Start with a concrete problem. Find an answer you can verify and reproduce.

Look High. Build Low.

XBSTACK continuously documents practical AI Agent, MCP, LangGraph and Workflow engineering, alongside useful developer tools, long-term research and outdoor field notes.

MCP LangGraph AI Agent Workflow AI Finance

AI Engineering Topics

AI Agent

Architecture, tool use, memory, RAG, evaluation, permissions and runtime governance.

Agent architecture and runtime →Tool authorization →Memory / RAG →

MCP

Servers, transports, OAuth, permissions, security and protocol troubleshooting.

MCP vs Function Calling →Streamable HTTP →JSON-RPC debugging →

LangGraph

State, checkpoints, HITL, failure recovery, concurrency and observability.

State isolation →HITL approval →Failure recovery →

Workflow Automation

n8n, self-hosting, webhooks, queues, retries, idempotency and cost governance.

Self-hosted n8n →Error handling and cost →Queue Mode →

Products & Tools

All products & tools →

AI Finance

Analyze public financial reports and company fundamentals.

Open →

Lunest

Sleep and recovery product for iOS and Android.

Open →

Latest Publications

Archive →Newsletter →

What Is Context Engineering? Reducing AI Agent Cost with Retrieval, Tool Search and Memory

Context engineering goes beyond prompt engineering. This guide combines Microsoft, Anthropic and Google sources with XBSTACK tests on retrieval, tools, memory and token cost.

AI Engineering09/04/2026

→

GPT-6 Astra API Guide: Pricing, Claude/Gemini Comparison, 1.05M Context and Migration

GPT-6 Astra API pricing, 1.05M context, Responses migration and rollout, plus Claude Fable 5.1 and Gemini 3.8 Flash comparisons for coding, agents and cost.

AI Engineering09/04/2026

→

Gemini 3.8 Flash vs 3.7 Flash: Same Price, Different Agent Cost?

Gemini 3.8 Flash vs 3.7 Flash: compare price, 1M context, thinking levels, AI coding, AIGC, Claude/GPT selection context, agent routing, migration and token cost.

AI Engineering09/03/2026

→

Claude Fable 5.1 vs Mythos 5.1: Pricing, Access, Coding, and Agent Trade-offs

Claude Fable 5.1 and Mythos 5.1 share the same underlying model but differ in safeguards and access. Compare pricing, cache costs, coding benchmarks, and who should use each.

AI Engineering09/02/2026

→

MCP StreamableHTTPClientTransport POST Stays Pending After SSE Disconnect: Issue #2739 Reproduced

A v1 MCP StreamableHTTPClientTransport POST can remain pending until request timeout after request-scoped SSE error/EOF. XBSTACK reproduced Issue #2739 on SDK 1.29.0 and 1.30.0.

AI Engineering09/01/2026

→

How to Configure llms.txt v2: rel=alternate, describedby, and Markdown Discovery

llms.txt v2 adds explicit discovery for Markdown pages and llms.txt through rel=alternate and rel=describedby. This guide shows how to implement and verify both relationships.

AI Engineering08/31/2026

→