feat: agent testing framework + parameter country filter #51
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Reduces agent turns for parameter lookups by allowing country filtering. Updated system prompt with parameter search tips.
…king) Reorganised test categories: - Parameter lookups are now separate from household calcs - Economy-wide tests are actual budgetary/distributional analyses
Allows agent to get just the current value with current=true
Key improvements: - Fix model name in system prompt (policyengine-uk with hyphen) - Add case-insensitive search using ILIKE for parameters and variables - Update API docstrings with correct model names Agent can now find UK personal allowance in 3 turns vs 10 baseline. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Adds infrastructure for testing and improving the agent's efficiency at answering policy questions.
API improvements
/parameters/tax_benefit_model_namefilter for country filtering/variables/searchandtax_benefit_model_namefilters/datasets/tax_benefit_model_namefilter/parameter-values/current=truefilter to get only current valuesOther changes
docs/AGENT_TESTING.mdto track ongoing workBaseline measurements (before these changes)
The main issue is parameter lookups getting mixed UK/US results. The country filter should significantly reduce turns.