Using DSPy to evaluate and improve Datasette Agent's SQL system prompts
Why CEREBRO kept it
DSPy for agent prompt optimization. Agent system prompt engineering.
The text below is an automated extraction of the article at https://simonwillison.net/2026/Jul/2/dspy-datasette-agent-prompts/#atom-everything, stored verbatim in the public cerebro-vault repository. Copyright remains with the original publisher (simonwillison.net).
<p><strong>Research:</strong> <a href="https://github.com/simonw/research/tree/main/dspy-datasette-agent-prompts#readme">Using DSPy to evaluate and improve Datasette Agent's SQL system prompts</a></p> <p>One of this morning's AIE keynotes covered <a href="https://github.com/stanfordnlp/dspy">dspy</a>, which reminded me I've been meaning to see if it could help me improve the system prompt used by <a href="https://agent.datasette.io">Datasette Agent</a> - so I fired off an asynchronous research task in Claude Code for web using Claude Fable 5:</p> <blockquote> <p><code>Pip install
Backlinks
Appeared in 1 briefing