Context.dev
An independent read of the brand's rendered accent and type usage, chosen logo, social accounts, and industry so the report can disclose where two separate captures agree or conflict.
The facts a reader needs
| What it unlocks | Six optional units, all off by default behind the same two gates: the report's design-system section (rendered style guide), a second opinion on five finished report claims, the quality reviewer's cross-source receipts, industry + NAICS/SIC seeding only where no human or domain-verified source exists, a one-credit competitor list beside DataForSEO's, and two rescues — interview prefill chips before a pull, and page recovery when a site blocks the crawler. None can alter a collector's output, outrank a human answer, or change the pull outcome. |
| When it is called | Only after every ordinary pull leg settles, and only when CONTEXT_DEV_ENABLED is exactly true and CONTEXT_DEV_API_KEY is present. Never on the free instant card and never when either gate is missing. |
| Cost basis | 25 measured credits per enabled pull when all three required endpoints run: 10 brand retrieval + 10 rendered style guide + 5 rendered font usage. Dollar cost stays unknown unless CONTEXT_DEV_CREDIT_TIER names a reviewed rate. |
| Environment | CONTEXT_DEV_API_KEY |
| Bring your own key | Not on this deployment. |
The optional capture_result.second_opinion sibling. It comments on the finished pull and never changes a collector, ranked result, report leg, pull outcome, or customer charge.
Endpoints we call
| Endpoint | Why we call it |
|---|---|
GET /v1/brand/retrieve | Identity record: logos, social-account set, registered address, EIC industry classification. 10 credits. Feeds the second opinion, the industry gap-filler, and the pre-interview intake peek's suggestion chips. |
GET /v1/web/styleguide | The rendered design system (type ladder, spacing, shadows, component CSS) that becomes the report's design-system section — and, REUSED at no extra cost, the second opinion's colour comparison. 10 credits, once per pull. |
GET /v1/web/fonts | Rendered-word font percentages, compared with the report's lead face. 5 credits. |
GET /v1/web/naics + /v1/web/sic | Taxonomy codes when the vendor fills the industry gap; high-confidence NAICS names also seed the SEO industry keyword tier, each keyword stamped vendor_taxonomy_term. 10 credits each, gap-filling pulls only. |
POST /v1/web/search | A second competitor list rendered beside DataForSEO's, never merged into it. 1 credit. |
GET /v1/web/scrape/markdown | Blocked-site rescue only: when the crawler is bot-walled on every page, up to three pages recovered at 1 credit each, honestly noted as markdown-only. Firecrawl is always first. |
Firecrawl
Your own site opened and rendered the way a browser would, page by page — batched rather than one at a time, with a bot-walled page retried once through a rotating proxy — and captured as images while we are there, cookie banner clicked out of frame first.
OpenAI
One language-model read of your own copy, turned into voice claims that each have to quote your text or be dropped — and, before any money is spent, a second opinion on whether a candidate business is really you.