<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>AI Automation Engineering</title><link>https://aiautomationengineering.com</link><description>Practical engineering for useful AI systems. Technical tutorials, working examples, and considered approaches to automation.</description><language>en-US</language><item><title>Build Retrieval That Can Explain Its Sources</title><link>https://aiautomationengineering.com/journal/retrieval-with-source-provenance/</link><guid>https://aiautomationengineering.com/journal/retrieval-with-source-provenance/</guid><description>Design retrieval around authorized evidence, stable document revisions, useful context, and claim-level provenance instead of a larger context window.</description><pubDate>Sat, 19 Sep 2026 00:00:00 GMT</pubDate></item><item><title>Choose a Workflow Before You Choose an Agent</title><link>https://aiautomationengineering.com/journal/choosing-workflows-and-agents/</link><guid>https://aiautomationengineering.com/journal/choosing-workflows-and-agents/</guid><description>Match autonomy to the actual uncertainty in a task, with a practical decision process for workflows, bounded agents, and human escalation.</description><pubDate>Sat, 19 Sep 2026 00:00:00 GMT</pubDate></item><item><title>Design Tool Contracts an Agent Can Use Correctly</title><link>https://aiautomationengineering.com/journal/designing-tool-contracts/</link><guid>https://aiautomationengineering.com/journal/designing-tool-contracts/</guid><description>Make tools discoverable, narrow, and recoverable with explicit schemas, authorization boundaries, useful results, and honest failure semantics.</description><pubDate>Sat, 19 Sep 2026 00:00:00 GMT</pubDate></item><item><title>Deterministic Patterns for Agentic Applications: A Practical Guide</title><link>https://aiautomationengineering.com/journal/deterministic-patterns-agentic-applications/</link><guid>https://aiautomationengineering.com/journal/deterministic-patterns-agentic-applications/</guid><description>Build reliable agent systems with validated proposals, pure state transitions, durable observations, scoped approvals, and transactional execution intents.</description><pubDate>Sat, 19 Sep 2026 00:00:00 GMT</pubDate></item><item><title>Make Retries Safe Before You Automate More</title><link>https://aiautomationengineering.com/journal/make-retries-safe/</link><guid>https://aiautomationengineering.com/journal/make-retries-safe/</guid><description>Design operation identities, retry budgets, and reconciliation paths that prevent an interrupted request from becoming duplicate work.</description><pubDate>Sat, 19 Sep 2026 00:00:00 GMT</pubDate></item><item><title>Observe Agent Runs and Enforce Useful Budgets</title><link>https://aiautomationengineering.com/journal/observing-agent-cost-and-latency/</link><guid>https://aiautomationengineering.com/journal/observing-agent-cost-and-latency/</guid><description>Trace the complete task, separate waiting from work, and enforce cost and latency limits without losing track of uncertain side effects.</description><pubDate>Sat, 19 Sep 2026 00:00:00 GMT</pubDate></item><item><title>Put Approval at the Point of Commitment</title><link>https://aiautomationengineering.com/journal/approval-at-the-point-of-commitment/</link><guid>https://aiautomationengineering.com/journal/approval-at-the-point-of-commitment/</guid><description>Bind human approval to a concrete action, authenticated identity, and resource version so execution still matches what was reviewed.</description><pubDate>Sat, 19 Sep 2026 00:00:00 GMT</pubDate></item></channel></rss>