Competitive intelligence on demand

Monitor competitors, markets, and signals — programmatically.

For

B2B sales tools, market research platforms, VC ops, growth teams — anyone whose product needs to know what is happening in a specific industry vertical right now.

The pain

Without a real retrieval layer.

Manual competitor monitoring is a part-time job no one wants. Google Alerts is unreliable and ad-polluted. Building your own crawler is six months of work just to start. Most "monitoring" SaaS charge per-keyword and lock data into their UI.

With SiftQ

One call, the right shape.

A scheduled SiftQ query gives you fresh, structured signal about a competitor or market on whatever cadence you want. Hand the results to an LLM for change-detection and you have a fully automated brief that drops into Slack every morning.

Recommended config

Start with this shape.

scopenews + webpage

size20

optionsincludeRawContent=true on confirmed leads only · Schedule daily or hourly

Working code

Paste, run, ship.

Python — Daily competitor brief

import os, requests, anthropic
from datetime import datetime

claude = anthropic.Anthropic()
HEADERS = {"Authorization": f"Bearer {os.environ['SIFTQ_API_KEY']}"}

COMPETITORS = ["Acme Robotics", "Beta Industries", "Gamma Labs"]

def fresh_news(company: str) -> list[dict]:
    r = requests.post(
        "https://api.siftq.com/v1/search",
        headers=HEADERS,
        json={
            "q": f'"{company}" announcement OR launch OR funding OR hire',
            "scope": "news",
            "size": "15",
            "conciseSnippet": True,
        },
        timeout=15,
    )
    return [h for h in r.json().get("webpages", []) if h.get("date")]

def brief(company: str) -> str:
    items = fresh_news(company)
    if not items:
        return f"## {company}\n_No notable news in the last cycle._"
    feed = "\n".join(f"- {h['date']}: {h['title']} — {h['link']}" for h in items)
    summary = claude.messages.create(
        model="claude-sonnet-4-6", max_tokens=400,
        messages=[{
            "role": "user",
            "content": f"3 bullets summarizing what {company} did this week:\n\n{feed}",
        }],
    ).content[0].text
    return f"## {company}\n{summary}\n\n<details>{feed}</details>"

print(f"# Competitor Brief — {datetime.now():%Y-%m-%d}\n")
for c in COMPETITORS:
    print(brief(c), "\n")

Why SiftQ for this