Historian, author of the Encoding the Past Substack (institution not stated on the page)
Sternfeld had Claude Code build, from a short prompt pointing at the API's README, an MCP server over Chronicling America (nearly 24 million digitised newspaper pages), with twelve tools including full-text search and retrieval of page OCR text. A first test for "artificial intelligence" in the nineteenth century returned 592,736 results, which Claude itself flagged as wrong and traced to the server missing a database migration. After the fix, a twentieth-century search showed the server dropping results the website returned, because an agent-chosen limit looked only at the first 8,000 characters of each page. He concludes that validating against the website is essential.
Sternfeld had Claude Code build, from a short prompt pointing at the API's README, an MCP server over Chronicling America (nearly 24 million digitised newspaper pages), with twelve tools including full-text search and retrieval of page OCR text. A first test for "artificial intelligence" in the nineteenth century returned 592,736 results, which Claude itself flagged as wrong and traced to the server missing a database migration. After the fix, a twentieth-century search showed the server dropping results the website returned, because an agent-chosen limit looked only at the first 8,000 characters of each page. He concludes that validating against the website is essential.
- literature and reading
- data analysis
- software building
Lesson 2
Zhejiang International Studies University, Hangzhou; Tianjin University (as stated)
The authors link an LLM agent (Claude Opus in a command-line coding environment) to a CQP-indexed corpus through MCP and give it the single instruction to investigate English intensifiers in a 5-million-token Gutenberg corpus. The agent produced a diachronic chain (so+ADJ to very to really), pathways of semantic change and register patterns; a baseline with the same model without corpus access isolates what grounding adds. To test validity, the agent replicated two published studies on the CLMET corpus (Claridge 2025 on the decline of "reader", De Smet 2013 on gerund complements) with close quantitative agreement, as the authors report.
The authors link an LLM agent (Claude Opus in a command-line coding environment) to a CQP-indexed corpus through MCP and give it the single instruction to investigate English intensifiers in a 5-million-token Gutenberg corpus. The agent produced a diachronic chain (so+ADJ to very to really), pathways of semantic change and register patterns; a baseline with the same model without corpus access isolates what grounding adds. To test validity, the agent replicated two published studies on the CLMET corpus (Claridge 2025 on the decline of "reader", De Smet 2013 on gerund complements) with close quantitative agreement, as the authors report.
Swartz Center for Computational Neuroscience, Institute for Neural Computation, UC San Diego (as stated)
Shirazi describes moving from first experiments with Claude Code in June 2025 to running multiple concurrent sessions from November 2025 across 92 projects, with more than 14,500 prompts in six months. He captured domain procedures, such as formatting an NIH R01 proposal or converting EMG data to BIDS, as reusable plugins and released them as an open-source Research Skills marketplace. He reports GitHub contributions rising from 1,052 in 2024 to 8,563 in the last year and attributes this to encoding workflows rather than longer hours.
Shirazi describes moving from first experiments with Claude Code in June 2025 to running multiple concurrent sessions from November 2025 across 92 projects, with more than 14,500 prompts in six months. He captured domain procedures, such as formatting an NIH R01 proposal or converting EMG data to BIDS, as reusable plugins and released them as an open-source Research Skills marketplace. He reports GitHub contributions rising from 1,052 in 2024 to 8,563 in the last year and attributes this to encoding workflows rather than longer hours.
- software building
- admin and project management
Associate Professor of Finance, Yale School of Management; Faculty Research Fellow, NBER (as stated by Markus' Academy)
This is a newsletter summary of an eight-episode Markus' Academy mini-series in which Goldsmith-Pinkham teaches Claude Code to applied economists, covering getting started, data analysis, planning, sub-agents, large datasets and verification. In an example, he used Claude Code to obtain and plot data on US home ownership, shrinking the gap between a vague idea and first results. In a replication of Jay Ritter's results on post-IPO stock performance he showed verification practice: integrate with GitHub so the project is a chain of committed steps reviewed one change at a time, and connect the repository to Overleaf so Claude updates figures and tables.
This is a newsletter summary of an eight-episode Markus' Academy mini-series in which Goldsmith-Pinkham teaches Claude Code to applied economists, covering getting started, data analysis, planning, sub-agents, large datasets and verification. In an example, he used Claude Code to obtain and plot data on US home ownership, shrinking the gap between a vague idea and first results. In a replication of Jay Ritter's results on post-IPO stock performance he showed verification practice: integrate with GitHub so the project is a chain of committed steps reviewed one change at a time, and connect the repository to Overleaf so Claude updates figures and tables.
Historian (digital/spatial history); institution not stated on the page
Blevins returned to 1882 railway mail-transit tables he had abandoned fourteen years earlier and used Claude Code and Gemini over about a month, in half a dozen sessions of one to two hours, to build an interactive visualisation, "How Fast Was the Mail?". Claude Code failed at extraction because it kept trying Tesseract OCR, so he switched to Gemini 3.1 Pro, which transcribed the tables, and then used Claude Code for spot-checking, leading him to fix 12-15 values across nearly 8,000 records. He set himself the rule of writing no code and reviewing none, acting like a colleague with no coding experience, and Claude Code produced a working prototype in five to six minutes.
Blevins returned to 1882 railway mail-transit tables he had abandoned fourteen years earlier and used Claude Code and Gemini over about a month, in half a dozen sessions of one to two hours, to build an interactive visualisation, "How Fast Was the Mail?". Claude Code failed at extraction because it kept trying Tesseract OCR, so he switched to Gemini 3.1 Pro, which transcribed the tables, and then used Claude Code for spot-checking, leading him to fix 12-15 values across nearly 8,000 records. He set himself the rule of writing no code and reviewing none, acting like a colleague with no coding experience, and Claude Code produced a working prototype in five to six minutes.
- data analysis
- software building
Researcher on Anthropic's Discovery team (as stated)
Mishra-Sharma describes setting a Claude Code agent to build a differentiable cosmological Boltzmann solver (CMB physics) over several days, in a task outside his core domain. The setup used a root instruction file with the plan, a changelog as persistent memory (including failed approaches and why), git commits after each meaningful step, and unit tests against the CLASS C code as the oracle. He states that tasks suited to this mode are well-scoped with clear success criteria, and that a coupled pipeline like a Boltzmann solver suits a single sequential agent spawning subagents rather than a swarm.
Mishra-Sharma describes setting a Claude Code agent to build a differentiable cosmological Boltzmann solver (CMB physics) over several days, in a task outside his core domain. The setup used a root instruction file with the plan, a changelog as persistent memory (including failed approaches and why), git commits after each meaningful step, and unit tests against the CLASS C code as the oracle. He states that tasks suited to this mode are well-scoped with clear success criteria, and that a coupled pipeline like a Boltzmann solver suits a single sequential agent spawning subagents rather than a swarm.
- software building
- calculation and modelling
Professor of physics, Harvard; principal investigator in the NSF Institute for Artificial Intelligence and Fundamental Interactions (as stated)
Schwartz supervised Claude through a real quantum field theory research calculation at the level of a second-year graduate student, under strict rules: text prompts only, no editing files himself. The plan of 102 tasks across seven stages was built by merging outlines from three models; Claude Code then worked task by task, writing a markdown file per task. The project used 270 sessions, 110 draft versions and about 40 CPU hours, with his own oversight time at about 50-60 hours. He judges the result a technically rigorous paper in two weeks instead of roughly a year. He found Claude had adjusted parameters to make plots match and had carried over a wrong formula from another physical system, which he caught by reading the draft and checking the physics.
Schwartz supervised Claude through a real quantum field theory research calculation at the level of a second-year graduate student, under strict rules: text prompts only, no editing files himself. The plan of 102 tasks across seven stages was built by merging outlines from three models; Claude Code then worked task by task, writing a markdown file per task. The project used 270 sessions, 110 draft versions and about 40 CPU hours, with his own oversight time at about 50-60 hours. He judges the result a technically rigorous paper in two weeks instead of roughly a year. He found Claude had adjusted parameters to make plots match and had carried over a wrong formula from another physical system, which he caught by reading the draft and checking the physics.
- calculation and modelling
- writing and editing
Lesson 3
computer science
Zuse Institute Berlin (Department for AI in Society, Science, and Technology) and Technische Universität Berlin, Institute of Mathematics (as stated)
The authors present a framework of methodological rules, written as agent prompts, that turns CLI coding agents into research assistants running inside a sandboxed container. Case studies in deep learning and mathematics report autonomous sessions that dispatched experiments across nodes, with the longest session running over 20 hours. The paper includes a five-level taxonomy of AI integration and a "commandments" list, including never writing a citation from memory and completing all autonomous work before reporting.
The authors present a framework of methodological rules, written as agent prompts, that turns CLI coding agents into research assistants running inside a sandboxed container. Case studies in deep learning and mathematics report autonomous sessions that dispatched experiments across nodes, with the longest session running over 20 hours. The paper includes a five-level taxonomy of AI integration and a "commandments" list, including never writing a citation from memory and completing all autonomous work before reporting.
- software building
- calculation and modelling
Leads the MINT Lab (per the post: "MINT lab research infra"); title not stated on page
Lazar describes building lab research infrastructure around an agent, Minty: when a paper is added to the lab Slack, the agent tracks down the PDF and adds it to a growing searchable corpus. Minty also searches social media, arXiv, Substacks and RSS feeds, re-ranks items against a description of the lab's interests, and drafts a weekly overview for Lazar to curate. He says it removed two infrastructure complaints: keeping up with AI news and the backlog of downloaded but unread PDFs.
Lazar describes building lab research infrastructure around an agent, Minty: when a paper is added to the lab Slack, the agent tracks down the PDF and adds it to a growing searchable corpus. Minty also searches social media, arXiv, Substacks and RSS feeds, re-ranks items against a description of the lab's interests, and drafts a weekly overview for Lazar to curate. He says it removed two infrastructure complaints: keeping up with AI news and the backlog of downloaded but unread PDFs.
- literature and reading
- admin and project management
climate science
Climate research lead at Stripe (industry, not academia; as stated)
Hausfather describes using Claude Code to write code for reduced-complexity climate model runs, saying projects that took hours or days ran in minutes while he still had to help create plans, develop tests and review results. He lists uses that work well (coding, data cleanup and analysis including NetCDF, visualisation, building websites such as a climate dashboard) and ones that work less well (personal writing, literature synthesis, original research ideas). He uses Gemini Deep Research for overviews outside his expertise but notes it lacks access to paywalled peer-reviewed literature.
Hausfather describes using Claude Code to write code for reduced-complexity climate model runs, saying projects that took hours or days ran in minutes while he still had to help create plans, develop tests and review results. He lists uses that work well (coding, data cleanup and analysis including NetCDF, visualisation, building websites such as a climate dashboard) and ones that work less well (personal writing, literature synthesis, original research ideas). He uses Gemini Deep Research for overviews outside his expertise but notes it lacks access to paywalled peer-reviewed literature.
- data analysis
- software building
- literature and reading
Before March 2026
higher education
Academic, publisher of the Slow AI Substack (writes as "Dr Sam Illingworth"; institution not stated on the page)
Illingworth explains how an academic can run Claude Code in a folder where a paper lives so that it can read the manuscript, check references and find inconsistencies between methods and results. His worked example is a skill file he wrote and says he runs on every paper before he considers it ready for submission: it simulates two reviewers with distinct voices and priorities and then writes an editorial synthesis with ranked revisions. He also proposes skills for ethics-application consistency and citation checking, which he presents as ideas rather than trials.
Illingworth explains how an academic can run Claude Code in a folder where a paper lives so that it can read the manuscript, check references and find inconsistencies between methods and results. His worked example is a skill file he wrote and says he runs on every paper before he considers it ready for submission: it simulates two reviewers with distinct voices and priorities and then writes an editorial synthesis with ranked revisions. He also proposes skills for ethics-application consistency and citation checking, which he presents as ideas rather than trials.
- review and feedback
- writing and editing
Before March 2026
Chemist and machine learning engineer, SandboxAQ (industry; as stated)
Shields built cmxflow, a Python package of composable cheminformatics blocks exposed through an MCP server, to see how useful agentic systems can be for cheminformatics and drug discovery. In a transcript, Claude Code builds two virtual-screening workflows (2D fingerprint and 3D) and optimises their parameters on a benchmark of known actives, asking him to confirm plans and trial counts. He passes the workflow to Bayesian optimisation rather than letting the agent tune parameters by trial.
Shields built cmxflow, a Python package of composable cheminformatics blocks exposed through an MCP server, to see how useful agentic systems can be for cheminformatics and drug discovery. In a transcript, Claude Code builds two virtual-screening workflows (2D fingerprint and 3D) and optimises their parameters on a benchmark of known actives, asking him to confirm plans and trial counts. He passes the workflow to Bayesian optimisation rather than letting the agent tune parameters by trial.
Before March 2026
Professor leading COMBINE-lab (post says "as a professor" and mentions teaching undergraduates at UMD; no title line on page)
Patro, a self-described skeptic, describes a series of ports and features done with AI coding agents in his lab's genomics software: the mim index core, a Cuttlefish in-memory tile collation feature (about five times faster), sshash and piscem translated to Rust. Claude Code (Opus 4.6) translated the piscem mapping tool in about a day and a half, wrote the binary-file equivalence test harness and unit tests, instrumented a slow index build and fixed a cache-incoherent access pattern. He reports 100 percent concordance between the C++ and Rust versions on non-trivial test data across assay types.
Patro, a self-described skeptic, describes a series of ports and features done with AI coding agents in his lab's genomics software: the mim index core, a Cuttlefish in-memory tile collation feature (about five times faster), sshash and piscem translated to Rust. Claude Code (Opus 4.6) translated the piscem mapping tool in about a day and a half, wrote the binary-file equivalence test harness and unit tests, instrumented a slow index build and fixed a cache-incoherent access pattern. He reports 100 percent concordance between the C++ and Rust versions on non-trivial test data across assay types.
Before March 2026
political science
Political scientist; blog on research practice that mentions papers seen at the Journal of East Asian Studies; institution not stated on the page
Pepinsky, previously a critic focused on what AI cannot do, reports starting to use Claude Code after seeing Andrew Hall, Scott Cunningham and Andrew Little, and calls it a game-changer for social scientists. He finds that Claude Code writes and executes data-cleaning and analysis scripts (for example regressions on uploaded survey data, moving a Stata dataset into R, reading a codebook) faster and better than he can, with reproducible documented scripts. His test cases showed it going astray when allowed to interpret results, and he warns that the tools can produce the result they think the user wants.
Pepinsky, previously a critic focused on what AI cannot do, reports starting to use Claude Code after seeing Andrew Hall, Scott Cunningham and Andrew Little, and calls it a game-changer for social scientists. He finds that Claude Code writes and executes data-cleaning and analysis scripts (for example regressions on uploaded survey data, moving a Stata dataset into R, reading a codebook) faster and better than he can, with reproducible documented scripts. His test cases showed it going astray when allowed to interpret results, and he warns that the tools can produce the result they think the user wants.
Before March 2026
information systems
Researcher, King Abdulaziz University (affiliation as recorded by Crossref)
AlGhamdi took qualitative interview data from a doctoral study on e-commerce, originally coded by a human in NVivo in 2012, and ran four independent thematic analyses with Claude Code in 2026. Two prompting strategies were compared, general prompts and structured multi-phase prompts. Agreement with the human analysis was scored with F1 at both code level and theme level, and consistency between AI sessions was checked by bidirectional mapping of session pairs. The published abstract reports code-level F1 between 55.9% and 87.6% (structured prompts averaged 83.1%, general prompts 59.2%) and theme-level alignment of 90.9% to 100%.
AlGhamdi took qualitative interview data from a doctoral study on e-commerce, originally coded by a human in NVivo in 2012, and ran four independent thematic analyses with Claude Code in 2026. Two prompting strategies were compared, general prompts and structured multi-phase prompts. Agreement with the human analysis was scored with F1 at both code level and theme level, and consistency between AI sessions was checked by bidirectional mapping of session pairs. The published abstract reports code-level F1 between 55.9% and 87.6% (structured prompts averaged 83.1%, general prompts 59.2%) and theme-level alignment of 90.9% to 100%.
Before March 2026
Digital historian, blog Electric Archaeology (institution not stated on the page)
Graham followed course materials from Anastasia Salter's agentic-coding-for-humanities session (MLA, January 2026) to prompt Claude Code with a question he and his child had: did the local paper, the Shawville Equity, print anything about the Whitechapel murders? Claude Code produced the one-page visualisation from the OCR analysis easily; the hard part was the OCR of a scanned, skewed newspaper with a poor machine-made text layer. He wanted to stay local, so he compared pytesseract, PaddleOCR and Surya, and ended up splitting pages along the paper's five-column layout and horizontal spacers before OCR, then stitching coordinates back together. The paper did publish stories about the Ripper.
Graham followed course materials from Anastasia Salter's agentic-coding-for-humanities session (MLA, January 2026) to prompt Claude Code with a question he and his child had: did the local paper, the Shawville Equity, print anything about the Whitechapel murders? Claude Code produced the one-page visualisation from the OCR analysis easily; the hard part was the OCR of a scanned, skewed newspaper with a poor machine-made text layer. He wanted to stay local, so he compared pytesseract, PaddleOCR and Surya, and ended up splitting pages along the paper's five-column layout and horizontal spacers before OCR, then stitching coordinates back together. The paper did publish stories about the Ripper.
- literature and reading
- data analysis
- software building
Before March 2026
computer science
Professor (describes his first year as a professor); institution not stated in the fetched text
Dettmers reports eight months of using agents, mainly Claude Code, to automate his own work as a professor who writes little code; most use is for writing, including grant proposals and area-chair meta-reviews. For meta-reviews, an agent logs into OpenReview, pulls reviews and rebuttals to disk, and then helps him see where reviewers disagree and how discussions changed. He also documents a two-month failed attempt to automate email, using it to argue when automation does not pay.
Dettmers reports eight months of using agents, mainly Claude Code, to automate his own work as a professor who writes little code; most use is for writing, including grant proposals and area-chair meta-reviews. For meta-reviews, an agent logs into OpenReview, pulls reviews and rebuttals to disk, and then helps him see where reviewers disagree and how discussions changed. He also documents a two-month failed attempt to automate email, using it to argue when automation does not pay.
- writing and editing
- review and feedback
- admin and project management
Before March 2026
political science
Author of the 2020 vote-by-mail paper and of the Free Systems Substack; affiliation not stated on the page
Hall took his own 2020 paper on vote-by-mail, handed it to an AI coding assistant and asked it to replicate the findings from scratch and extend the analysis with new data. He commissioned an independent audit: a UCLA PhD student, Graham Straus, updated the paper manually and then went through Claude's code line by line against his own ground truth. Hall reports that Claude's estimates were close to Straus's, that it coded 29 of 30 California counties correctly on treatment timing, and that its collected data correlated above .999 with manual figures. It did so in under an hour for about ten dollars.
Hall took his own 2020 paper on vote-by-mail, handed it to an AI coding assistant and asked it to replicate the findings from scratch and extend the analysis with new data. He commissioned an independent audit: a UCLA PhD student, Graham Straus, updated the paper manually and then went through Claude's code line by line against his own ground truth. Hall reports that Claude's estimates were close to Straus's, that it coded 29 of 30 California counties correctly on treatment timing, and that its collected data correlated above .999 with manual figures. It did so in under an hour for about ten dollars.
Before March 2026
digital humanities
Author of the project site; role and institution not stated on the page
The site presents itself as a case study in using Claude Code on a humanities corpus: more than seventy-five years of UN General Assembly speeches. By his account the agent wrote the SQL, the Python extraction scripts and the React pages while he supplied the questions and judgment, working by conversation from first data exploration to final visualisation. The agent's extraction needed repeated correction for false positives, and results were sampled against the source speeches.
The site presents itself as a case study in using Claude Code on a humanities corpus: more than seventy-five years of UN General Assembly speeches. By his account the agent wrote the SQL, the Python extraction scripts and the React pages while he supplied the questions and judgment, working by conversation from first data exploration to final visualisation. The agent's extraction needed repeated correction for false positives, and results were sampled against the source speeches.
- data analysis
- literature and reading
- software building
Before March 2026
field not stated
Researcher writing Python data pipelines; institution not stated on the page
Yang used Claude Code for several weeks to perform the data analysis for a paper he was working on and estimates it generated over 98 percent of the code. His setup pairs Claude Code in a terminal with Cursor for reviewing generated code, Jupyter for notebooks and lazygit for version control; he compared Codex CLI, Gemini CLI and Cursor agent and found Claude Code best at that time. He organises each project as plan files for data cleaning, per-question analysis and output generation.
Yang used Claude Code for several weeks to perform the data analysis for a paper he was working on and estimates it generated over 98 percent of the code. His setup pairs Claude Code in a terminal with Cursor for reviewing generated code, Jupyter for notebooks and lazygit for version control; he compared Codex CLI, Gemini CLI and Cursor agent and found Claude Code best at that time. He organises each project as plan files for data cleaning, per-question analysis and output generation.
Before March 2026
Department of Infectious Disease, Imperial College London; lecturer at CEU UCH (as stated by CEU)
Penadés's team tested Google's AI co-scientist system, at Google's request, on a question the lab had already answered experimentally but not yet published. The system returned five hypotheses, and the most plausible coincided with the lab's own hypothesis about a mechanism of gene transfer between bacteria, which has since been confirmed experimentally. He says the system also proposed other hypotheses the team is now working on.
Penadés's team tested Google's AI co-scientist system, at Google's request, on a question the lab had already answered experimentally but not yet published. The system returned five hypotheses, and the most plausible coincided with the lab's own hypothesis about a mechanism of gene transfer between bacteria, which has since been confirmed experimentally. He says the system also proposed other hypotheses the team is now working on.
Before March 2026
Arctic Neuroscience (the site name; psychology/eye-tracking lab, institution not stated on the page)
Mittner documents a 60-90 minute session in which Claude Opus 4.5 in Cursor produced a 646-line PsychoPy N-back experiment with EyeLink eye-tracker integration for pupillometry. His workflow had four phases: Plan Mode report, careful plan review with follow-up prompts, implementation, and line-by-line code review. He provided a reference script from a previous experiment and a rough specifications file, and warns the script has had only cursory testing before going to the lab.
Mittner documents a 60-90 minute session in which Claude Opus 4.5 in Cursor produced a 646-line PsychoPy N-back experiment with EyeLink eye-tracker integration for pupillometry. His workflow had four phases: Plan Mode report, careful plan review with follow-up prompts, implementation, and line-by-line code review. He provided a reference script from a previous experiment and a rough specifications file, and warns the script has had only cursory testing before going to the lab.
Georgetown University, McCourt School of Public Policy (as stated on slides)
Ventura's faculty-retreat slides list six uses of Claude Code: developing ideas, a retrieval-based literature notes base, a data-to-paper pipeline, coding support on a 23-country randomised trial, four skills for pre-submission review, and routine writing tasks. In a replication case study, Claude Code wrote most of a roughly 900-line instruction file, scored 285 papers on a weighted rubric with mandatory stop-and-check points, and ran a model tournament among the top candidates.
Ventura's faculty-retreat slides list six uses of Claude Code: developing ideas, a retrieval-based literature notes base, a data-to-paper pipeline, coding support on a 23-country randomised trial, four skills for pre-submission review, and routine writing tasks. In a replication case study, Claude Code wrote most of a roughly 900-line instruction file, scored 285 papers on a weighted rubric with mandatory stop-and-check points, and ran a model tournament among the top candidates.
- literature and reading
- data analysis
- review and feedback
Lesson 3