Real Agent Cases

Get a quick sourced briefing on a local wildlife species with Grok DeepSearch

Posted
by Bijin Jose (Indian Express)
Last checked
Method:
How we verify

Evidence: Article or interviewA newsletter, journalist or interview account of what happened.

Context: In a comparison test: from a head-to-head chatbot review, not a standalone agent test.

Outcome

Indian Express's reviewer asked Grok 3 DeepSearch about the state of the house sparrow in India; he reports it scoured 101 sources in 46 seconds before presenting its findings.

Poster says:101 sources in 46 seconds

This is the source's own number. We haven't measured it.

Agent

Grok DeepSearch

Prompt Original prompt

Exact prompt as published in the source.

What is the state of the species House Sparrow in India?
Optional stronger version

Our rewrite with extra checks. The poster didn't test it.

Before you start, ask me 1–3 short questions about the details below and wait for my answers. Once I've answered, confirm the plan in one line and run the whole task start to finish.

Goal: Get a fast, sourced overview of how a species is doing where I live.

Quick-check questions: Which species and region, and what do you want to know most (numbers, causes, what helps)?

What I need from you:
- Species and region
- What you'll use it for (school, a talk, curiosity)

Rules:
- Prefer surveys, conservation groups and research papers over blogs.
- Give population trend, main threats and what's being done, each with a source link.
- Say how recent each figure is and flag disagreements between sources.
- Keep it to one page.
- End with 3 things an ordinary person can do to help, each with a source.

Output: A one-page briefing with headings and a source list.

If my answers leave a gap, make a sensible choice, say what you assumed, and keep going.

You'll know it worked when: every key claim has a link and a date.

Source

https://indianexpress.com/article/technology/artificial-intelligence/grok-3-review-elon-musk-chatgpt-ai-model-9848064/

Related cases

  • Find links to content with Project Mariner (no links returned)Improved promptEvidence: Described by posterFailure

    Asked to find links to content, Project Mariner found the content but wouldn't return the links, which the poster said made the result not very helpful.

    Project Mariner · Research · Source date:

  • Run async code-research benchmarks with a coding agentEvidence: Screenshots or logs

    An async coding agent cloned several Python Markdown libraries, benchmarked them against cmarkgfm, and wrote a report with charts, with almost no human time spent.

    Claude Code for web, OpenAI Codex · Research · Source date:

  • Report global NAND market share with Gemini Deep ResearchImproved promptEvidence: Screenshots or logsFailure

    Asked for a simple report on global NAND market share, Gemini Deep Research returned figures the poster called an incredible failure when compared with Sandisk's investor-day slide and Claude's answer to the same query.

    Gemini Deep Research · Research · Source date: