--- title: "Foundations" canonical: "https://current.tinyfish.ai/issue/1/foundations" publication: "TinyFish" publisher: "TinyFish" language: "en-US" guide: "https://current.tinyfish.ai/llms.txt" permalink: "https://current.tinyfish.ai/issue/1/foundations" issue: 1 section: "foundations" description: "Conceptual clarity earned from building at scale" authors: ["Nora Kaplan","Rina Takahashi"] published: 2025-10-28 updated: 2025-10-28 articles: 10 --- # 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 1 — Foundations Conceptual clarity earned from building at scale ### What Building Teaches Builders - [Consequence-Bounded Autonomy]() — By [Nora Kaplan]() · Published 2025-10-28 · Format: Field Guide Been thinking about how every agent conversation I have circles back to capability questions—model accuracy, task completion rates, benchmark scores. But the teams actually running these systems at scale? They're asking completely different questions. Mainly: what breaks if this screws up? ### Web Evolution's Lessons - [When Shopping Carts Became Identity]() — By [Rina Takahashi]() · Published 2025-10-28 · Format: Web Archaeology Been thinking about why authentication breaks so predictably at scale. Years of watching production login flows, and there's this pattern where the complexity isn't in the code—it's in managing state that lives in two places at once. Browser thinks you're logged in, server disagrees, user sees an error that looks like a bug. Turns out a 1994 shopping cart decision is still dictating how that works. ### Pattern Recognition from the Field - [The Reasoning Model Gap Nobody's Talking About]() — Published 2025-10-28 Every major AI lab just announced a "reasoning" model. OpenAI's o1. Anthropic's extended thinking. Google's Gemini thinking mode. The pitch is identical: these models think longer, reason deeper, solve harder problems. ### Questions Worth Asking - **Does It Work Once or Every Time?** — [Source]() — Published 2025-10-28 Tag: Consistency Testing A single successful run means nothing. Run the same task eight times and watch what happens. Performance can crater from 61% to under 25% when you need reliability. The demo that works perfectly today might fail half the time tomorrow. - **What Happens When Dependencies Fail?** — [Source]() — Published 2025-10-28 Tag: Tool Dependencies Your agent calls six external APIs. Three of them have 99% uptime. Do the math on compound reliability. Can you measure latency for each dependency? More than half of agent failures trace back to function calls and tool selection breaking down. - **Can You See Failures in Real Time?** — [Source]() — Published 2025-10-28 Tag: Production Monitoring Offline testing catches obvious problems. Production reveals everything else. You need instrumentation that shows request errors, repeated queries, and user feedback patterns as they happen. The gap between your test cases and actual usage is where things break. - **How Many Steps to Finish?** — [Source]() — Published 2025-10-28 Tag: Path Complexity Watch your agent work through a task. Does it loop? Repeat steps? Take three attempts to do what should happen once? Path errors create the worst debugging sessions. Count iterations early and inspect traces manually before you scale. - **What Does Each Success Cost?** — [Source]() — Published 2025-10-28 Tag: Cost Efficiency An agent that works beautifully but costs $12 per task isn't production-ready if you need to run it ten thousand times daily. Track cost from day one: API calls, compute, human review time. Capability without efficiency is a prototype, not a system. - **Do Tests Match Real Usage?** — [Source]() — Published 2025-10-28 Tag: Test Coverage Your test suite should cover every function the agent supports, plus edge cases and queries it should reject. The set can be small but must be complete. Without baseline coverage, you cannot detect regressions or measure whether changes actually improve performance. ### In Dialogue With Complexity - [A Conversation with /graphql, The Endpoint That Swallowed the API]() — Published 2025-10-28 We meet in a dimly lit server room—metaphorically speaking, since our interviewee doesn't technically exist in physical space. `/graphql`, the single endpoint that's become the face of modern API design, has agreed to talk. If you've worked with GraphQL, you've hit this endpoint countless times: that lone path that somehow handles your entire data layer. It's an architectural choice that makes REST developers uncomfortable and has sparked endless debates about whether consolidating everything into one URL is brilliant or insane. ## Other sections in Issue 1 - [Daily Brief]() - [Market Pulse]() - [Practitioner's Corner]() - [Echoes]() - [Vision]() ## More - [Publication guide]() - [Issue archive]()