zgbrenner makes Gary's review tables push-button

A suggested next step in a document-review grid now becomes a ready-to-run AI task - but only after the lawyer says go.

workflow

When Gary reviews a batch of documents and spots that a row calls for a recognized task, that suggestion used to just sit there as a label. zgbrenner turned it into a launch point: open the cell, and a button spins up the assistant already loaded with the row's context, the right task selected, and the source document attached.

The discipline is the interesting part. Nothing fires automatically - a confirmation step previews the exact prompt, and the lawyer reviews and sends by hand. The suggestion has to match one of eight known tasks exactly; anything vague, blank or unrecognised shows no button at all. The prompt itself tells the model to treat extracted values as unverified draft and not to invent dates, parties or authorities.

So what Legal-ops leads weighing AI review tools should note the pattern: speed from prefill, safety from a human gate that never lets the machine send on its own.

View this fork on GitHub →

Spotted something wrong? Or know the PR text has fresher detail than the writeup above?

Commits in this thread

1 commit from zgbrenner/gary, oldest first. Source extracted verbatim from the harvested git log.

SHA Subject Author Date

b01092b7 feat: run a Saved Legal Task from a Review Table row Claude 2026-05-20 ↗ GitHub

SHA	Subject	Author	Date
`b01092b7`	feat: run a Saved Legal Task from a Review Table row	Claude	2026-05-20	↗ GitHub
commit body Make the "Suggested Saved Legal Task" column actionable. When Gary suggests a recognized task for a document, a lawyer can launch that task in the assistant prefilled with the row's context. - suggestedTask.ts: maps the eight recognized task names to built-in Saved Legal Task ids. Matching tolerates whitespace, case, tag brackets, and trailing punctuation but is never fuzzy - an unrecognized value resolves to null rather than guessing. Also builds the row-context prompt (task name, matter, document name, extracted fields, and attorney-review safety language). - RunSuggestedTaskModal.tsx: a simple "Run Saved Legal Task?" confirmation with a prompt preview and Open in Assistant / Cancel. - TRSidePanel: shows a "Run Suggested Task" action - only on the Suggested Saved Legal Task column's cell, and only when the value resolves to a recognized task and the cell has finished generating. - TabularReviewView: resolves the row's suggested task, builds the row-context prompt from the row's other cells, and on confirm creates a chat, prefills an assistant draft, and opens it. - Prefill, not auto-run: a new newChatDraft channel on ChatHistoryContext carries a draft (content + workflow + attached document) that ChatInput seeds its initial state from. The lawyer reviews and sends manually - nothing is auto-submitted. ChatView renders an empty-with-draft chat instead of the loading skeleton. - The row's document is attached via the existing chat file mechanism; the document_id rides in the attachment, never in the visible prompt text. No raw internal ids appear in the prompt. - Safety: the prompt instructs Gary to treat the row as draft and unverified, use the uploaded document, not invent facts / dates / legal authorities / deadlines / parties, and flag uncertainty. - Docs: add "Running a Saved Legal Task from a Review Table" to the U.S. lawyer guide; add a terminology-map entry. - Tests: suggestedTask.test.ts covers the eight-task mapping (and that each id is a real assistant built-in), match tolerance, the no-fuzzy-match guarantee, blank/Unknown/None handling, the prompt's attorney-review language, Unknown fallbacks, and the absence of raw internal ids and legacy terminology.

commit body

Make the "Suggested Saved Legal Task" column actionable. When Gary
suggests a recognized task for a document, a lawyer can launch that
task in the assistant prefilled with the row's context.

- suggestedTask.ts: maps the eight recognized task names to built-in
  Saved Legal Task ids. Matching tolerates whitespace, case, tag
  brackets, and trailing punctuation but is never fuzzy - an
  unrecognized value resolves to null rather than guessing. Also
  builds the row-context prompt (task name, matter, document name,
  extracted fields, and attorney-review safety language).
- RunSuggestedTaskModal.tsx: a simple "Run Saved Legal Task?"
  confirmation with a prompt preview and Open in Assistant / Cancel.
- TRSidePanel: shows a "Run Suggested Task" action - only on the
  Suggested Saved Legal Task column's cell, and only when the value
  resolves to a recognized task and the cell has finished generating.
- TabularReviewView: resolves the row's suggested task, builds the
  row-context prompt from the row's other cells, and on confirm
  creates a chat, prefills an assistant draft, and opens it.
- Prefill, not auto-run: a new newChatDraft channel on
  ChatHistoryContext carries a draft (content + workflow + attached
  document) that ChatInput seeds its initial state from. The lawyer
  reviews and sends manually - nothing is auto-submitted. ChatView
  renders an empty-with-draft chat instead of the loading skeleton.
- The row's document is attached via the existing chat file
  mechanism; the document_id rides in the attachment, never in the
  visible prompt text. No raw internal ids appear in the prompt.
- Safety: the prompt instructs Gary to treat the row as draft and
  unverified, use the uploaded document, not invent facts / dates /
  legal authorities / deadlines / parties, and flag uncertainty.
- Docs: add "Running a Saved Legal Task from a Review Table" to the
  U.S. lawyer guide; add a terminology-map entry.
- Tests: suggestedTask.test.ts covers the eight-task mapping (and
  that each id is a real assistant built-in), match tolerance, the
  no-fuzzy-match guarantee, blank/Unknown/None handling, the prompt's
  attorney-review language, Unknown fallbacks, and the absence of raw
  internal ids and legacy terminology.

Capture this thread into my fork

Download a single Markdown prompt that tells Claude how to port every commit above into your working tree — adapting paths and structure to match your repo. Run it via claude -p < capture-thread-569.md from inside the repo you want the changes in.

⬇ Download capture-thread-569.md