When converting a vendor's feature-comparison page (plans in columns, features in rows) to text, included/not-included cells rendered as SVG icons vanish, so researchers conclude the check marks are images and unreadable, and record tier availability as unknown or guess it from tooltips.

When researching an API vendor's developer docs through its llms.txt index, the "OpenAPI Specs" section lists /docs/specs/<version>/<name>.json links that return 404, and the .md variant of a page shows no "last updated" date. Old changelog posts found by a search engine can also return 404 because the changelog was migrated and only recent posts are still hosted.

When researching observed behavior on a Discourse-based community forum, curl gets HTTP 403 (bot protection) and a rendered scrape of /t/<slug>/<id> often returns only the first post because replies are lazy-loaded by JavaScript. Accepted answers and later replies are then missing.

Research notes that cite documentation with verbatim quotes drift from the source: quotes get typed from a markdown scrape that inserted or dropped spaces, curly apostrophes become straight ones, a quote ends up attributed to the wrong page, or a paraphrase sits in quotation marks. Checking by eye misses these.

When researching a vendor's developer docs built on a docs platform that exposes Markdown variants of each page (URL + ".md", advertised via llms.txt), the Markdown version of "object definition" pages only contains headings like "Properties" and "Associations" with no content. The property tables (label, internal name, type, description) and association type ID tables are rendered client-side by a JS component, so the .md export and simple fetchers report that the table is absent.

Large web-verified research tasks (a dozen entities, each needing several dated episodes plus a current-state snapshot, every number sourced) blow the context of a single agent and take too long serially; naive delegation returns prose that is hard to merge and unverifiable.

When compiling sourced stock-performance research (episodes + current YTD/12-month numbers) via an agent, the plain URL fetcher returns HTTP 403 on CNBC, Morningstar, Forbes, Axios and Yahoo Finance sub-pages, and aggregator "YTD tables" silently disagree with each other (one showed a 1-year return of +898% for a $5T stock — a data error) and with dated primary articles.

You want to find companies currently valued below what large strategic corporate investors paid for their stakes. Naive approaches fail: 13F filings show holdings but not cost basis; many deal prices are never disclosed; private-company "current valuations" are just the latest round mark, so a flat number can mean either "no markup" or simply "no news"; and headlines about position changes are often wrong.