--- title: "Foundations" canonical: "https://current.tinyfish.ai/issue/48/foundations" publication: "TinyFish" publisher: "TinyFish" language: "en-US" guide: "https://current.tinyfish.ai/llms.txt" permalink: "https://current.tinyfish.ai/issue/48/foundations" issue: 48 section: "foundations" description: "Conceptual clarity earned from building at scale" authors: ["Sevda Polat","Sable Whitford"] published: 2026-09-28 updated: 2026-09-25 articles: 23 --- # 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 48 — Foundations Conceptual clarity earned from building at scale ### Callable Knowledge - [What Gets Lost When a Paper Becomes Callable]() — By [Sevda Polat]() · Published 2026-09-24 · Format: Callable Knowledge A research paper carries its findings, and it also carries the conditions under which those findings can be challenged: methods, assumptions, stated limitations. Paper2Agent, published in *Nature* this month, turns papers into callable servers you can point at your own data to run a paper's methods on it. The system keeps more than you might expect. But when findings move out of a container built for scrutiny and into one built for invocation, certain things get harder to see: version history, the seam between sourced results and the agent's own inference, and the surface a second party would push against. ### Paper to Server - [What a Paper Becomes When You Make It Callable]() — By [Sevda Polat]() · Published 2026-09-24 · Format: Paper to Server Paper2Agent, published in *Nature* this month, takes an academic paper together with its code repository and turns them into an MCP server whose methods you can call on new inputs. The conversion requires sorting the paper's contents into MCP's categories: tools, resources, prompts. A hard-coded threshold becomes a typed parameter. A workflow described in prose becomes a prompt template. The protocol forces a decision about what each piece of a method actually *is*, and those decisions show which parts of a paper sort cleanly into executable form and which resist it. ### Extended Reading - **Paper2Agent: Converting Research Papers into Validated MCP Servers** — [Source]() — Published 2026-09-24 Stanford framework that automates paper-to-tool conversion, surfacing what executable knowledge demands beyond retrievable text. - **When Paper Conversion Becomes a Reproducibility Test** — [Source]() — Published 2026-09-24 26 of 100 papers couldn't be agentified. Missing code and broken dependencies turned conversion into an audit. - **MCP Tasks Extension: What "Completed" Means at the Protocol Layer** — [Source]() — Published 2026-09-24 Cooperative cancellation, bearer-token task IDs, and the distance between protocol status and application validity. - **Separating Identity, Authority, and Intent in Agent Architectures** — [Source]() — Published 2026-09-24 An IETF draft proposes vocabulary for what authentication proves about an agent and what it leaves open. ### What Gets Easier A paper in Nature this month describes Paper2Agent, a framework that reads a research paper and its associated code, then generates an MCP server — a set of callable tools that an AI agent can invoke on demand. Methods that lived as prose descriptions and tangled codebases become typed functions with pre-configured environments. The individual capabilities are worth cataloging because they compound. When published knowledge becomes something you can call rather than something you read and reimplement, the constraints shift: who can use a method, how fast they can apply it, and which questions are even possible to ask. - **Type a Question, Skip the Dependency Hell** — [Source]() — By [Sable Whitford]() — Published 2026-09-24 Tag: Access Shift A biologist predicting a genetic variant's effect on chromatin accessibility can ask a question in plain language. The agent configures the environment, selects parameters, and runs the method. Hours of setup — API keys, input formatting, package installation — collapse into a sentence. - **Twenty-Two Tools, Forty-Five Minutes, Fourteen Dollars** — [Source]() — By [Sable Whitford]() — Published 2026-09-24 Tag: Tool Generation Paper2Agent processed the AlphaGenome paper on a personal laptop and produced 22 MCP tools — each wrapping a method from the paper as a callable function with its own execution environment. All 22 passed automated validation without human intervention. - **Reproduce a Full Workflow From One Prompt** — [Source]() — By [Sable Whitford]() — Published 2026-09-24 Tag: Pipeline Replay MCP prompts can encode multi-step analysis pipelines inferred from a paper's text and code. A Scanpy agent, given only a data file path, ran preprocessing and clustering steps that matched human-researcher outputs — equivalent cell counts, gene counts, and top differentially expressed markers. - **Three Papers' Agents Working One Problem Together** — [Source]() — By [Sable Whitford]() — Published 2026-09-24 Tag: Cross-Paper Reasoning MCP servers are modular, so agents from separate papers can connect to a single session. Three agents from independent studies jointly prioritized a causal gene for psoriasis — correlating perturbation signatures across datasets in a combination none of the source papers had attempted. - **Use a Paper's Own Methods Against It** — [Source]() — By [Sable Whitford]() — Published 2026-09-24 Tag: Conclusion Challenge Callable papers let you interrogate findings, not just reproduce them. The AlphaGenome agent prioritized a different causal gene (SORT1) than the original paper emphasized — surfacing how hard it is to assign causality at genomic loci with multiple candidates. - **Apply Published Methods to Data They've Never Seen** — [Source]() — By [Sable Whitford]() — Published 2026-09-24 Tag: New Data Across 42 execution tasks from 10 non-biology papers, Paper2Agent hit 98.1% accuracy applying methods to new datasets. The Scanpy agent adapted its parameters across seven diverse single-cell datasets without manual reconfiguration, adjusting to each dataset's structure on its own. - **Broken Code Repositories Get Fixed Before Extraction** — [Source]() — By [Sable Whitford]() — Published 2026-09-24 Tag: Repo Decay Code rots. Dependencies vanish, paths break, APIs deprecate. Anyone who's tried to run a two-year-old research repo knows the feeling. Paper2Agent's test-verifier loop detected and repaired four injected failure types across three repositories, recovering functional servers from code that would have stopped most users cold. ### What Gets Harder Paper2Agent, published in *Nature* on September 16, converts research papers into AI agents that answer questions, run analyses, and expose methods as callable tools. The framework calls these agents "virtual corresponding authors." A corresponding author knows what the paper proved and where the evidence runs thin. An agent has the paper's code and text. The gap between those two kinds of knowledge matters because the infrastructure science depends on — peer review, citation, retraction, replication — assumes that published knowledge stays fixed. Six challenges are mapped below. Each describes something that worked tolerably in a world of static papers and becomes harder once knowledge is executable. - **Reproducing the Original Paper's Output Proves Nothing New** — [Source]() — By [Sevda Polat]() — Published 2026-09-24 Tag: Verification Gap Paper2Agent validates its agents against the original codebase's reported results. An agent that matches those outputs is a more faithful copy, not an independent witness. The same artifact runs the method and describes what running it should produce. - **Three Versioned Artifacts and No Authority Standard** — [Source]() — By [Sevda Polat]() — Published 2026-09-24 Tag: Version Drift A callable paper has simultaneous versions in play: the publication, the code repository, and the agent server. Only 17% of research software tools carry version numbers. Paper2Agent introduces yet another versioned artifact whose relationship to the original paper grows ambiguous with each update. - **Assumptions Encoded as Defaults Surface When They Break** — [Source]() — By [Sevda Polat]() — Published 2026-09-24 Tag: Hidden Assumptions Paper2Agent encodes methodological choices as executable defaults — a specific preprocessing order, for instance. These reflect the original study's dataset and analytic goals. Applied to a different context, violated assumptions produce technically valid outputs that answer the wrong question. - **Callable Papers Give Citations Three Layers of Instability** — [Source]() — By [Sevda Polat]() — Published 2026-09-24 Tag: Citation Decay One in five research articles already suffers from reference rot. Callable papers add software dependency decay and model version drift on top of that. Paper2Agent was built on Claude Sonnet 4; a citation six months later points to a stack that may no longer exist in the same form. - **The Agent Cannot Flag Its Own Extrapolations** — [Source]() — By [Sevda Polat]() — Published 2026-09-24 Tag: Epistemic Boundaries Paper2Agent's evaluation reported 100% accuracy on questions the paper never addressed, scored by expert plausibility judgments rather than independent replication. A corresponding author knows where the evidence stops. The agent produces fluent answers with no visible boundary between finding and interpolation. - **Wrong Answers Have No Established Correction Path** — [Source]() — By [Sevda Polat]() — Published 2026-09-24 Tag: Challenge Procedures Static papers have peer commentary, replication, retraction, and errata. A paper-agent introduces at least three challenge layers: the underlying science, the agent's implementation fidelity, and the specific query response. No institution currently receives or investigates challenges at any of these layers. ### Past Articles - [The Score Is Not the Agent]() — By [Sable Whitford]() · Published 2026-09-17 · Format: Evaluation Thesis Six models, a hundred enterprise problems, one evaluation harness — and the top-ranked agent changed depending on whether it faced scripted opponents or other agents. The rank correlation between the two conditions was 0.182, barely better than ranking them by coin flip. Three recent studies converge on the same finding: an agent's benchmark score is not a property of the agent. It's a property of the agent and everything around it while the test ran. That distinction changes what any benchmark result can tell you. - [The Agent Clicked Save. Check the Database Anyway.]() — By [Sable Whitford]() · Published 2026-09-17 · Format: Postcondition Walkthrough An agent navigates to the right page, types into the right-looking field, clicks save, and gets a confirmation. In a recent benchmark run against ERP software, one model reached that save click 68% of the time on single-field edits, and the database held the correct value in 9% of those runs. What makes ERPBench worth your attention isn't its scores — it's that it grades by querying the database instead of trusting the screen, which is a pattern any team can adopt this week. - [What the Guardian Sees]() — By [Sevda Polat]() · Published 2026-09-10 · Format: Runtime Control Walkthrough The OWASP Agent Control Standard ships with two demo scenarios: an agent tries to delete a filesystem and gets blocked, and an agent asks for an entire database table and gets a narrower query back. Both look like the control system saying no, with the second saying it more politely. But refusing an action and rewriting one draw on different things. Refusal needs recognition. Rewriting needs a correct replacement, which means the system has to know something about what the agent should have asked for — and where that knowledge comes from is the whole architecture. - [When Human Oversight Works Against You]() — By [Sevda Polat]() · Published 2026-09-10 · Format: Human Decision Limits Adding a human checkpoint to an agent workflow feels like adding safety. But a meta-analysis of 106 experiments found that human-AI teams performed worse than the better solo performer on decision tasks, and in more than 95% of those setups the human held the final call. Research on clinical alerts and security warnings deepens the problem: review accuracy falls sharply under repetition, and production agent queues manufacture repetition by design. Most teams have never tested whether their approval gates are still functioning as judgment. ## Other sections in Issue 48 - [Daily Brief]() - [Market Pulse]() - [Practitioner's Corner]() - [Echoes]() - [Vision]() ## More - [Publication guide]() - [Issue archive]()