--- title: "Foundations" canonical: "https://current.tinyfish.ai/issue/32/foundations" publication: "TinyFish" publisher: "TinyFish" language: "en-US" guide: "https://current.tinyfish.ai/llms.txt" permalink: "https://current.tinyfish.ai/issue/32/foundations" issue: 32 section: "foundations" description: "Conceptual clarity earned from building at scale" authors: ["Rina Takahashi","Nora Kaplan"] published: 2026-06-07 updated: 2026-06-04 articles: 21 --- # 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 32 — Foundations Conceptual clarity earned from building at scale ### The Control Question - [Where You Can Afford to Be Surprised]() — By [Rina Takahashi]() · Published 2026-06-03 · Format: The Control Question "Agent" means at least three different things right now, and the confusion isn't just semantic. Underneath the terminology sits a design decision with real operational consequences: who picks the next step, your code or the model? Code-determined paths produce bounded, explainable failures. Model-determined paths produce creative ones you didn't plan for. Most production systems need both. The hard part is drawing the line between them, and it's a risk-tolerance decision that happens to look like an architecture one. ### WebMCP Walkthrough - [What a Website Chooses to Tell an Agent]() — By [Rina Takahashi]() · Published 2026-06-03 · Format: WebMCP Walkthrough A new browser protocol lets websites publish structured tool definitions that agents can call directly, skipping the page entirely. A site registers a product search with four categories in the enum. The actual catalog has fifty. The agent receives that simplified view as the complete picture and has no mechanism to ask what else exists. When a website decides what to tell an agent about itself, it's also deciding what disappears. ### Further Reading - **Pass@k vs Pass^k: Understanding Agent Reliability** — [Source]() — Published 2026-06-03 The same 70% benchmark score means wildly different things depending on how you measure. Phil Schmid makes the math legible. - **AI Browser Agents: The New Automation Layer** — [Source]() — Published 2026-06-03 Production teams are converging on hybrid architectures: deterministic scripts for stable paths, AI only where things get weird. - **State of Context Engineering in 2026** — [Source]() — Published 2026-06-03 A field report on how context engineering grew from blog-post advice into platform-level convention. Worth reading for the trajectory alone. - **Google Chrome Ships WebMCP in Early Preview** — [Source]() — Published 2026-06-03 WebMCP's scoping to user-present sessions is a deliberate design boundary. VentureBeat covers the enterprise implications well. - **Agentic AI Explained: Agents vs Workflows** — [Source]() — Published 2026-06-03 Orkes maps the middle ground between full autonomy and rigid orchestration, where most production systems actually live. ### The Agentic Ladder The most durable distinction in agentic systems has nothing to do with sophistication. It has to do with who decides what happens next. If code dictates every step, you have a workflow, even when it calls a model at each one. If the model picks the next action, you've crossed into something structurally different. Worth saying upfront: this spectrum is not a maturity ranking. A deterministic workflow at level three can deliver more value than an autonomous agent at level five when the task demands reliability, explainability, and a limited blast radius. The best architecture is the simplest one that meets the requirements you actually have today. Six levels, from fully code-controlled to fully model-controlled. - **Single Model Call: One Prompt, One Answer** — [Source]() — Published 2026-06-03 Tag: Code Control Code controls everything. The model handles exactly one reasoning step: classify this, extract that, summarize this document. No retrieval, no iteration, no branching. When the task is well-scoped enough, the simplest architecture is also the most reliable. - **RAG: Code Retrieves, the Model Reasons** — [Source]() — Published 2026-06-03 Tag: Code Control Code still owns the flow. It decides what to retrieve and when. The model reasons over whatever context it's handed but never initiates a search on its own. Good for document Q&A, policy lookup, knowledge-base queries. External knowledge without external autonomy. - **LLM Workflow: The Path Is Mapped Beforehand** — [Source]() — Published 2026-06-03 Tag: Code Control Chaining, routing, parallelization. The developer defines the sequence before runtime; the model handles each step within it. Pick this over a tool-calling agent when the flow is known in advance and you need the whole process to be inspectable and replayable. - **Tool-Calling Agent: Model Decisions Become Executable Actions** — [Source]() — Published 2026-06-03 Tag: Shared Control The first level where the model influences what happens next. It picks tools and constructs parameters; code defines the options and enforces guardrails. Something meaningful changes here: model reasoning errors become executable consequences. Tool selection becomes a security surface, not just a design choice. - **Web Agent: Navigating Interfaces Built for Humans** — [Source]() — Published 2026-06-03 Tag: Model Control The model controls perception and action inside an environment. It decides what to look at, interprets what it sees, and acts against interfaces designed for people. Powerful where APIs don't exist. Also means operating through the user's most privileged general-purpose interface: the browser. - **Multi-Agent: Coordination Across Contexts and Capabilities** — [Source]() — Published 2026-06-03 Tag: Distributed Control Multiple models coordinate, delegate, and verify each other's work. Reach for this when no single context window holds the full task. Worth knowing: multi-agent systems burn roughly 10–15x more tokens than a single agent. The simplest architecture that works remains the right starting point. ### Three Protocols Untangled Three protocols keep surfacing in the same conversations about how AI agents interact with the world. They share governance under the Linux Foundation, overlapping vocabulary around capability discovery, and enough surface similarity to blur together fast. They shouldn't. Each operates at a different layer, runs in a different environment, and puts control in different hands. This grid draws the lines: what each protocol connects, where it executes, and who decides what gets exposed. - **MCP Connects AI Platforms to Tools Server-Side** — [Source]() — Published 2026-06-03 Tag: Protocol Card Backend JSON-RPC protocol. AI platforms (Claude, ChatGPT, Copilot) act as clients; tool providers host servers that expose capabilities. Anthropic-originated, now governed by the Linux Foundation's Agentic AI Foundation. Over 10,000 registered servers and 97M monthly SDK downloads. The plumbing layer, not the policy layer. - **WebMCP Lets Websites Talk to Browser Agents** — [Source]() — Published 2026-06-03 Tag: Protocol Card Client-side browser standard. Websites expose structured tools to AI agents running in the browser, with no server component involved. The website operator decides what gets exposed; the agent consumes it. Co-developed by Google and Microsoft under W3C. Live in Chrome 149 as an origin trial. Cross-browser adoption still pending. - **A2A Connects Agents to Each Other Horizontally** — [Source]() — Published 2026-06-03 Tag: Protocol Card Where MCP connects agents to tools and WebMCP connects agents to websites, A2A handles agent-to-agent discovery, task delegation, and coordination across organizational lines. Google-originated, now under the Agentic AI Foundation alongside MCP. Version 1.2 stable, with 150+ organizations in production. - **Three Protocols, Three Layers, One Stack** — [Source]() — Published 2026-06-03 Tag: Integration Pattern A travel company runs an MCP server so ChatGPT can query its booking API directly. It implements WebMCP tools on its consumer site so browser agents can walk through booking flows in a user's live session. And it uses A2A so its planning agent can hand off tasks to a partner airline's agent. Different protocols, different interaction patterns, same company. ### Past Articles - [What Browser Agents See Before They Think]() — By [Rina Takahashi]() · Published 2026-05-28 · Format: The Perception Layer Before a browser agent reasons about a task, it needs a representation of the page. Raw HTML, a screenshot, or the accessibility tree. That choice, made once and early, sets the token budget, failure modes, and reliability ceiling for everything downstream. OpenAI, Microsoft, and Perplexity built their agent systems independently and all three landed on the same primary perception layer: infrastructure originally designed for people who can't see screens. The convergence is worth understanding. - [Where Agent Behavior Actually Gets Decided]() — By [Nora Kaplan]() · Published 2026-05-28 · Format: Context Over Instruction A developer's coding agent worked perfectly for thirty minutes, then started contradicting its own decisions. The prompt was the same. The model was the same. Everything else in the context window had been accumulating. His fix was radical: stop carrying context forward entirely. It worked. Across production agent systems, the same asymmetry kept surfacing — a carefully engineered prompt drowning in accumulated tool outputs performed worse than a simple prompt in a clean, focused context. The field needed a word for the thing practitioners were actually optimizing, because "prompt" didn't describe it. - [Where Intelligence Lives in Each Step]() — By [Rina Takahashi]() · Published 2026-05-21 · Format: The Autonomy Dial A login form needs zero intelligence. A Playwright selector finds the username field, fills it, clicks "Sign In" in milliseconds. Two steps later, the same workflow hits a CAPTCHA rendered as a bitmap inside a canvas element. Now you need a vision model looking at a screenshot. Same workflow, wildly different requirements per step. Browser automation has three layers of intelligence available at every step, from free and instant to expensive and flexible. How a system moves between them mid-run is the design choice that actually holds up or doesn't. - [The Non-Determinism Budget]() — By [Nora Kaplan]() · Published 2026-05-21 · Format: The Determinism Budget A system with 95% reliability at each model-directed step delivers 36% reliability over twenty steps. The math is just multiplication. But the agent ecosystem has no standard way to measure this decay, and new research shows why it's so insidious: failed runs are statistically indistinguishable from successful ones through most of their execution. The budget is spent long before anyone can tell. Experienced teams navigate this constraint well. They navigate it by instinct, without a number, making consequential architecture decisions about a resource they've never quantified. ## Other sections in Issue 32 - [Daily Brief]() - [Market Pulse]() - [Practitioner's Corner]() - [Echoes]() - [Vision]() ## More - [Publication guide]() - [Issue archive]()