Deep Research
Research topic: $ARGUMENTS
When to use (vs parallel-web-search)
ONLY use this skill when the user explicitly requests deep/exhaustive research. Deep research is 10-100x slower and more expensive than parallel-web-search. For normal "research X" requests, quick lookups, or fact-checking, use parallel-web-search instead.
Step 1: Start the research
bash
parallel-cli research run "$ARGUMENTS" --processor pro-fast --no-wait --json
This returns instantly. Do NOT omit
— without it the command blocks for minutes and will time out.
Processor options (choose based on user request):
| Processor | Expected latency | Use when |
|---|
| 30s – 5 min | Default — good balance of depth and speed |
| 1 – 10 min | Deeper analysis, more sources (~2x cost) |
| 5 – 25 min | Maximum depth, only when explicitly requested (~3x cost) |
Parse the JSON output to extract the
and monitoring URL. Immediately tell the user:
- Deep research has been kicked off
- The expected latency for the processor tier chosen (from the table above)
- The monitoring URL where they can track progress
Tell them they can background the polling step to continue working while it runs.
Step 2: Poll for results
Choose a descriptive filename based on the topic (e.g.,
,
). Use lowercase with hyphens, no spaces.
bash
parallel-cli research poll "$RUN_ID" -o "$FILENAME" --timeout 540
Important:
- Use (9 minutes) to stay within tool execution limits
- Do NOT pass — the full output is large and will flood context. The flag writes results to files instead.
- The flag generates two output files:
- — metadata and basis
- — formatted markdown report
If the poll times out
Higher processor tiers can take longer than 9 minutes. If the poll exits without completing:
- Tell the user the research is still running server-side
- Re-run the same
parallel-cli research poll
Response format
After step 1: Share the monitoring URL (for tracking progress only — it is not the final report).
After step 2: Tell the user the two generated file paths:
- — formatted markdown report
- — metadata and basis
Do NOT re-share the monitoring URL after completion — the results are in the files, not at that link.
Ask the user if they would like to read through the files now. Do NOT read the file contents into context unless the user asks.
Setup
If
is not found, install and authenticate:
bash
curl -fsSL https://parallel.ai/install.sh | bash
parallel-cli login
Or set an API key:
export PARALLEL_API_KEY="your-key"