Software engineer to AI engineer, Part 5: scaling tools with MCP
Model Context Protocol—a shared tool catalog for AI apps: server, client, JSON-RPC, and a PayIQ FastMCP walkthrough.
Stuzhuk Lab — Chemistry of Code
Chemistry of Code
← All posts
Tag
agents
All blog posts with this tag.
How Far Has AI Really Come? A Maturity Map Across Domains
AI does not advance evenly: in some fields it is already a professional tool, in others an impressive demo. A maturity scale, ratings across ten domains, and the key question — not "can it" but "how reliably and autonomously."
Cheap LLMs for agents: why token savings raise task cost
Why distilled models spawn extra tool calls, how benchmarks mislead, and which metrics beat price-per-million for agent TCO.
NanoGPT Speedrun: 153 agent runs across frontier models
Prime Intellect’s nanoGPT speedrun: 18 models, validated top score for Kimi K3kimi-code, plus 41 full agent trajectories.
Problem Engineering: specs beat prompt tricks for AI-generated code
Five-layer problem specs for AI coding: invariants, data contracts, concurrency, fault topology, and observability—before you prompt.
Vector databases for AI agents in 2026: beyond raw ANN speed
Qdrant, Pinecone, Weaviate, pgvector, and Milvus compared for agent memory: filtering, hybrid search, tenancy, and quantization.
CrewAI on Go with zero deps: agent orchestration on the standard library
crewai-go mirrors Agent, Task, and Crew in pure Go stdlib: one binary, fast cold start, and explicit task dependencies.
JavaScript in the agent harness: when a script is cheaper than model reasoning
A sandboxed JS interpreter replaces some tool hops and LLM arithmetic. Notes from a Habr deep dive on LM Studio and LangChain.
Claude system prompts: lessons from Haiku 3 to Opus 5
Anthropic publishes system prompts: not magic personas, but decision rules, tools, uncertainty handling, and UX for long agent tasks.
AI agents need a platform, not just faster typing
Why coding assistants don't shorten monolith release cycles without trackers, runtimes, data access, and MCP—SimpleOne's low-code cases.
How Cursor and other AI IDEs work with code: from autocomplete to agents
Evolution of IDEs and AI tool internals: LSP, repo indexing, context assembly, Tab/Chat/Agent modes, MCP, and comparison of Cursor, Copilot, JetBrains, CLI agents — what happens to code under the hood in 2026.
Agentic Engineering in 2026: How to Manage AI Agents Without Sacrificing Quality
A practical model for agentic development: context, task decomposition, verification loops, multi-agent orchestration, security, DORA metrics, and the engineer's role in the 2026 SDLC.
AI Guardrails in 2026: Policy Gates, Tool Allowlists, and Safe Autonomy for Production Agents
A practical operating model for putting AI agents and RAG systems into production: policy-as-code, narrowly scoped tools, human approvals, adversarial testing, and audit evidence that engineers can actually use.
Prompt Injection in Production 2026: Defending RAG, Tools, and Agents Against Untrusted Content
A production security model for prompt injection: treat retrieved documents, web pages, tool results, and MCP resources as hostile input; isolate context, constrain egress and tools, sandbox execution, and test layered defenses.
MCP in production 2026: the stateless spec, security, and migration
A practical guide to Model Context Protocol after the 2026-07-28 release: no sessions, MRTR, header-based routing, auth hardening, shadow MCP, and servers that survive real load.
Reference Architecture for an Enterprise AI Platform
A practical architecture that connects business problems, knowledge, RAG, agents, security, and observability into one enterprise AI platform.
Why Enterprise AI Needs Agents
How agent systems connect language models to enterprise services and automate processes while keeping people in control.