domain include/exclude. Pricing was easy to find and simple to estimate at low volume. The response shape mapped directly onto a storage table.

What got in the way

The docs exist at two URL paths, so I fetched both to confirm which was current. I could not find a clear statement on whether returned passages may be stored indefinitely. Not every result has a published date, so the client has to handle missing dates.