🥳Hi all -- DAAF v3.0.0 is out today, and the two features I get asked about most are FINALLY here: Full R support, and the ability to run DAAF on your OpenAI API key/subscription (yes, that means GPT-5.6 Sol working away inside Claude Code!!). Plus Fable support! A quick tour:

I've been running workshops on AI for academics across the country the past few months, and the same question has come up in every single room: So... what are we going to do about teaching and learning? There are no easy answers, but I want to offer a few distilled suggestions:

🥳 DAAF v2.1.0 is live today! With it, I feel strongly that DAAF is now finally the best, safest, AND easiest (+free!) way to get started w/ Claude Code for anyone doing data analysis of any kind. v2.1.0 was focused on three core features for quality of life and ease of use:

🥳It's been about a month since I first launched DAAF, the Data Analyst Augmentation Framework... which means now is as good a time as any to celebrate the launch of DAAF v2.0.0 and re-introduce you all to what I hope is a more useful, more usable, and far more flexible tool for any researcher across disciplines working with data in their work!! What is DAAF? DAAF is a free and open-source instructions framework for Claude Code that helps skilled researchers rapidly scale their expertise and accelerate data analysis across any domain with AI assistance -- without sacrificing the transparency, rigor, or reproducibility that good science demands. DAAF sits between you and Claude Code to automatically and consistently help Claude think more like a *responsible* and *rigorous* researcher by: - Enforcing strict auditability and reproducibility standards for all work, thus allowing you to verify everything Claude does on your behalf - Preventing potentially dangerous unintended file access and editing, by sandboxing Claude with strict protections and logging traces - Setting high standards of care, rigor, and thoroughness in all data analysis, by forcing Claude to comment, verify, and review all analytic code before you ever see it - Embedding best practices for a wide variety of research methodologies like causal inference and geospatial analysis, by providing rich Skills that extend Claude's base capabilities with real research and resources - Collaborating with you, the human expert, directly on all key decisions, thus keeping you firmly in the driver's seat Think of it as a force-multiplying exoskeleton for human researchers -- a tool explicitly designed to augment your hard-earned expertise, not replace it. The goal is to make it easy for researchers to use Claude Code effectively and responsibly. Importantly, DAAF is not and will never be perfect -- but it is already immensely useful, and this is the worst a tool like DAAF will ever be from now on with the help and support of the broader research community. Install and begin using it in as little as 10 minutes from a fresh install with a high-usage Anthropic account!

Reposting for visibility: One of my biggest recent unlocks for improving Claude's performance on tasks is running a "consilience" strategy, and I can't recommend it enough. The basic plan of attack: When you have any given process/task you want Claude to do, have Claude instead launch several agents to do that exact task in parallel (producing parallel outputs in files like output_alpha, output_beta, output_gamma, etc.). Then, ask Claude to run a final alignment/consilience step where it reviews all the separate outputs, assesses strengths/weaknesses across them, and then produces a final harmonized output with all that context together. You can spice this up in a number of ways (more iterations, add a review step, play with multiple harmonization steps almost tournament-style, etc.), but the gameplan is broadly applicable to a ton of tasks. Just be aware it'll eat your usage limits accordingly!

How can we get to a more optimistic AI-empowered future for academia and science? Step 1: As AI allows us to accelerate the production of more and more scientific claims, we *must* center transparency and reproducibility as core requirements for all AI research tooling

Today, I’m launching DAAF, the Data Analyst Augmentation Framework: an open-source, extensible workflow for Claude Code that allows skilled researchers to rapidly scale their expertise and accelerate data analysis by as much as 5-10x -- without sacrificing the transparency, rigor, or reproducibility demanded by our core scientific principles. You (yes, YOU!) can install and begin using it in as little as 10 minutes from a fresh computer with a high-usage Anthropic account (crucial accessibility caveat, unfortunately very expensive!) github.com/DAAF-Contribution… DAAF explicitly embraces the fact that LLM-based research assistants will never be perfect and can never be trusted as a matter of course. But by providing strict guardrails, enforcing best practices, and ensuring the highest levels of auditability possible, DAAF ensures that LLM research assistants can still be immensely valuable for critically-minded researchers capable of verifying and reviewing their work. In energetic and vocal opposition to deeply misguided attempts to replace human researchers, DAAF is intended to be a force-multiplying "exo-skeleton" for human researchers (i.e., firmly keeping humans-in-the-loop). The base framework comes ready out-of-the-box to analyze any or all of the 40+ foundational public education datasets available via the Urban Institute Education Data Portal (educationdata.urban.org/docu…), and is readily extensible to new data domains and methodologies with a suite of built-in tools to ingest new data sources and craft new Skill files at will! With DAAF, you can go from a research question to a shockingly nuanced research report with sections for key findings, data/methodology, and limitations, as well as bespoke data visualizations, with only five minutes of active engagement time, plus the necessary time to fully review and audit the results (see my 10-minute video demo here: youtu.be/ZAM9OA0AlUs). To that crucial end of facilitating expert human validation, all projects come complete with a fully reproducible, documented analytic code pipeline and consolidated analytic notebooks for exploration. Then: request revisions, rethink measures, conduct new sub-analyses, run robustness checks, and even add additional deliverables like interactive dashboards, policymaker-focused briefs, and more -- all with just a quick ask to Claude. And all of this can be done *in parallel* with multiple projects simultaneously. By open-sourcing DAAF under the GNU LGPLv3 license as a forever-free and open and extensible framework, I hope to provide a foundational resource that the entire community of researchers and data scientists can use, benefit from, learn from, and extend via critical conversations and collaboration together. By pairing DAAF with an intensive array of educational materials, tutorials, blog deep-dives, and videos via project documentation and the DAAF Field Guide Substack (daafguide.substack.com/ – MUCH more to come!), I also hope to rapidly accelerate the readiness of the scientific community to genuinely and critically engage with AI disruption and transformation writ large. I don't want to oversell it: DAAF is far from perfect (much more on that below!). But it is already extremely useful, and my intention is that this is the worst that DAAF will ever be from now on given the rapid pace of AI progress and (hopefully) community contributions from here. More than anything, I just hope all of this work can somehow be useful for my many peers and colleagues trying to "catch up" to this rapidly developing (and extremely scary) frontier. It's a wild time, but we need as many people informed and at the table together as possible. Never used Claude Code? No idea where you'd even start? My full installation guide walks you through every step -- but hopefully this video shows how quick a full DAAF installation can be from start-to-finish. Just 3mins! youtube.com/watch?v=jqkVLXA1… Learn more about my vision for DAAF, what makes DAAF different from other attempts to create LLM research assistants, what DAAF currently can and cannot do as of today, how you can get involved, and how you can get started with DAAF yourself! github.com/DAAF-Contribution… So there it is. I am absolutely as surprised and concerned as you are, believe me. With all that in mind, I would *love* to hear what you think, what your questions are, what you’re seeing if you try testing it out, and absolutely every single critical thought you’re willing to share, so we can learn on this frontier together. Thanks for reading and engaging earnestly!