JamJet · Field notes from the runtime RSS

Things we learned
by running agents.

Engineering posts on durable execution, policy, audit, memory, and the boring reliability work that makes AI agents survive past the demo.

  1. 01
    Enterprise & Governance just shipped · 11 min read

    Your AI Agents Won't Survive an Audit

    89% of enterprise AI agents never reach production. The EU AI Act is enforceable in August. Here's what production safety actually requires — and why most agent frameworks aren't ready.

    SP Sunil Prakash Read →
  2. 02
    Technical Deep Dive just shipped · 6 min read

    Zero-Sidecar Durable AI Agents in Java

    Kill your agent. Restart it. It remembers everything. The JamJet Java Runtime embeds durable execution directly in your JVM — no Docker, no sidecar, no REST overhead.

    SP Sunil Prakash Read →
  3. 03
    Architecture & Deep Dives · 7 min read

    Why Your AI Agents Need Observability — and What to Measure

    You would not deploy a microservice without metrics and tracing. Why are you deploying AI agents blind? Here is what to measure and how.

    SP Sunil Prakash Read →
  4. 04
    Architecture & Deep Dives · 6 min read

    Getting Started with MCP: Connect AI Agents to Any Tool

    Model Context Protocol is becoming the USB-C of AI agents. Here is how to connect your agents to databases, APIs, and file systems — with working code.

    SP Sunil Prakash Read →
  5. 05
    Architecture & Deep Dives · 14 min read

    Google ADK vs JamJet: Building a Claims Processing Agent

    We built the same insurance claims agent in both frameworks. One crashes and loses everything. The other picks up exactly where it left off.

    SP Sunil Prakash Read →
  6. 06
    Architecture & Deep Dives · 8 min read

    How to Choose an AI Agent Framework in 2026

    LangGraph, CrewAI, AutoGen, Google ADK, JamJet — the landscape is crowded. Here is a practical decision framework for picking the right one.

    SP Sunil Prakash Read →
  7. 07
    Releases & Updates · 4 min read

    Engram: A Memory Layer for AI Agents That Actually Works

    One cargo install. Zero infrastructure. Your agents remember everything — with temporal knowledge graphs, semantic search, and MCP-native tools.

    SP Sunil Prakash Read →
  8. 08
    Architecture & Deep Dives · 13 min read

    The State of Memory in Java AI Agents (April 2026)

    A tour of every option Java developers have for adding persistent memory to AI agents — and why most of them stop at chat history.

    SP Sunil Prakash Read →
  9. 09
    Strategy & Vision · 11 min read

    The Companies Quietly Replacing Entire Workflows with AI Agents — While You're Still Debating Prompts

    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's what they know that you don't.

    SP Sunil Prakash Read →
  10. 10
    Architecture & Deep Dives · 15 min read

    Akka Agents vs JamJet: Actor Model or Agent-Native Runtime?

    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.

    SP Sunil Prakash Read →
  11. 11
    Releases & Updates · 8 min read

    JamJet Spring Boot Starter — Production-Grade Agent Runtime for Spring AI

    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.

    SP Sunil Prakash Read →
  12. 12
    Strategy & Vision · 9 min read

    Every Major AI Agent Failure Has the Same Root Cause

    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.

    SP Sunil Prakash Read →
  13. 13
    Technical Deep Dive · 12 min read

    AI Agents Need Their Spring Moment — It Starts with the Runtime

    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.

    SP Sunil Prakash Read →
  14. 14
    Strategy & Vision · 20 min read

    What Your Competitors Are Already Doing With AI Agents

    Named companies, real metrics, sourced data. How finance, legal, support, and insurance deploy AI agents in production — and what it means if you haven't started.

    SP Sunil Prakash Read →
  15. 15
    Strategy & Vision · 16 min read

    Why AI Agents Are the Next Competitive Advantage — and What Leaders Need to Know

    What AI agents mean for business leaders: faster decisions, better scale, and a new operating model. No code, no jargon — just the strategic case.

    SP Sunil Prakash Read →
  16. 16
    Releases & Updates · 2 min read

    What's New: Incremental Streaming, LLM Tiebreaker, and Reasoning Modes

    True incremental NDJSON streaming for agent tools, async LLM tiebreaker for coordinator routing, and reasoning mode scoring for Agent Cards.

    SP Sunil Prakash Read →
  17. 17
    Strategy & Vision · 8 min read

    Why We Built JamJet

    The demo-to-production gap in AI agents is real. Here is why we built a new runtime instead of reaching for another framework.

    SP Sunil Prakash Read →
  18. 18
    Architecture & Deep Dives · 5 min read

    Building a multi-agent wealth advisor with JamJet

    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.

    SP Sunil Prakash Read →
  19. 19
    Enterprise & Security · 4 min read

    OAuth delegation and federation auth for AI agents

    RFC 8693 token exchange, scope narrowing, per-step scoping, mTLS federation — how JamJet ensures agents never exceed the permissions they were granted.

    SP Sunil Prakash Read →
  20. 20
    Enterprise & Security · 4 min read

    Phase 4: Enterprise security for production agents

    Multi-tenant isolation, PII redaction, OAuth delegation, mTLS federation — the enterprise layer that lets agents handle real data in real organizations.

    SP Sunil Prakash Read →
  21. 21
    Enterprise & Security · 4 min read

    Data governance for AI agents: PII, redaction, and retention

    How JamJet's data policy engine handles PII detection, automatic redaction, and time-based retention — enforced by the Rust runtime, not by convention.

    SP Sunil Prakash Read →
  22. 22
    Architecture & Deep Dives · 4 min read

    Migrating from LangGraph to JamJet: what actually changes

    A side-by-side walkthrough of the same workflow in LangGraph and JamJet — what maps across, what disappears, and what you gain.

    SP Sunil Prakash Read →
  23. 23
    Architecture & Deep Dives · 3 min read

    Building a self-evaluating AI agent in 50 lines

    Draft, judge, retry. A workflow that scores its own output and loops until it is good enough — or gives up gracefully.

    SP Sunil Prakash Read →
  24. 24
    Testing & Evaluation · 3 min read

    Testing AI agents like software

    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.

    SP Sunil Prakash Read →
  25. 25
    Testing & Evaluation · 5 min read

    Phase 3: Eval Harness, Project Templates, and the Path to Trustworthy Agents

    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.

    SP Sunil Prakash Read →
  26. 26
    Strategy & Vision · 4 min read

    Why I built JamJet's runtime in Rust

    Not a trendy choice. A conviction-based one. Here is what it cost, what it taught me, and why I would do it again.

    SP Sunil Prakash Read →
  27. 27
    Releases & Updates · 2 min read

    Announcing JamJet: The Agent-Native Runtime

    We built the runtime we wished existed for AI agents — durable, composable, and built for production from day one.

    SP Sunil Prakash Read →