MIT-led researchers analyze 67 deployed agentic AI systems and find widespread gaps in safety disclosure. Around 70% provide documentation and nearly half publish code, but only about 19% disclose formal safety policies and fewer than 10% report external safety evaluations. The authors warn that as agents gain autonomy and handle emails, files and transactions, public transparency about testing and guardrails has not kept pace.
Key Points
- 1Catalogs 67 deployed agentic systems, finds only ~19% disclose formal safety policies
- 2Highlights imbalance: 70% document capabilities while under 10% report external evaluations
- 3Warns practitioners to expect limited public safety testing when integrating agents into workflows
Scoring Rationale
Strong empirical evidence of industry-wide transparency gaps, but study is observational and lacks prescriptive remediation steps.
Sources
Public references used for this report.
Practice interview problems based on real data
1,625 SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems
