Research
Everything Intel keeps, in one place — every brief we run, every department, readers' own, and every finding behind them. Browse below, or see the same body of work as a connected graph on the live map.
All coverage
Everything Intel has read, newest first. Each title opens at its original publisher.
- MCP & Interop✓ verified
24,008 secrets found in public MCP config files — 2,117 of them still live
The convenience of pasting a key into an MCP config is exactly how it leaks — keep secrets out of tool configs, and read a tool's description as untrusted input, not just documentation.
- Research✓ verified
Agentic Context Engineering (evolving contexts for self-improving LMs)
The academic framing of what the substrate-batch + landscape-brief + KB-principle loop does informally. Indexed via a curated list — read the underlying papers before teaching specifics.
- Agent Frameworks & Orchestration✓ verified
Four ways to orchestrate agents just quietly became the standard menu
Four orchestration styles stabilizing means picking a framework is now a real architecture decision, not a bet on which project survives — match your agent's actual coordination problem (graph, role, handoff, or hierarchical) before committing to one.
- Dev Tooling & Infra✓ verified
'ClawHavoc': 900+ malicious agent 'skills' pushed through a third-party marketplace
Any skill, tool, or config you didn't write deserves the same scrutiny as a code dependency — and 'delete the skill' is not the same as 'undo what it did.'
- MCP & Interop✓ verified
MCP now spoken natively by every major host; 500+ public servers
Confirms MCP as the durable interop bet for Intel's agent-facing side — "serve our KB over MCP" reaches every major client without per-client integration.
- Agent Frameworks & Orchestration✓ verified
OWASP's agentic security Top 10 turns 'excessive agency' into a least-agency discipline
If your product lets an agent take actions, this is the checklist to threat-model against: give it the least autonomy the job needs, gate the state-changing steps behind a human, and cap how long it can loop.
- AI in Education✓ verified
UK LearnLM classroom RCT — independent corroboration
A second independent RCT with transfer-to-novel-problems as the outcome — the hard test — strengthening the evidence base beyond a single study or vendor.
- AI in Education✓ verified
AI tutoring keeps beating active learning in RCTs
The empirical floor under AI Uni's whole pedagogical thesis — structured AI tutoring over traditional pedagogy. Verify specific effect-size figures against the primary before re-quoting.