<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>JamJet Blog</title><description>Performance-first, agent-native runtime for AI agents. Engineering deep dives, architecture posts, and release notes.</description><link>https://jamjet.dev/</link><language>en-us</language><item><title>The State of Memory in Java AI Agents (April 2026)</title><link>https://jamjet.dev/blog/state-of-memory-java-ai-agents/</link><guid isPermaLink="true">https://jamjet.dev/blog/state-of-memory-java-ai-agents/</guid><description>A tour of every option Java developers have for adding persistent memory to AI agents — and why most of them stop at chat history.</description><pubDate>Tue, 07 Apr 2026 00:00:00 GMT</pubDate><category>Architecture &amp; Deep Dives</category><author>Sunil Prakash</author></item><item><title>Engram: A Memory Layer for AI Agents That Actually Works</title><link>https://jamjet.dev/blog/engram-agent-memory/</link><guid isPermaLink="true">https://jamjet.dev/blog/engram-agent-memory/</guid><description>One cargo install. Zero infrastructure. Your agents remember everything — with temporal knowledge graphs, semantic search, and MCP-native tools.</description><pubDate>Tue, 07 Apr 2026 00:00:00 GMT</pubDate><category>Releases &amp; Updates</category><author>Sunil Prakash</author></item><item><title>The Companies Quietly Replacing Entire Workflows with AI Agents — While You&apos;re Still Debating Prompts</title><link>https://jamjet.dev/blog/companies-quietly-replacing-workflows/</link><guid isPermaLink="true">https://jamjet.dev/blog/companies-quietly-replacing-workflows/</guid><description>While most teams argue about prompt engineering, early movers are shipping autonomous agent workflows that handle claims, onboarding, and due diligence end-to-end. Here&apos;s what they know that you don&apos;t.</description><pubDate>Tue, 31 Mar 2026 00:00:00 GMT</pubDate><category>Strategy &amp; Vision</category><author>Sunil Prakash</author></item><item><title>Akka Agents vs JamJet: Actor Model or Agent-Native Runtime?</title><link>https://jamjet.dev/blog/akka-agents-vs-jamjet/</link><guid isPermaLink="true">https://jamjet.dev/blog/akka-agents-vs-jamjet/</guid><description>Two production-grade approaches to AI agents on the JVM. Akka adapted 20 years of actor infrastructure. JamJet was purpose-built from day one. An honest architectural comparison with code, diagrams, and a decision matrix.</description><pubDate>Sun, 29 Mar 2026 00:00:00 GMT</pubDate><category>Architecture &amp; Deep Dives</category><author>Sunil Prakash</author></item><item><title>JamJet Spring Boot Starter — Production-Grade Agent Runtime for Spring AI</title><link>https://jamjet.dev/blog/jamjet-spring-boot-starter/</link><guid isPermaLink="true">https://jamjet.dev/blog/jamjet-spring-boot-starter/</guid><description>Add one dependency to your Spring Boot application. Get crash recovery, audit trails, replay testing, and human-in-the-loop for every Spring AI agent call. JamJet brings its full agent runtime — strategies, multi-agent coordination, MCP, A2A, eval harness — to the Spring ecosystem.</description><pubDate>Sun, 29 Mar 2026 00:00:00 GMT</pubDate><category>Releases &amp; Updates</category><author>Sunil Prakash</author></item><item><title>Every Major AI Agent Failure Has the Same Root Cause</title><link>https://jamjet.dev/blog/ai-agent-failures-root-cause/</link><guid isPermaLink="true">https://jamjet.dev/blog/ai-agent-failures-root-cause/</guid><description>Klarna, Air Canada, DPD — sourced post-mortems of real AI agent failures. The pattern is always the same: prototype infrastructure in production. Named companies, real timelines, avoidable lessons.</description><pubDate>Sat, 28 Mar 2026 00:00:00 GMT</pubDate><category>Strategy &amp; Vision</category><author>Sunil Prakash</author></item><item><title>AI Agents Need Their Spring Moment — It Starts with the Runtime</title><link>https://jamjet.dev/blog/jamjet-java-ai-ecosystem/</link><guid isPermaLink="true">https://jamjet.dev/blog/jamjet-java-ai-ecosystem/</guid><description>Spring transformed how Java built enterprise apps. AI agents need the same transformation — not another framework, but a production runtime. A sourced comparison of every major JVM AI framework and where the gap remains.</description><pubDate>Sat, 28 Mar 2026 00:00:00 GMT</pubDate><category>Technical Deep Dive</category><author>Sunil Prakash</author></item><item><title>What Your Competitors Are Already Doing With AI Agents</title><link>https://jamjet.dev/blog/competitors-already-deploying-ai-agents/</link><guid isPermaLink="true">https://jamjet.dev/blog/competitors-already-deploying-ai-agents/</guid><description>Named companies, real metrics, sourced data. How finance, legal, support, and insurance deploy AI agents in production — and what it means if you haven&apos;t started.</description><pubDate>Wed, 25 Mar 2026 00:00:00 GMT</pubDate><category>Strategy &amp; Vision</category><author>Sunil Prakash</author></item><item><title>Why AI Agents Are the Next Competitive Advantage — and What Leaders Need to Know</title><link>https://jamjet.dev/blog/ai-agents-business-case/</link><guid isPermaLink="true">https://jamjet.dev/blog/ai-agents-business-case/</guid><description>What AI agents mean for business leaders: faster decisions, better scale, and a new operating model. No code, no jargon — just the strategic case.</description><pubDate>Sat, 21 Mar 2026 00:00:00 GMT</pubDate><category>Strategy &amp; Vision</category><author>Sunil Prakash</author></item><item><title>What&apos;s New: Incremental Streaming, LLM Tiebreaker, and Reasoning Modes</title><link>https://jamjet.dev/blog/incremental-streaming-tiebreaker/</link><guid isPermaLink="true">https://jamjet.dev/blog/incremental-streaming-tiebreaker/</guid><description>True incremental NDJSON streaming for agent tools, async LLM tiebreaker for coordinator routing, and reasoning mode scoring for Agent Cards.</description><pubDate>Fri, 20 Mar 2026 00:00:00 GMT</pubDate><category>Releases &amp; Updates</category><author>Sunil Prakash</author></item><item><title>Why We Built JamJet</title><link>https://jamjet.dev/blog/why-we-built-jamjet/</link><guid isPermaLink="true">https://jamjet.dev/blog/why-we-built-jamjet/</guid><description>The demo-to-production gap in AI agents is real. Here is why we built a new runtime instead of reaching for another framework.</description><pubDate>Sun, 15 Mar 2026 00:00:00 GMT</pubDate><category>Strategy &amp; Vision</category><author>Sunil Prakash</author></item><item><title>Building a multi-agent wealth advisor with JamJet</title><link>https://jamjet.dev/blog/wealth-management-multi-agent/</link><guid isPermaLink="true">https://jamjet.dev/blog/wealth-management-multi-agent/</guid><description>Four specialist AI agents — risk profiler, market analyst, tax strategist, portfolio architect — collaborate through a durable workflow to produce investment recommendations. A deep dive into the architecture, with a side-by-side comparison to Google ADK.</description><pubDate>Fri, 13 Mar 2026 00:00:00 GMT</pubDate><category>Architecture &amp; Deep Dives</category><author>Sunil Prakash</author></item><item><title>OAuth delegation and federation auth for AI agents</title><link>https://jamjet.dev/blog/oauth-federation-agent-auth/</link><guid isPermaLink="true">https://jamjet.dev/blog/oauth-federation-agent-auth/</guid><description>RFC 8693 token exchange, scope narrowing, per-step scoping, mTLS federation — how JamJet ensures agents never exceed the permissions they were granted.</description><pubDate>Thu, 12 Mar 2026 00:00:00 GMT</pubDate><category>Enterprise &amp; Security</category><author>Sunil Prakash</author></item><item><title>Phase 4: Enterprise security for production agents</title><link>https://jamjet.dev/blog/phase4-enterprise-security/</link><guid isPermaLink="true">https://jamjet.dev/blog/phase4-enterprise-security/</guid><description>Multi-tenant isolation, PII redaction, OAuth delegation, mTLS federation — the enterprise layer that lets agents handle real data in real organizations.</description><pubDate>Thu, 12 Mar 2026 00:00:00 GMT</pubDate><category>Enterprise &amp; Security</category><author>Sunil Prakash</author></item><item><title>Data governance for AI agents: PII, redaction, and retention</title><link>https://jamjet.dev/blog/data-governance-pii-retention/</link><guid isPermaLink="true">https://jamjet.dev/blog/data-governance-pii-retention/</guid><description>How JamJet&apos;s data policy engine handles PII detection, automatic redaction, and time-based retention — enforced by the Rust runtime, not by convention.</description><pubDate>Thu, 12 Mar 2026 00:00:00 GMT</pubDate><category>Enterprise &amp; Security</category><author>Sunil Prakash</author></item><item><title>Migrating from LangGraph to JamJet: what actually changes</title><link>https://jamjet.dev/blog/langgraph-migration-real-example/</link><guid isPermaLink="true">https://jamjet.dev/blog/langgraph-migration-real-example/</guid><description>A side-by-side walkthrough of the same workflow in LangGraph and JamJet — what maps across, what disappears, and what you gain.</description><pubDate>Sun, 08 Mar 2026 00:00:00 GMT</pubDate><category>Architecture &amp; Deep Dives</category><author>Sunil Prakash</author></item><item><title>Building a self-evaluating AI agent in 50 lines</title><link>https://jamjet.dev/blog/self-evaluating-agent-50-lines/</link><guid isPermaLink="true">https://jamjet.dev/blog/self-evaluating-agent-50-lines/</guid><description>Draft, judge, retry. A workflow that scores its own output and loops until it is good enough — or gives up gracefully.</description><pubDate>Sun, 08 Mar 2026 00:00:00 GMT</pubDate><category>Architecture &amp; Deep Dives</category><author>Sunil Prakash</author></item><item><title>Phase 3: Eval Harness, Project Templates, and the Path to Trustworthy Agents</title><link>https://jamjet.dev/blog/phase3-eval-harness-templates/</link><guid isPermaLink="true">https://jamjet.dev/blog/phase3-eval-harness-templates/</guid><description>Shipping the eval harness, four built-in project templates, and why testing your agents the same way you test software is the only path forward.</description><pubDate>Sun, 08 Mar 2026 00:00:00 GMT</pubDate><category>Testing &amp; Evaluation</category><author>Sunil Prakash</author></item><item><title>Testing AI agents like software</title><link>https://jamjet.dev/blog/testing-ai-agents-like-software/</link><guid isPermaLink="true">https://jamjet.dev/blog/testing-ai-agents-like-software/</guid><description>Most teams test their agents by running them manually and eyeballing the output. There is a better way — and it fits in a CI pipeline.</description><pubDate>Sun, 08 Mar 2026 00:00:00 GMT</pubDate><category>Testing &amp; Evaluation</category><author>Sunil Prakash</author></item><item><title>Why I built JamJet&apos;s runtime in Rust</title><link>https://jamjet.dev/blog/why-rust-for-ai-workflows/</link><guid isPermaLink="true">https://jamjet.dev/blog/why-rust-for-ai-workflows/</guid><description>Not a trendy choice. A conviction-based one. Here is what it cost, what it taught me, and why I would do it again.</description><pubDate>Sun, 08 Mar 2026 00:00:00 GMT</pubDate><category>Strategy &amp; Vision</category><author>Sunil Prakash</author></item><item><title>Announcing JamJet: The Agent-Native Runtime</title><link>https://jamjet.dev/blog/announcing-jamjet/</link><guid isPermaLink="true">https://jamjet.dev/blog/announcing-jamjet/</guid><description>We built the runtime we wished existed for AI agents — durable, composable, and built for production from day one.</description><pubDate>Sat, 07 Mar 2026 00:00:00 GMT</pubDate><category>Releases &amp; Updates</category><author>Sunil Prakash</author></item></channel></rss>