Datasette Agent gains app tagging and query management in 0.3a0
Source published ·Modelwire updated
Original coverage: Simon Willison ↗·How Modelwire adds context
The development
Datasette Apps 0.3a0 deepens the integration between Datasette and Datasette Agent, enabling LLM-driven application development within a database-native environment. The release adds autocomplete tagging for apps in Agent chat and new APIs for managing stored queries, lowering friction for non-developers to build custom data interfaces through conversational AI. This represents a meaningful step toward embedding generative AI into data infrastructure workflows, where the LLM acts as a scaffolding layer between user intent and application code.
Modelwire’s AI-generated summary of coverage from Simon Willison.
Modelwire analysis
Analyst takeOur AI-generated reading of the wider context and the next developments to watch.
The release pairs autocomplete tagging with stored query APIs, but the real signal is timing: this ships four days after datasette-llm 0.1a10 fixed model filtering constraints and one day after the LLM CLI tool reached 0.37. Willison is shipping reliability fixes and UX polish in lockstep, suggesting the bottleneck has shifted from capability to usability and operational safety.
The Zendesk and Heimstaden case studies (late October) show enterprises running LLM agents at scale across hundreds of applications and users. But the arXiv study on text-to-SQL agents (November 2) exposed a hard constraint: only 25% of agent configurations meet acceptance criteria in production. Datasette-apps 0.3a0 addresses this gap by lowering the friction for non-developers to build and iterate on custom interfaces, reducing reliance on agent autonomy for the full task lifecycle. The stored query APIs matter because they let users encode domain logic upfront rather than asking the LLM to infer it each time.
If Willison ships a datasette-apps 0.4 release within six weeks that includes versioning or rollback for stored queries, that confirms the next friction point is managing query drift as non-technical users iterate. If adoption stalls at the current release, it signals that even reduced friction isn't enough to move beyond early adopters in enterprise settings.
This interpretation is generated from the summary above and the archive coverage cited below. Our methodology · Report an error
Coverage behind this analysis
These archive entries ground the connection in our analysis. They are ordered by source publication date, with links to our coverage and the original sources.
·arXiv cs.CL
LLM agents fail to meet enterprise engineering standards in requirement-to-delivery test
A new study evaluates whether LLM agents can function as forward-deployed engineers, handling both customer requirement discovery and post-training delivery in enterprise settings. Testing across 15 models on a realistic text-to-SQL task reveals a significant capability gap: top performers discover over 80% of hidden requirements, while open-weight models plateau at 40-50%. More critically, only 25%…
MentionsDatasette · Datasette Apps · Datasette Agent · Simon Willison
How this coverage is produced
Modelwire uses AI to generate summaries and context from source headlines, snippets, and selected archive coverage. Automated checks do not verify every claim, and items are not routinely reviewed by a person before publication. Zacaria Solis operates the site. Read the linked source for the full evidence and report errors through our corrections process.
Modelwire summarizes, we don’t republish. Simon Willison originally reported this story as “datasette-apps 0.3a0”. The full content lives on simonwillison.net. If you’re a publisher and want a different summarization policy for your work, see our takedown page.