Skip to content

Add blog post: Bringing AI to policymaking — a chat interface to PolicyEngine UK#1070

Closed
vahid-ahmadi wants to merge 9 commits into
mainfrom
blog/uk-chat-cant-make-up-numbers
Closed

Add blog post: Bringing AI to policymaking — a chat interface to PolicyEngine UK#1070
vahid-ahmadi wants to merge 9 commits into
mainfrom
blog/uk-chat-cant-make-up-numbers

Conversation

@vahid-ahmadi

Copy link
Copy Markdown
Contributor

Adds the research post "Bringing AI to policymaking: a chat interface to PolicyEngine UK" by Vahid Ahmadi and Anthony Volk.

What's here

  • New article app/src/data/posts/articles/uk-chat-cant-make-up-numbers.md
  • posts.json entry (date 2026-06-25; tags uk / featured / technology / ai; authors vahid-ahmadi, anthony-volk)
  • Cover image (reusing the multi-agent-workflows cover for now — to be replaced)

Content

The post explains why every figure comes from the policyengine-uk-compiled microsimulation engine rather than the language model's memory, then a technical section covering:

  • An inline-SVG architecture diagram of the tool-use loop
  • The bounded loop (MAX_ITERATIONS = 30, repeated-identical-call breaker, stop_reason="iteration_cap")
  • The deterministic vs non-deterministic contract
  • Structurally-enforced plan mode (tools omitted from the request)
  • The six typed tools and the version-stamped engine reference

Technical claims were verified against the policyengine-uk-chat runtime source.

@anth-volk — requesting your review, especially on the technical section and the cover image (placeholder for now).

🤖 Generated with Claude Code

vahid-ahmadi and others added 2 commits June 25, 2026 12:11
Add "Bringing AI to policymaking: a chat interface to PolicyEngine UK"
with Vahid Ahmadi and Anthony Volk as co-authors. Reuses the
multi-agent workflows cover image for now.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add high-level technical content adapted from the engineering draft:
an inline-SVG architecture diagram of the tool-use loop, the bounded
loop with its iteration cap and repeated-call breaker, the
deterministic vs non-deterministic contract, structural plan mode,
the six typed tools, and the version-stamped engine reference.

Claims verified against the policyengine-uk-chat runtime; engine
attributed to policyengine-uk-compiled.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@vahid-ahmadi
vahid-ahmadi requested a review from anth-volk June 25, 2026 11:22
@vercel

vercel Bot commented Jun 25, 2026

Copy link
Copy Markdown

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Actions Updated (UTC)
policyengine-app-v2 Ready Ready Preview, Comment Jun 26, 2026 1:39pm
policyengine-calculator Ready Ready Preview, Comment Jun 26, 2026 1:39pm
policyengine-calculator-next Ready Ready Preview, Comment Jun 26, 2026 1:39pm
policyengine-website Ready Ready Preview, Comment Jun 26, 2026 1:39pm

Request Review

…p code block

- Rework the opening to lead with AI's growing role in policymaking
- Set subtitle to a plain description of the chat interface
- Remove the related-work sentence and the tool-loop code block

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Replace the borrowed placeholder with a dark-mode screenshot of the
UK Chat interface ("What's on your mind today?").

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
…label

- Shorten three section headings
- Soften strong/informal phrasings toward neutral language
- Reposition the "result → back into model" diagram label so the
  dashed return arrow no longer crosses it

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
… UK-gov sources

- Lead with the guess-vs-compute contrast; add H1 title
- Drop unsupported "version-stamped" engine-reference claim
- Attribute calculations to the compiled engine (policyengine-uk-compiled)
- Surface the audit-vs-trust contract early; name the failure mode
- Describe input-token routing, single-tool error path, and eval checks
- Add "For technical readers" divider; add free/citable/checkable trust line
- British English (artefact) and trimmed repetition
- Add three UK public-sector sources (GOV.UK AI Playbook, POST, NAO)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
…ep-link citations

- Remove the H1 title (title comes from posts.json) and the "For technical
  readers" and "Constraints" sections
- Group the technical deep-dive under "How it works" with H3 subsections;
  make The architecture and The tool-use loop numbered lists
- Replace the duplicated six-tools prose/table with a single SVG graphic
- Generalise "A Claude model" to "AI tools like Claude or ChatGPT"; drop the
  compiled-build aside and the eval-cross-check sentence
- Deep-link the AI Playbook and add a Wikipedia citation for next-token
  generation, both via #:~:text= fragments
- Move the loop-diagram caption to a lead-in above the diagram; trim repetition
- Update the cover image

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
…ix, cover

- Shorten section/subsection titles to short noun phrases (no interrogatives)
- Replace the six-tools figure with a centred, grouped (Calculate/Support) SVG;
  add a figure lead-in and drop the trailing synthetic-illustration note
- Generalise "Anyone comparing two reforms"; unlink Claude/ChatGPT mention
- Deep-link the POST and NAO citations to their exact sentences (#:~:text=)
- Fix ordered/unordered list rendering: restore list markers that Tailwind
  preflight had reset, so numbered steps show their numbers
- Update the cover image

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@vahid-ahmadi

Copy link
Copy Markdown
Contributor Author

Superseded by #1073, which consolidates all the UK chatbot launch work (blog post, homepage CTA, featured tools, CliffWatch rename) into a single PR.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant