Skip to content
Longterm Wiki
Back

FutureSearch Research Publications

web
futuresearch.ai·futuresearch.ai/research/

FutureSearch uses AI-assisted forecasting to analyze AI development trajectories; their publications may be useful for those researching AI timelines, risk estimation, and evidence-based safety planning, though content could not be directly verified from the provided metadata.

Metadata

Importance: 42/100homepage

Summary

FutureSearch is an AI-assisted forecasting and research organization that publishes work on predicting future developments, including AI timelines and safety-relevant forecasts. Their research applies probabilistic reasoning and superforecasting techniques to questions of technological and societal change. The publications page aggregates their outputs relevant to AI risk and futures analysis.

Key Points

  • Applies superforecasting and probabilistic methods to AI timelines and safety-relevant future scenarios
  • Produces research on questions like transformative AI arrival dates and associated risks
  • Bridges forecasting methodology with AI safety considerations to inform planning and policy
  • Outputs are intended to support evidence-based reasoning about long-term AI trajectories

Cited by 1 page

PageTypeQuality
FutureSearchOrganization50.0

Cached Content Preview

HTTP 200Fetched Apr 9, 20262 KB
Research | FutureSearch FutureSearch Agent

 Research, then analyze

 An agent researches each row on the web, then analyzes what it finds. Add columns of data you don't have yet.

 Try Research free Give to your AI ▶ 2-min demo video coming soon

 1–11¢ per row accuracy verified in Deep Research Bench 💰 company → annual_price, tier_name

 Enrich SaaS Pricing

 Research pricing pages for hundreds of products. Extract tier names, annual prices, and feature lists as structured columns.

 $6.68 • 99.6% success • 246 products

 Tutorial → Try it → 🏷️ job_title → category, seniority

 Classify Job Postings

 Add category, seniority level, and confidence columns to job listings using LLM classification.

 $1.74 • 100% success • 200 postings

 Tutorial → Try it → 📦 package → days_since_release, contributors

 Research Package Metadata

 Look up days since last release, contributor counts, and other metrics for PyPI packages from the web.

 $3.90 • 1.3¢/row • 300 packages

 Tutorial → Try it → Give your AI a team of agents

 Claude Code

 claude mcp add futuresearch --scope project --transport http https://mcp.futuresearch.ai/mcp

Then ask Claude to research your data. Agent setup guide → Python SDK

 pip install futuresearch

from futuresearch.ops import agent_map
result = await agent_map(
 task="Find the annual price
 of the lowest paid tier",
 input=products_df,
 response_model=PricingInfo
) Get API key → Docs → Pricing

 Start with $20 in free credits . No credit card required. Pay only for what you use—costs scale with research complexity.

 Task Rows Cost/row Success SaaS pricing lookup 246 2.7¢ 99.6% Job classification 200 0.9¢ 100% Package metadata 300 1.3¢ — Why costs vary

 Every row gets its own web research agent. Agents have degrees of freedom. They spend more tokens doing more research for harder tasks. Simple lookups finish quickly; complex research requires multiple page visits and reasoning steps.

 Resources

 Tutorials

 • SaaS pricing enrichment 
 • Classify with LLMs 
 • Research external metrics 
 SDK Docs

 • agent_map() reference 
 • Add a Column with Web Lookup 
 • Classify and Label Data with an LLM 
 Case Studies

 • Agent map regulatory status 
 • LLM web research agents at scale
Resource ID: 8330d6cca4a886c9 | Stable ID: sid_HlIQ1JBAd8