Research

Research the company ____ and its 2026 outlook. Provide a brief overview
of the company, its products, services, and market position.

Conduct a competitive analysis of ____ in 2026. Identify their main
competitors, compare market positioning, and analyze key differentiators.

We're evaluating Notion as a potential partner. We already know they
primarily serve SMB and mid-market teams, expanded their AI features
significantly in 2025, and most often compete with Confluence and ClickUp.
Research Notion's 2026 outlook, including market position, growth risks,
and where a partnership could be most valuable. Include citations.

result = client.research(
    input="Analyze the competitive landscape for ____ in the SMB market, "
          "including key competitors, positioning, pricing models, customer "
          "segments, recent product moves, and defensible advantages or risks "
          "over the next 2-3 years.",
    model="pro"
)

result = client.research(
    input="What are the top 5 competitors to ____ in the SMB market, and how do they differentiate?",
    model="mini"
)

import time
from tavily import TavilyClient

client = TavilyClient()

# Step 1: Start research task
result = client.research(
    input="Latest developments in quantum computing and their practical applications",
    model="pro"
)
request_id = result["request_id"]

# Step 2: Poll until completed
response = client.get_research(request_id)
while response["status"] not in ["completed", "failed"]:
    print(f"Status: {response['status']}... polling again in 10 seconds")
    time.sleep(10)
    response = client.get_research(request_id)

# Step 3: Handle result
if response["status"] == "failed":
    raise RuntimeError(f"Research failed: {response.get('error', 'Unknown error')}")

report = response["content"]
sources = response["sources"]

stream = client.research(
    input="Latest developments in quantum computing",
    model="pro",
    stream=True
)

for chunk in stream:
    print(chunk.decode('utf-8'))

schema = {
    "properties": {
        "summary": {
            "type": "string",
            "description": "Executive summary of findings"
        },
        "key_points": {
            "type": "array",
            "items": {"type": "string"},
            "description": "Main takeaways from the research"
        },
        "metrics": {
            "type": "object",
            "properties": {
                "market_size": {"type": "string", "description": "Total market size"},
                "growth_rate": {"type": "number", "description": "Annual growth percentage"}
            }
        }
    },
    "required": ["summary", "key_points"]
}

result = client.research(
    input="Electric vehicle market analysis 2024",
    output_schema=schema
)

stream = client.research(
    input="AI agent frameworks comparison",
    model="mini",
    stream=True,
    output_schema={
        "properties": {
            "summary": {"type": "string", "description": "Executive summary"},
            "key_points": {"type": "array", "items": {"type": "string"}}
        },
        "required": ["summary", "key_points"]
    }
)

for chunk in stream:
    data = chunk.decode('utf-8')
    print(data)  # Content chunks will be structured JSON