Peter Wilson & Davide Eynard - cq - Stack Overflow for Agents - AI Native DevCon June 2026
Summary
The session introduces CQ (Mozilla.ai's proposal), a system designed as a 'Stack Overflow for agents.' Its core purpose is to standardize and share knowledge units (KUs) across autonomous AI agents—locally, within an organization, or publicly. This prevents agents from repeating mistakes, wasting tokens, and ensures that lessons learned by one agent can benefit all others, thereby improving the reliability of complex automated workflows.
Key takeaways
-
Knowledge Unit (KU) Standardization
17:09
A KU is a standardized knowledge artifact (stored in JSON format) capturing solutions to novel problems. It includes domains, insights, actions taken, summaries, and metadata (languages/frameworks).
-
Agentic Context Management
6:15
Effective agent performance relies heavily on context injection. The system aims to move beyond simple memory files by allowing agents to query a centralized knowledge base for relevant solutions before starting a task.
-
Layered Sharing Model
20:40
CQ supports three levels of knowledge sharing: local (SQLite database, no review), private/team (requires user authentication and human-in-the-loop review), and public commons (CQ Exchange).
Technical details
-
Knowledge Unit Schema
1035s
KUs are structured to capture problem context, including domains, insights, actions taken, summary, and metadata regarding languages and frameworks. This standardized format is key for cross-agent knowledge transfer.
-
CQ Workflow (Remote Mode)
1065s
When an agent encounters a novel issue, it proposes a KU to the CQ server. The proposal must undergo Human-in-the-Loop review before becoming available for querying by other agents via a dedicated skill plugin.
-
Security and Mitigation
1320s
To mitigate risks (e.g., PII leakage, identity spoofing), proposed defenses include OAuth stride, cryptographic signing of KUs, layered guardrails pipelines, and mandatory human review.
Mentioned resources
- CQ Exchange
- Mozilla AI Open Source CQ Repo
Channel & topics
Watch on YouTube · Back to latest
This independent, AI-assisted summary is provided for commentary and informational purposes. It may contain errors or omit important context. Please watch the original video for the creator's complete presentation. Video, thumbnail, and related copyrights belong to their respective owners.
