Guide contents
A chain of 5 prompts: checking information on the Internet
Open intelligence (OSINT) is first and foremost a process: it is important to know what to ask, in what sequence, and how to verify what is received.
This guide is available to AI-Base subscribers
Get full access to this practical guide, ready-made configurations and terminal scripts.
Related Ecosystem Resources
Explore practical workflows, core terminology, and engineering tools
Hermes Profile: OSINT Researcher & Deep Web Intelligence
Hermes open-source intelligence (OSINT) profile: multi-hop web investigation, primary source verification, competitive intelligence, and citation-backed synthesis.
5-Prompt Chain: Internet Verification and OSINT Investigations
A step-by-step 5-prompt OSINT methodology for online fact-checking and verification: scoping, email audits, username pivots, source corroboration, and report synthesis.
Monte Carlo Tree Search for Agents (MCTS)
An algorithmic approach to AI agent action planning that combines heuristic search, intermediate state evaluation, and backtracking to find optimal solutions in high-complexity spaces.
Verification Discipline
A fundamental engineering principle stating that any output generated by artificial intelligence is treated as an unverified hypothesis requiring empirical validation before acceptance.
Service estimates the risk of being banned by Anthropic
Chinese developers launched a tool that analyzes IP address, country, ISP, connection type, DNS and WebRTC leaks to score trust from 0 to 100 for Anthropic-related access.
Claude Code cuts background subagent status update costs by 99%
In the CLI version of Claude Code, status updates for background subagents now use Haiku 5.5 based on short notes, reducing limit consumption.