Field notes on agentic systems.

Selected reading on reliability, security and system architecture, with the engineering question each item raises. Dates and source types stay visible so you can judge what applies to your work.

A stone specimen board with five small woven pieces, each pinned down and tied to its own blank tag, with room left for more.

Reliability and evaluation

Treat control-context compression as a behaviour change

Research preprint · 2 August 2026

The authors of Control Under Compression evaluate compressed system prompts through executable agent outcomes. Their results vary by context and compression method. For your system, the useful question is which tool behaviour changes when those prompts are shortened.

Read the research

Examine what happens at the compaction boundary

Research preprint · first submitted 6 August 2026; revised 14 October 2026

Min and colleagues study execution instability after repeated context compression. Their TRACE approach evaluates compaction through paired continuations. This is early empirical evidence; it suggests testing the behaviour following compaction rather than judging only the quality of a summary.

Read the research

Security and evidence

Include poisoned data in the threat model

Research preprint · July 2026

The authors of Agent Data Injection Attacks are Realistic Threats to AI Agents examine attacks on the data an agent uses. The review question is how your system checks retrieved facts before an action depends on them.

Read the paper

Check the authority behind consequential actions

Vendor security research · Zscaler ThreatLabz

ThreatLabz describes indirect prompt injection in web content aimed at AI agents. Its sandboxed test conditions matter when interpreting the results. For a design review, examine tool permissions, spending boundaries and approval for consequential actions alongside the model prompt.

Read the research and test conditions

Protocol and deployment

Read the MCP specification and migration guidance together

Official project publications · 2026-07-28 specification

The Model Context Protocol project describes changes to its protocol and SDKs. Review the version your client and server actually negotiate, the migration requirements and the effect on your deployment architecture. Check the current project guidance before applying a change.

Read the specification announcement · Read the SDK guidance

Explore more resources