#Datasette Agent
22 related articles
·2 min
Datasette Agent 0.2a0: A New Mechanism for AI Agents to Ask Users Questions During Tool Execution
Datasette Agent 0.2a0 introduces an ask_user() mechanism enabling AI agents to pause during tool execution and ask users questions, with three interaction modes and a save_query tool for human approval.
Read more →
Tech Frontiers·2 min
Datasette Agent: An Open-Source AI Assistant for Querying Databases with Natural Language
Simon Willison releases Datasette Agent, combining LLM with Datasette to enable natural language database queries, plugin extensions, and local model support for personal data analysis.
Read more →
Tech Frontiers·2 min
datasette-agent-sprites: A Deep Dive into the AI Agent Sandbox Execution Plugin
Simon Willison releases datasette-agent-sprites plugin for secure AI Agent command execution in Fly Sprites sandbox. Analysis of its architecture, use cases, and significance.
Read more →
sqlite-utils 4.1 Released: The --code …
·7 min
sqlite-utils 4.1 Released: The --code Option, Type Overrides, and AI-Assisted Development in Practice
sqlite-utils 4.1 brings practical new features: the --code option for generating rows via Python, type overrides to solve ZIP-code leading-zero loss, STRICT table mode switching, drop-index, and more. A deep dive into the design and AI-assisted dev workflow.
Read more →
sqlite-utils 4.1 Released: The --code …
·7 min
sqlite-utils 4.1 Released: The --code Option, Type Overrides, and AI-Assisted Development in Practice
sqlite-utils 4.1 brings practical new features: the --code option for generating rows with Python, field type overrides fixing leading-zero ZIP codes, STRICT table mode switching, drop-index, and more. A deep dive into each design and the AI-assisted dev workflow.
Read more →
ChatGPT Work Deep Dive: The Cloud-Loca…
·3 min
ChatGPT Work Deep Dive: The Cloud-Local Split and What It Means for Users
ChatGPT Work runs in the cloud on web/mobile but accesses local files on desktop — and they don't sync. A deep dive into the split design, UX tradeoffs, and broader AI agent challenges.
Read more →
Meta Muse Spark 1.1 Released: A Deep D…
·4 min
Meta Muse Spark 1.1 Released: A Deep Dive into the First Spark Model with an Open API
Meta officially releases Muse Spark 1.1, the first model in the Spark series to offer an API, with a focus on strengthening agentic tool calling and computer use capabilities.
Read more →
·5 min
Claude Drives the sqlite-utils 4.0 Release: The Real Cost and Collaboration Methodology of AI-Assisted Refactoring
Developer Simon Willison used Claude to ship sqlite-utils 4.0: 37 prompts, 34 commits, $149 API cost — revealing coding agents' real capabilities, cross-model review, and agentic engineering best practices.
Read more →
Building a Coding Agent with LLM: A De…
·3 min
Building a Coding Agent with LLM: A Deep Dive into Simon Willison's llm-coding-agent Experiment
Simon Willison built llm-coding-agent — an open-source Claude Code-style agent — using just two prompts and TDD. Explore its tool design, bootstrapped dev process, and real-world test results.
Read more →
·2 min
Simon Willison Updates WebRTC Voice Tool: Now Supports Document Context Conversations and GPT-Realtime-2
Simon Willison updates his OpenAI WebRTC voice tool with document context support and GPT-Realtime-2, enabling low-latency voice conversations grounded in specific documents.
Read more →
·3 min
Claude Sonnet 4 Invents Its Own Browser Automation: The Wild Debugging Journey of a CSS Bug
Simon Willison shares how Claude Sonnet 4 (Fable) autonomously invented PyObjC screenshots, built a CORS server, and penetrated Shadow DOM to debug a CSS bug — revealing both tool-making power and security risks.
Read more →
·2 min
Datasette 1.0a33 Released: Comprehensive JSON Extras API Expansion and AI-Assisted Development in Practice
Datasette 1.0a33 extends the ?_extra= pattern from tables to queries and rows. Simon Willison uses dual-AI workflow with Claude and GPT to build an interactive API Explorer tool.
Read more →
Product Reviews·1 min
Datasette LLM Accountant: An Open-Source Tool for LLM Usage Tracking and Cost Management
datasette-llm-accountant 0.1a4 released, fixing a response chain tracking bug. This open-source plugin helps developers monitor LLM API calls, token usage, and costs with chain tracking for Agent workflows.
Read more →
Tech Frontiers·2 min
OpenClaw's Six Rename History: Tracing an Open Source Project's Naming Evolution Through Git Commit Records
OpenClaw went through six renames from Warelay to its final name. Simon Willison used a Python script to reconstruct this complete naming evolution from Git commit history.
Read more →
Tech Frontiers·2 min
Datasette Launches Official Blog: Simon Willison Built It from Scratch with OpenAI Codex
Datasette founder Simon Willison launches official blog built with OpenAI Codex Desktop, sharing full AI session transcripts and demonstrating transparent AI-assisted development practices.
Read more →
Tech Frontiers·1 min
LLM 0.32a1 Released: Fixes Critical Bug Where Tool-Calling Conversations Failed to Restore from SQLite
Simon Willison releases LLM CLI tool v0.32a1, fixing a critical bug where tool-calling conversations failed to restore from SQLite. Details on the fix and installation.
Read more →
Tech Frontiers·1 min
LLM 0.32a1 Released: Detailed Fix for Tool-Calling Conversation Storage Bug
Simon Willison releases LLM CLI tool v0.32a1, fixing a critical bug where tool-calling conversations failed to reload from SQLite. Details on the fix and upgrade.
Read more →
Tutorials·3 min
Building an iNaturalist Observation Display Tool Over a Weekend with a Phone + Claude Code: Full Workflow
Simon Willison built an iNaturalist observation display tool from scratch using his phone and Claude Code while camping. Full breakdown of the three-layer data pipeline architecture and AI-assisted mobile development workflow.
Read more →
Tutorials·2 min
Simon Willison's Full Journey: Building a Wildlife Sightings Feature for His Blog Using Claude Code on His Phone
Simon Willison used Claude Code for web on his phone to add iNaturalist wildlife sightings to his blog, going from prototype to production in one day.
Read more →
Tech Frontiers·2 min
LLM 0.32a0 Released: Message Sequences and Typed Streaming Refactor Explained
Simon Willison releases LLM 0.32a0 alpha with message sequence modeling and typed streaming parts, supporting multimodal output and conversation history injection while maintaining backward compatibility.
Read more →