TinyFish | Foundations

The Control Question

Where You Can Afford to Be Surprised

By Rina Takahashi— June 3, 2026

Feature image for article: Where You Can Afford to Be Surprised

"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.

The Control Question

Where You Can Afford to Be Surprised

By Rina Takahashi— June 3, 2026

"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— June 3, 2026

Feature image for article: What a Website Chooses to Tell an Agent

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.

WebMCP Walkthrough

What a Website Chooses to Tell an Agent

By Rina Takahashi— June 3, 2026

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 ReliabilityThe 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 LayerProduction teams are converging on hybrid architectures: deterministic scripts for stable paths, AI only where things get weird.

Quick links

State of Context Engineering in 2026

Google Chrome Ships WebMCP in Early Preview

Agentic AI Explained: Agents vs Workflows

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.

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.

Code Control

Single Model Call: One Prompt, One Answer

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.

Code Control

RAG: Code Retrieves, the Model Reasons

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.

Code Control

LLM Workflow: The Path Is Mapped Beforehand

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.

Shared Control

Tool-Calling Agent: Model Decisions Become Executable Actions

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.

Model Control

Web Agent: Navigating Interfaces Built for Humans

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.

Distributed Control

Multi-Agent: Coordination Across Contexts and Capabilities

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.

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.

Protocol Card

MCP Connects AI Platforms to Tools Server-Side

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.

Protocol Card

WebMCP Lets Websites Talk to Browser Agents

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.

Protocol Card

A2A Connects Agents to Each Other Horizontally

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.

Integration Pattern

Three Protocols, Three Layers, One Stack

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.