--- title: "Foundations" canonical: "https://current.tinyfish.ai/issue/20/foundations" publication: "TinyFish" publisher: "TinyFish" language: "en-US" guide: "https://current.tinyfish.ai/llms.txt" permalink: "https://current.tinyfish.ai/issue/20/foundations" issue: 20 section: "foundations" description: "Conceptual clarity earned from building at scale" authors: ["Rina Takahashi"] published: 2026-03-16 updated: 2026-03-12 articles: 20 --- # TinyFish > CURRENT is a journal about AI agents in production, for the engineering and product leaders who have to make them work. Drawing on experience building enterprise web agents, it explains why the demo succeeded and the deployment didn't, and what that means for choosing vendors, briefing the board, and avoiding mistakes others have already made. [Read on the website]() ## Issue 20 — Foundations Conceptual clarity earned from building at scale ### The Conceptual Argument - [The Distributed Systems Playbook Runs Out Halfway Through Agent Infrastructure]() — By [Rina Takahashi]() · Published 2026-03-11 · Format: The Conceptual Argument The MCP roadmap names problems the distributed systems community solved a decade ago. Stateful sessions fighting load balancers. No service discovery. Horizontal scaling requiring workarounds. With Gartner logging a 1,445% surge in multi-agent inquiries, the ecosystem is reaching for a familiar playbook: decompose, orchestrate, observe. And the pattern transfer is genuine. Server Cards look like service discovery because they are service discovery. But the old reliability toolkit was built on a specific assumption about what failure looks like. Agent systems may not share it. ### The Practical Mapping - [How Much of Your Distributed Systems Playbook Actually Transfers to Agent Infrastructure]() — By [Rina Takahashi]() · Published 2026-03-11 · Format: The Practical Mapping Teams building agent infrastructure keep reaching for the distributed systems playbook they already trust. Service discovery, API gateways, message queues, tracing. Sensible instinct. Some of those patterns port cleanly to the MCP ecosystem. Others break in ways that experienced engineers won't anticipate, because familiar-looking problems can have unfamiliar mechanics inside them. ### Further Reading - **The 2026 MCP Roadmap** — [Source]() — Published 2026-03-11 The protocol's own maintainers name the infrastructure gaps out loud: stateful sessions that fight load balancers, no way to discover servers without connecting to them first, and an enterprise working group that hasn't been formed yet. If you want to understand where MCP's distributed-systems growing pains actually live, start here. - **Why the Model Context Protocol Won** — [Source]() — Published 2026-03-11 An MCP spec contributor traces how a rough Anthropic-internal tool became shared infrastructure within a year. The "grew up in public" thesis goes a long way toward explaining why the governance gaps now surfacing in the 2026 roadmap were baked in from the start. Worth noting: the author runs a commercial MCP management product, so the perspective is informed but not disinterested. - **5 Key Trends Shaping Agentic Development in 2026** — [Source]() — Published 2026-03-11 Useful for what agent development actually looks like at the tool level right now, particularly on parallel execution patterns (tasks running simultaneously against isolated git branches) and the quiet operational burden of managing MCP server fleets as they multiply inside organizations. - **Agentic AI Strategy — Deloitte Tech Trends 2026** — [Source]() — Published 2026-03-11 The sharpest framing of why agentic deployments stall: organizations keep layering agents onto processes designed for humans instead of rethinking the operations themselves. Survey data backs it up. Only 11% of enterprises have agents in production despite 38% piloting them. Their coinage, "workslop," for agents that generate work rather than absorb it, is worth keeping in your vocabulary. - **State of AI Agent Security 2026 Report** — [Source]() — Published 2026-03-11 The governance gap in hard numbers. 88% of organizations have experienced or suspect an agent security incident, yet fewer than half of deployed agents are actively monitored. The finding that stings most: only 21.9% of organizations treat agents as independent identity-bearing entities, which tells you exactly how far operational reality trails behind deployment velocity. - **NIST Launches AI Agent Standards Initiative** — [Source]() — Published 2026-03-11 A law firm's analysis of NIST's February 2026 push toward formal agent interoperability and security standards. The public comment period on agent security closed March 9, making this a live regulatory story. Read it for a sense of where voluntary-only governance norms may be heading. ### The Translation Table Every hard problem in the agent ecosystem has a cousin in distributed systems. Service discovery, load balancing, gateways, tracing, registries, inter-service communication. We've built solutions to all of these before. The patterns translate surprisingly well. The implementations, so far, mostly don't. What's revealing is seeing all six side by side. Some are one metadata standard away from working infrastructure. Others lack even a working group. That unevenness tells you more about where the ecosystem actually stands than any roadmap slide deck will. Six cards below. Each pairs the distributed systems pattern with its agent equivalent and a frank read on where things are. - **Server Cards Promise Discovery Without Full Handshakes** — [Source]() — Published 2026-03-11 Tag: Service Discovery Microservices use `.well-known` URIs so clients learn about services before connecting. MCP's proposed equivalent, Server Cards (SEP-1649), would publish metadata at `.well-known/mcp.json`. Proven pattern, clean fit. But it's still a draft SEP with competing proposals. Today, every MCP client completes a full handshake just to learn what a server offers. - **Stateful Sessions Still Break Every Load Balancer** — [Source]() — Published 2026-03-11 Tag: Horizontal Scaling Distributed systems cracked this years ago: externalize state, keep compute stateless. MCP's Streamable HTTP transport carries stateful sessions requiring sticky routing that most cloud load balancers choke on. The 2026 roadmap targets stateless protocol evolution. For now, teams jury-rig HAProxy or Nginx workarounds and hope for the best. - **Gateway Semantics Remain the Widest Enterprise Gap** — [Source]() — Published 2026-03-11 Tag: API Gateway API gateways centralize auth, routing, rate limiting, and audit logging. MCP has none of this in standardized form. Authorization doesn't propagate cleanly through proxies, session IDs may not survive traversal, and JSON-RPC payloads resist the middleware parsing that REST made routine. Named as unresolved on the roadmap. No working group yet. - **Agent Audit Trails Have Tools but No Standard** — [Source]() — Published 2026-03-11 Tag: Distributed Tracing OpenTelemetry gives microservices end-to-end trace propagation with a shared schema. Agent observability has commercial tooling (Arize, Langfuse, Braintrust) but nothing comparable for correlating traces across agent handoffs. With EU AI Act audit requirements arriving, this gap has a deadline. No MCP-native logging standard exists, and nobody owns the problem yet. - **MCP Registry Launched but Waits on Server Cards** — [Source]() — Published 2026-03-11 Tag: Service Registry Service registries like Consul and etcd catalog what exists and where to find it. The MCP Registry preview shipped in September 2025 as an open catalog with an API. Solid start. But automated crawling depends on Server Cards, which haven't shipped. Without them, populating the registry means manual submissions or establishing full connections to each server. - **Four Agent Protocols Compete, None Have Won Yet** — [Source]() — Published 2026-03-11 Tag: Inter-Service Communication REST, gRPC, and WebSockets coexist in distributed systems after years of consolidation and natural selection. Agent-to-agent communication has A2A (Google, 50+ partners, now under the Linux Foundation), ACP (IBM, drifting toward A2A), and ANP (decentralized). All under 18 months old. Multi-protocol coexistence looks likely, convergence does not. ### This Week's Signals Over the past few weeks, a federal standards body, the largest enterprise software company, and a pair of industry surveys all arrived at the same uncomfortable conclusion from different directions: agent deployment is outrunning governance by a widening margin. The protocol layer, to its credit, is being candid about what breaks at production scale. The foundation meant to steward it is formally taking shape. And the market projections are staggering enough to make the governance gap feel less like a temporary lag and more like a structural feature. These six cards trace that convergence. The responses are arriving, but they're arriving late. - **MCP's Roadmap Is Refreshingly Honest About Breaking** — [Source]() — Published 2026-03-11 Tag: Protocol Evolution The March 2026 MCP roadmap lists four priorities: transport scalability, agent communication, governance, enterprise readiness. But the real story is what it admits. Stateful sessions choke on load balancers. Enterprise requirements are left deliberately vague. The June spec release is tentative. The maintainers are asking practitioners to help fill the gaps, which is either admirable transparency or a tell about how much remains unsolved. - **NIST Steps Into Agent Governance With Standards Initiative** — [Source]() — Published 2026-03-11 Tag: Federal Standards NIST's CAISI announced an AI Agent Standards Initiative in February covering interoperability, open-source protocols, and agent security. The RFI comment period closed March 9. Sector-specific listening sessions for finance, healthcare, and education start in April. Worth watching: federal involvement tends to shift the conversation from "should we govern this?" to "how fast can we?" - **More Than Half of Deployed Agents Fly Blind** — [Source]() — Published 2026-03-11 Tag: Governance Gap Two separate Gravitee-commissioned surveys (919 and 750 respondents) landed on nearly identical numbers: roughly 47% of enterprise AI agents operate without active monitoring or security oversight. Only 14.4% launch with full IT approval. Yes, it's vendor-sourced data. But two independent samples converging on the same figure is harder to dismiss. - **Microsoft Gives IT Teams an Agent Control Plane** — [Source]() — Published 2026-03-11 Tag: Enterprise Tooling Agent 365 goes generally available May 1 at $15/user/month. IT teams get deployment tracking, behavioral monitoring, and least-privilege enforcement across Microsoft's AI platforms. Every agent receives a governed identity through Entra Agent ID. Tens of millions of agents surfaced during the preview period alone, which tells you something about the inventory problem even inside a single vendor's ecosystem. - **Agentic AI Foundation Puts MCP Under Formal Stewardship** — [Source]() — Published 2026-03-11 Tag: Open Governance Anthropic, Block, and OpenAI co-founded the Agentic AI Foundation under the Linux Foundation, contributing MCP, goose, and AGENTS.md as founding projects. Platinum members include AWS, Google, and Microsoft. The MCP Dev Summit lands in New York April 2–3 with 95-plus sessions. Formal governance distributes the stewardship question. Whether it resolves it is a different matter. - **Agent Market Projections Hit Tenfold by 2030** — [Source]() — Published 2026-03-11 Tag: Market Trajectory MarketsandMarkets pegs the AI agents market at $5.2 billion in 2024, growing to $52.6 billion by 2030. NVIDIA's State of AI 2026 survey finds 44% of companies already deploying or assessing agents. Gartner projects up to 40% of enterprise apps will feature agents by year-end. The capital is moving. The governance architecture, as every other card here suggests, has not kept pace. ## Other sections in Issue 20 - [Daily Brief]() - [Market Pulse]() - [Practitioner's Corner]() - [Echoes]() - [Vision]() ## More - [Publication guide]() - [Issue archive]()