Excel

Teaching Coding Agents to do Spreadsheets - Nuno Campos, Witan Labs

Jul 8, 2026 · 19:09

Nuno Campos from Witan Labs explains how his team spent four months teaching coding agents to master spreadsheets, raising accuracy from 50% to 92% on a financial analysis benchmark. Key failures included a rigid three-agent architecture and standalone representations like SQL and XML. The breakthrough was replacing 15 separate tools with a single JavaScript repo tool offering persistent state and code-mode semantics, enabling agents to combine multiple operations in one call and drastically reduce timeouts. The team built high-fidelity formula and rendering engines to close the verification loop, and added domain knowledge prompts to focus the model. For evaluation, they moved from LLM-as-judge to deterministic comparisons using golden spreadsheets. Campos urges practitioners to replace many tool calls with real scripting languages, invest in feedback loops, and regularly revisit interfaces as model capabilities evolve.

The Pipeline Is Dead - Iris ten Teije, Sky Valley Ambient Computing

Jul 7, 2026 · 19:50

Iris ten Teije, co-founder of Differ, argues that the traditional software pipeline—built on one frozen artifact for everyone—is dying because producing code changes has become nearly free. This shift enables per-user adaptive software: instead of one codebase shipped to all, a canonical stem plus bounded, isolated, and reversible divergences adapt live per user. She explains how this dissolves the line between development and distribution, using examples like a CRM that learns an investor’s intro paths and skips unused fields. Key challenges include provenance (every divergence must be attributable and inspectable), correctness testing at scale, desirability measurement, and coordination—not merging code but merging intent and outcome. The hard part isn’t AI-generated code; it’s the observability, validation, and isolation that make per-user versions safe rather than terrifying.

How LLMs work for Web Devs: GPT in 600 lines of Vanilla JS - Ishan Anand

Jul 13, 2025 · 1:41:34

Ishan Anand shows that GPT-2 small implemented in 600 lines of vanilla JavaScript makes LLMs understandable for web developers without ML backgrounds. He explains tokenization via byte-pair encoding, 768-dimensional embeddings representing semantic meaning via co-occurrence, and the Transformer's attention mechanism that lets tokens share context. The multi-layer perceptron learns next-token prediction through backpropagation, while the language head converts embeddings to token probabilities using softmax. Anand demonstrates each step—tokenization, embedding lookup, positional encoding, attention, MLP, and output—in a browser debugger, and notes that GPT-2's architecture underpins ChatGPT, with innovations like scale, supervised fine-tuning, and RLHF. The workshop provides an intuitive mental model of Transformers, turning perceived AI magic into understandable machinery.

Building AI Agents that actually automate Knowledge Work - Jerry Liu, LlamaIndex

Jun 24, 2025 · 17:57

Jerry Liu, CEO of LlamaIndex, argues that building AI agents which actually automate knowledge work requires a combination of really good tools and carefully tailored agent reasoning, moving beyond naive RAG to a 'document toolbox' that includes parsing, extraction, indexing, and manipulation of complex unstructured data like PDFs, Excel, and PowerPoints. He introduces two main agent categories: assistive agents (chat-based, human-in-the-loop, unconstrained reasoning) and automation agents (batch-processing, constrained workflows, less human oversight). A key new capability is an Excel agent that uses reinforcement learning to learn a semantic map of unnormalized spreadsheets, achieving 95% accuracy on data transformation, surpassing the 75% baseline of LLMs with code interpreter and even human baselines of 90%. Real-world examples include financial due diligence combining automation (inhaling financial data) and assistant interfaces (analyst co-pilot), enterprise search with specialized agentic RAG, and technical data sheet injection for a global electronics company that reduced weeks of manual work to an automated extraction pipeline. Liu emphasizes that the right preprocessing…

Code Generation and Maintenance at Scale: Morgante Pell

Oct 17, 2024 · 18:54

Morgante Pell, founder of Grit, argues that AI agents for code generation must be built for modifying large existing codebases rather than generating new apps, and that combining static analysis with AI enables reliable migrations at scale. Grit has merged more PRs than any other company by focusing on supercharging top engineers, using GritQL to precisely find code via syntactic and semantic queries, and relying on compilers like TSC to catch errors that LLMs miss. They overcome slow enterprise builds (10 minutes for type checking) by precomputing in-memory indexes and using Firecracker to snapshot and fork environments for parallel agent execution, achieving PRs with only a few iterations. For editing, they developed a custom 'loose search and replace' format to avoid expensive full-file generation and LLM laziness. This approach allowed one customer to complete a multi-year OpenTelemetry migration in a week with under 100 developer hours. Morgante envisions future UIs that let engineers manage entire codebases like SimCity.

Decoding the Decoder LLM without de code: Ishan Anand

Aug 9, 2024 · 17:08

Ishan Anand demonstrates how decoder-based LLMs like GPT-2 work internally using a fully functional spreadsheet implementation. He explains tokenization (e.g., 're-injury' splitting into 'rain' and 'injury' due to subword units), 768-dimensional embeddings, multi-headed attention where tokens look backward (e.g., 'he' focuses 0.48 on 'Mike'), and the multi-layer perceptron with matrix multiplies (MMULT). He shows residual connections creating an information superhighway and uses logit lens to reveal layer-by-layer predictions (e.g., 'Wednesday' appears early but only rises to top probability at later layers). Finally, he injects a sparse autoencoder feature vector for 'Jedi' into the residual stream, steering GPT-2 to output 'lightsaber' instead of 'phone', and contrasts this with alternative steering methods like representation engineering and activation steering.

Climbing the Ladder of Abstraction: Amelia Wattenberger

Nov 3, 2023 · 16:47

Amelia Wattenberger, a designer at Adept, argues that AI can augment knowledge work by enabling users to 'zoom out' on information across different levels of abstraction, much like Google Maps hides detail at higher zoom levels. She reframes augmentation as composed of smaller automations, using the example of spreadsheets automating calculations so accountants can focus on analyzing numbers. Wattenberger demonstrates a prototype that uses LLMs to summarize paragraphs of Peter Pan into single sentences at higher zoom levels, and sketches how Adept's AI could extract key factors like Wi-Fi speed and walking distance from Airbnb and hotel listings, presenting them in customizable views and even a scatter plot for comparing 50 listings at once. The talk emphasizes that structured interfaces around AI models—not just chatbots—will transform how we work, and that Adept is building AI to automate tedious tasks while keeping users in control.