searchcans-deep-researchlisted

# SearchCans Deep Research Investigate a defined question with current localized web sources. Build an evidence bundle with an explicit source budget before writing conclusions; do not treat search snippets as proof. ## Set the scope Collect the research question, decision it supports, geographic and language scope, freshness requirement, exclusions, and source budget. If a missing constraint would materially change the answer, ask one concise question before searching. Write 3–5 distinct subquestions before calling the API. Cover the main claim, alternatives, primary evidence, material objections, and decision implications. The subquestions are the auditable research plan; do not start broad searching without them. Set `SEARCHCANS_API_KEY` in the execution environment. Never put a key in a prompt, file, command output, or report. ## Build the evidence bundle Pass the 3–5 subquestions to the script. Add `--query` only for an additional search formulation that the plan requires. Keep the source budget small unless the user explicitly needs broader coverage. ```bash python scripts/deep_research.py "What is changing in the EU AI Act for SaaS teams?" \ --subquestion "What official EU AI Act milestones apply to SaaS teams?" \ --subquestion "Which obligations differ for providers and deployers?" \ --subquestion "What 2026 guidance changes implementation priorities?" \ --country eu --language en --max-sources 5 --out research-bundle.json ``` Use `--headless` only wh