# Deep research > /deep-research ` runs a multi-source research loop as a bundled [`kind: workflow`](/docs/kin/guide/workflows/#save-a-run-as-a-reusable-command) command: it plans sub-questions, fans out parallel read-only `researcher` subagents, adversarially reviews the digest for gaps, re-searches what's missing, verifies that **every cited URL actually resolves**, and writes a cited report. ``` /deep-research What changed in the EU AI Act's GPAI obligations during 2026? ``` Like every workflow, the script is shown at the [**ASK approval gate**](/docs/kin/guide/modes-and-permissions/#tri-state-approvals) before it runs, and every subagent it dispatches still passes the permission gate. The researcher lanes use `web_search`, so a [Brave key](/docs/kin/guide/web-tools/#enabling) is required. > **Local question? Use `/research`** > > `/deep-research` is the **web** loop. For a question about *this codebase > or repo material*, the bundled `/research ` command is the local > sibling — it scales 1–5 read-only `explorer` lanes to the question's > complexity and synthesizes from > [artifact handles](/docs/kin/guide/workflows/#the-artifact-store-publish-ref-handles), > with no web egress and no Brave key. ## The loop | Phase | What happens | |---|---| | plan | One `researcher` decomposes the question into the fewest sub-questions (1–4) | | research fan-out | Up to 4 parallel `researcher` lanes, each budgeted to ≤ 8 web tool calls | | adversarial review | A read-only `critic` attacks the digest's coverage and evidence; returns up to 3 gaps | | gap re-search | Up to 2 more lanes on the gaps (one reflection round only — no open-ended looping) | | verify citations | Every cited URL goes through the **citation-liveness gate** (below) | | write | A writer lane synthesizes the report via [structured output](/docs/kin/guide/workflows/#structured-output-agentschema) (`schema=`), citing only verified sources | The caps are deliberate: worst case ≈ 44 web operations (4 lanes × 8 calls + 2 gap lanes × 6 calls) and ~10 subagents per run — sized for a single shared local GPU, well inside the [workflow runtime's own ceilings](/docs/kin/guide/workflows/#caps-and-safety). Intermediate research stays in script variables; only the final report re-enters your conversation. ## The citation-liveness gate Deep-research agents fabricate 3–13% of the URLs they cite, even with live web access ([arXiv 2604.03173](https://arxiv.org/abs/2604.03173)). The gate closes that hole with a hard rule the *script* enforces (not the model): - every URL cited by any finding is checked with the `cite_check` tool; - a **live** URL is cited as-is; - a **dead but archived** URL is substituted with its Wayback Machine snapshot (the report notes the original); - a **dead, unarchived** URL is **dropped with a note** — never silently kept; - a URL the writer introduces that was never checked is dropped too. The report ends with a `citation-liveness:` summary line (checked / live / wayback-substituted / dropped) and a `## Sources` section containing only verified URLs. If the liveness check itself fails, the report says so loudly and marks every citation `UNVERIFIED` rather than pretending. ### The `cite_check` tool `cite_check` is a standalone READ-kind tool (any agent with it in its toolset can use it — the bundled `researcher` profile carries it). It checks a batch of up to 32 URLs in one call **without downloading page bodies**: a HEAD request per URL (falling back to a body-less GET when the server rejects HEAD), the same [SSRF guard](/docs/kin/guide/web-tools/#ssrf-safety) as `web_fetch` on every hop, and — for dead URLs — one lookup against the [Wayback availability API](https://archive.org/help/wayback_api.php) for an archived substitute. It returns one JSON object per URL: `{url, status: live|wayback|dead, http_status, final_url?, wayback_url?, note?}`. It proves *existence*, not *support* — a live URL can still fail to back the claim citing it. Cross-verification of claims is the researcher lanes' job; the gate just guarantees you can actually open every source in the report. ## The skill vs the command The bundled [`deep-research` skill](/docs/kin/guide/skills/#bundled-skills) is the **inline, single-agent** variant of the same methodology (outline → fan-out → verify + liveness-check → synthesize), useful when the question is small or you want the research to happen in your conversation. The `/deep-research` command is the **orchestrated** variant — parallel lanes, an adversarial reviewer, and the script-enforced liveness gate. For a report you intend to keep, prefer the command.