Communityagentscontext engineeringsecurity riskthoughtworks
AI Agents Tempt Developers, Increase Review Burden
6.1
Birgitta Böckeler, Thoughtworks' global lead for AI-assisted software delivery, told attendees at QCon London this week that AI agents and context engineering are making tools too useful to ignore but risk pulling developers out of the loop. She highlighted sub-agents, agent teams, rising costs, and security threats like malware and data extraction, urging context/harness engineering and ongoing review to manage risk.
Key Points
- 1Warns that AI agents and context engineering reduce hands-on supervision while increasing error and security risks.
- 2Explains that sub-agents and agent teams improve scale but complicate orchestration and cost management.
- 3Advises developers to adopt context/harness engineering and continuous review to mitigate leakage and malware.
Scoring Rationale
Timely conference insight from a reputable Thoughtworks lead; single-source commentary limits novelty and broad empirical validation.
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
