Deep research & multi-hop web agents

Scores as of 2026-09-14 (43 days old; Depot marks scores stale after 30 days). The pick is still Depot's current editorial pick; it has not been re-reviewed since. Prices below carry their own dates.

Depot Pick

Parallel · 8.07/10 for this job (curated estimate, high confidence)

Watch Perplexity Sonar deprecation timing. Confidence: medium-high on Parallel positioning.

Runner-up

Perplexity · 7.65/10

Scores higher than the pick on: Maturity / track record.

When not to use the pick

Perplexity Sonar/Agent API already adopted, or Tavily/Exa fit simpler RAG search.

Lock-in / migration

The pick has lower stored lock-in risk than runner-up Perplexity (4.2 vs 5.5). Self-host fallback listed for this job: Crawl4AI.

Sourced price (usd_per_search)

Pick: no sourced price in this job's unit (no_sourced_price).

Cheapest matching SKU: Exa Agent search tool call $0.005 — source, as of 2026-10-03. Not the pick; not quality-adjusted.

Price history: first seen 2026-10-03 · last changed no change recorded · history JSON

Free option

• Crawl4AI (oss) — source, as of 2026-10-25
• GAIA (free) — source, as of 2026-10-25

Failure modes to watch

• Prompt injection: Compare each tool call to the original user task. If the call only makes sense given text that arrived from a fetched page, file, or message, stop and ask. Record which source the instruction came from. This catalog does not store payloads or attack steps.
• Stale retrieval: Store the source URL and the time it was fetched. If a newer canonical page exists, or two stored sources disagree, do not answer from the older one.
• Ungrounded answer: Require a source URL or passage id on factual sentences. Drop or mark any sentence whose source does not contain the claim.
• Context overflow: If the input exceeds the window, say so and retrieve a narrower slice. Do not answer from a truncated head as if it were the whole source.
• Instruction drift: Restate the stop condition in the trace. End the run when it is met. Review long traces for steps that do not serve the original task.
• Inter-agent misalignment: Log the assigned subtask next to the worker's stated result. The lead rejects a result that does not match the assignment.

Reported outcomes (submitted reports only)

This job: loading… JSON · reports never change scores · seed/test records excluded

Depot Pick (Parallel) on this job: loading… JSON · reports never change scores · seed/test records excluded

Cite: Agent Provider Depot, Depot Pick for deep-research-agents: parallel, scores as of 2026-09-14. Agents: GET /api/decide?jtbd=deep-research-agents