EdTech Research Agent

EdTech is a $300B+ global market where product claims outrun evidence, regulation (FERPA, COPPA, CIPA) is non-negotiable, and procurement runs through districts, ESSER funds, and Title I budgets. This guide builds a Python agent for EdTech investors, startup founders, district curriculum directors, learning scientists, and instructional designers. It chains all four Superhighway endpoints — /research for the market landscape, /search against EdTech industry and research sources, /scrape for a specific product profile or research brief, and /news for funding and procurement activity — then uses an LLM to emit a structured market brief as JSON.

Overview

The agent takes a product or market segment — "adaptive math learning platform K-12", "AI writing tutor higher education" — and produces a structured EdTech market brief:

• Synthesizes the market: size estimates, growth trajectory, key players, funding trends, adoption patterns, learning efficacy evidence, and the regulatory landscape
• Searches EdTech industry sources — EdSurge (news and product reviews), Crunchbase (funding), ISTE (ed-tech standards)
• Searches research evidence — peer-reviewed studies, efficacy data, and adoption reports from RAND, the Gates Foundation, What Works Clearinghouse, and IES
• Scrapes one relevant page: an EdSurge product profile, a district RFP, or a research brief
• Pulls recent news: funding rounds, district procurement decisions, policy changes (ESSER, Title I/II), product launches, and acquisitions
• Uses an LLM to generate a structured brief — segment, evidence base, learning outcomes claimed, regulatory considerations, procurement landscape, deployment contexts, and funding activity as JSON

Who it's for: EdTech investors and analysts, startup founders, district curriculum directors and procurement leads, learning scientists, and instructional designers.

How it works

Five endpoint calls feed one LLM synthesis:

1. /research — deep synthesis of the market: size, growth, key players, funding trends, adoption patterns, learning efficacy evidence, regulatory landscape.
2. /search (industry sources) — EdTech news, reviews, and funding scoped to EdSurge, Crunchbase, and ISTE.
3. /search (research evidence, time=year) — peer-reviewed studies, efficacy data, and adoption reports from research bodies.
4. /scrape — one relevant URL, e.g. an EdSurge product profile, a district RFP, or a research brief.
5. /news (time=month) — recent funding rounds, district procurement decisions, policy changes, product launches, and acquisitions.

Full example

pip install openai requests python-dotenv

Create a .env file with your two keys:

SUPERHIGHWAY_API_KEY=your_key_here
OPENAI_API_KEY=your_key_here

import requests, os, json
from openai import OpenAI

SUPERHIGHWAY_KEY = os.getenv("SUPERHIGHWAY_API_KEY")
BASE = "https://superhighway.walls.sh"
HEADERS = {"Authorization": f"Bearer {SUPERHIGHWAY_KEY}"}

llm = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))

NOTE = (
    "EdTech product claims vary widely in research support. Verify efficacy "
    "evidence independently through What Works Clearinghouse (ies.ed.gov/ncee/wwc) "
    "and RAND Education research before procurement decisions."
)

# 1. Deep synthesis of the EdTech market landscape
def research_market(query: str) -> str:
    """Market size, key players, funding trends, adoption, efficacy, regulation."""
    r = requests.get(
        f"{BASE}/research",
        params={"q": f"{query} education technology market"},
        headers=HEADERS,
    )
    data = r.json()
    return data.get("summary", "")[:3000]

# 2. EdTech industry sources: EdSurge, Crunchbase, ISTE
def search_industry(query: str) -> list[dict]:
    """Product reviews (EdSurge), funding (Crunchbase), standards (ISTE)."""
    r = requests.get(
        f"{BASE}/search",
        params={
            "q": f"{query} edtech startup funding product review "
                 f"site:edsurge.com OR site:crunchbase.com OR site:iste.org",
        },
        headers=HEADERS,
    )
    return r.json().get("results", [])

# 3. Research evidence: efficacy studies, adoption reports (last year)
def search_evidence(query: str) -> list[dict]:
    """Peer-reviewed studies, efficacy data from RAND, Gates, WWC, IES."""
    r = requests.get(
        f"{BASE}/search",
        params={
            "q": f"{query} education technology research evidence classroom efficacy",
            "time": "year",
        },
        headers=HEADERS,
    )
    return r.json().get("results", [])

# 4. Scrape one relevant product profile / RFP / research brief
def scrape_page(url: str) -> dict:
    """Pull an EdSurge product profile, a district RFP, or a research brief."""
    r = requests.post(
        f"{BASE}/scrape",
        json={"url": url, "mode": "markdown"},
        headers=HEADERS,
    )
    data = r.json()
    return {
        "url": url,
        "title": data.get("title", ""),
        "content": data.get("markdown", data.get("text", ""))[:2500],
    }

# 5. Recent edtech news: funding, procurement, policy (last month)
def get_news(query: str) -> list[dict]:
    """Funding rounds, district procurement, policy changes, launches, M&A."""
    r = requests.get(
        f"{BASE}/news",
        params={
            "q": f"{query} edtech education technology school district",
            "time": "month",
        },
        headers=HEADERS,
    )
    return r.json().get("results", [])

def generate_brief(
    query: str,
    market: str,
    industry: list[dict],
    evidence: list[dict],
    scraped: dict | None,
    news: list[dict],
) -> dict | None:
    """Generate a structured EdTech market brief as JSON."""

    industry_text = "\n".join(
        f"- {r.get('title', '')}: {r.get('snippet', '')} ({r.get('url', '')})"
        for r in industry[:6]
    )
    evidence_text = "\n".join(
        f"- {r.get('title', '')}: {r.get('snippet', '')}"
        for r in evidence[:6]
    )
    news_text = "\n".join(
        f"- {n.get('title', '')}: {n.get('snippet', '')}"
        for n in news[:6]
    )
    scraped_text = ""
    if scraped and scraped.get("content"):
        scraped_text = f"{scraped['title']}\n{scraped['content']}"

    response = llm.chat.completions.create(
        model="gpt-4o-mini",
        messages=[
            {
                "role": "system",
                "content": (
                    "You are an EdTech market and competitive analyst. Use ONLY the "
                    "provided sources. Do not invent company names, funding figures, "
                    "study results, or efficacy claims — if a detail is not in the "
                    "sources, say 'not found in sources.' This is market research, NOT "
                    "instructional design advice or legal compliance guidance. Be "
                    "precise about the strength of the evidence base and always remind "
                    "the reader to verify efficacy and student-data-privacy compliance."
                ),
            },
            {
                "role": "user",
                "content": f"""Write an EdTech market brief for: {query}

Market Landscape (synthesis):
{market}

EdTech Industry Sources (EdSurge / Crunchbase / ISTE):
{industry_text}

Research Evidence (studies, efficacy, adoption reports):
{evidence_text}

Scraped Product / RFP / Research Page:
{scraped_text}

Recent EdTech News:
{news_text}

Return JSON with ALL of these fields:
- product_or_market_segment: what's being researched (product name or market category)
- market_segment: "K-12" | "higher-ed" | "corporate-learning" | "early-childhood" | "professional-development" | "mixed"
- market_overview: market size estimate, growth trajectory, key trends driving adoption
- key_players: list of leading companies/products in this space
- evidence_base: strength of research evidence — "strong" | "moderate" | "emerging" | "limited" | "not-established"; summary of key studies or lack thereof
- learning_outcomes_claimed: what the product/category claims to improve (reading scores, engagement, retention, etc.)
- regulatory_considerations: FERPA (student data privacy), COPPA (under-13 data), CIPA (school internet safety), state-specific laws, student data privacy pledges
- procurement_landscape: how schools/districts buy (RFP process, per-seat pricing, Title I eligibility, ESSER fund eligibility, pilot programs)
- deployment_contexts: classroom, blended learning, 1:1 device programs, LMS integration requirements (Canvas, Schoology, Google Classroom, Clever SSO)
- funding_activity: recent funding rounds, acquisitions, or notable investors in this space
- competitive_differentiators: what distinguishes leaders (AI features, content library, assessment integration, teacher PD)
- data_quality: "high" | "medium" | "low" — based on how well sources covered EdSurge/research/district procurement
- note: always exactly the note string provided below""",
            },
        ],
        response_format={"type": "json_object"},
    )

    try:
        brief = json.loads(response.choices[0].message.content)
        brief["note"] = NOTE
        return brief
    except (json.JSONDecodeError, KeyError):
        return None

def research_edtech(query: str) -> dict | None:
    """Run the full EdTech market research pipeline."""
    print(f"Researching EdTech market: {query}")

    print("Synthesizing market landscape...")
    market = research_market(query)

    print("Searching EdTech industry sources...")
    industry = search_industry(query)

    print("Searching research evidence...")
    evidence = search_evidence(query)

    print("Scraping a relevant product/RFP/research page...")
    scraped = None
    for result in industry + evidence:
        url = result.get("url")
        if url and ("edsurge.com" in url or "iste.org" in url or "rand.org" in url
                    or "ed.gov" in url):
            scraped = scrape_page(url)
            if scraped.get("content"):
                break

    print("Pulling recent edtech news...")
    news = get_news(query)

    print("Generating market brief...")
    return generate_brief(query, market, industry, evidence, scraped, news)

def print_brief(brief: dict):
    if not brief:
        print("Could not generate brief.")
        return
    print(f"\n{'='*60}")
    print(f"EdTech Market Brief")
    print(f"{'='*60}")
    print(f"\nProduct / Segment: {brief.get('product_or_market_segment', '')}")
    print(f"Market Segment: {brief.get('market_segment', '')}")
    print(f"\nMarket Overview:\n{brief.get('market_overview', '')}")
    print(f"\nKey Players: {', '.join(brief.get('key_players', []))}")
    print(f"\nEvidence Base:\n{brief.get('evidence_base', '')}")
    print(f"\nLearning Outcomes Claimed:\n{brief.get('learning_outcomes_claimed', '')}")
    print(f"\nRegulatory Considerations:\n{brief.get('regulatory_considerations', '')}")
    print(f"\nProcurement Landscape:\n{brief.get('procurement_landscape', '')}")
    print(f"\nDeployment Contexts:\n{brief.get('deployment_contexts', '')}")
    print(f"\nFunding Activity:\n{brief.get('funding_activity', '')}")
    print(f"\nCompetitive Differentiators:\n{brief.get('competitive_differentiators', '')}")
    print(f"\nData Quality: {brief.get('data_quality', '?')}")
    print(f"\n{brief.get('note', '')}")

if __name__ == "__main__":
    import sys
    query = sys.argv[1] if len(sys.argv) > 1 else "adaptive math learning platform K-12"
    brief = research_edtech(query)
    print_brief(brief)

Usage examples

• "adaptive math learning platform K-12" — maps the adaptive-math landscape (DreamBox, Khan Academy, IXL, Zearn), summarizes the evidence base for adaptive learning, and surfaces ESSER-eligible pricing and Title I procurement paths.
• "AI writing tutor higher education" — AI writing-assistant tools for colleges, the (still emerging) evidence on AI tutoring efficacy, FERPA implications for tools that store student work, and LMS integration patterns (Canvas, Blackboard).
• "professional development platform corporate learning" — the L&D and skills-based learning market, evidence on microlearning efficacy, and LMS/LXP integration requirements for enterprise deployments.

Getting your API key

Grab a free Superhighway key at /pricing (1,000 calls/month, no credit card). For an agent that provisions its own access, skip the key entirely with x402: it pays $0.002 per call in USDC on Base — no signup, no key management. See the x402 pay-per-call guide for the wallet setup.

See also

The brand monitoring agent applies the same multi-endpoint pattern to tracking mentions and sentiment, and the content research agent covers the deep-research synthesis pattern in more depth.