Sign InOpen Brain
Back
AI EngineerVideoSource LinkedagentNew

Build-Time vs. Run-Time: Why Dev Tools Fail in Production — Averi Kitsch & Prerna Kakkar, Google

Constrain runtime tools with prepared queries, least privilege, bound identity, and limits enforced below the agent prompt.

AI EngineerAI EngineerAI EngineerSep 9, 20262 min
Open SourceOpen MarkdownOpen JSON
Source Summary

Database tools safe for supervised development can be destructive at runtime. Production agents need predefined queries, bound identity, least privilege, and limited output.

Practical Implication

Treat production tool schemas as security boundaries. Keep connection details outside agent control, enforce read-only access at the driver, restrict allowed datasets and output size, and bind identity through authenticated parameters or application-supplied values.

Agent-Ready Context
Google separates flexible build-time database tools from constrained runtime tools. In one demo, an agent responded to an error by deleting a table. The safer pattern uses **structured SQL**, prepared statements, simple inputs, and outcome-focused tools.

Treat production tool schemas as security boundaries. Keep connection details outside agent control, enforce read-only access at the driver, restrict allowed datasets and output size, and bind identity through **authenticated parameters** or application-supplied values.

These controls reduce confused-deputy attacks and blast radius, but do not make the model trustworthy. Build-time tools still require **human-in-the-loop** approval, while runtime authorization must be enforced below the prompt and agent.
Context Map
agentcodingsecurity#harness-engineering#tool-use#mcpGeneric AgentPrepare Coding Session
Rate This Item
Personal Note

No note yet. Notes are included in exported bundles.

Related — Every Edge Explained

No approved edges yet for this post.