McRitchie Studio
Say Hi 👋
Agents Builders
← All Tasks
Sizing

Rolio admin Prompts page

Reviewed carl
rolio-prompts

Created

Jun 26, 22:21

Started

Jun 26, 22:23

DevOps handoff

Type

Feature

Shape

ui+db

Worktree Slug

rolio-prompts

Repositories

rolio

Release Train

—

Branch

feat/rolio-demo

Pull Request

https://github.com/amcritchie/rolio/pull/16

Local URL

—

QA URL

—

Production URL

—

demo

Acceptance Criteria

  • Data-driven Prompt model: feature, platform, model, text
  • Admin Prompts page lists prompts from the DB
  • All prompts seeded as Anthropic Claude Opus 4.8

Expected Test Plan

No expected checks recorded.

Checks Run

  • [unit] Prompt seed regression: enrich catalog matches facts-only provider contract
  • [suite] bin/rails test: 239 runs, 952 assertions, 0 failures on head 23b9fbb
  • [ci] GitHub Actions CI: completed success on feat/rolio-demo run 28274558968

Agent Context

New admin 'Prompts' page (alongside Schema + AI Results) cataloging the prompt behind each AI feature. DATA-DRIVEN: a Prompt model (feature, name, platform, model, body) + seed, NOT hardcoded in the view. platform='Anthropic', model='claude-opus-4-8' (display 'Claude Opus 4.8') for ALL seeded prompts (the examples are generated by Claude Opus 4.8). One prompt per AI feature: enrich, socials, note_extraction, outreach_draft. Admin page /admin/prompts linked from the admin hub, following the existing app/views/admin/ai_results.html.erb pattern (admin layout, inline styles - admin layout has NO :head yield). PARALLEL worktree feat/rolio-prompts off feat/rolio-demo, concurrent with Wave 2b UI; keep changes scoped (model, seed file + load line, admin route/controller/view, admin index link, tests); DON'T touch event/notes/socials files; merges into feat/rolio-demo.

Stage Timeline

Who handled each stage, the time it took (measured), and the model / tokens / cost reported (best-effort) — plus who's on it right now. — means the agent didn't report that metric.

Sizing Avi · PO SMALL Dev SMALL Actual —
  1. Created → Designed
    D Dewgong
    Dewgong
    Model
    —
    Duration
    —
    Tokens
    —
    Cost
    —
    Completed Jun 26, 22:21 · about 12 hours ago
    api
  2. Designed → Building
    D Dewgong
    Dewgong
    Model
    claude-opus-4-8
    Duration
    2 minutes
    Tokens
    2,458,160
    Cost
    ~$1.97
    Started Jun 26, 22:21
    Completed Jun 26, 22:23 · about 11 hours ago
    cli
  3. Building → Submitted
    D Dewgong
    Dewgong
    Model
    claude-opus-4-8
    Duration
    14 minutes
    Tokens
    39,640,017
    Cost
    ~$25.46
    Started Jun 26, 22:23
    Completed Jun 26, 22:37 · about 11 hours ago
    cli
  4. Submitted → Blocked
    —
    Model
    —
    Duration
    about 1 hour
    Tokens
    —
    Cost
    —
    Started Jun 26, 22:37
    Completed Jun 26, 23:39 · about 10 hours ago
    api
  5. Blocked → Submitted
    D Dewgong
    Dewgong
    Model
    —
    Duration
    39 minutes
    Tokens
    —
    Cost
    —
    Started Jun 26, 23:39
    Completed Jun 27, 00:18 · about 10 hours ago
    api
  6. Submitted → Blocked
    —
    Model
    —
    Duration
    10 minutes
    Tokens
    —
    Cost
    —
    Started Jun 27, 00:18
    Completed Jun 27, 00:28 · about 9 hours ago
    api
  7. Blocked → Submitted
    D Dewgong
    Dewgong
    Model
    gpt-5.5
    Duration
    about 1 hour
    Tokens
    —
    Cost
    —
    Started Jun 27, 00:28
    Completed Jun 27, 01:37 · about 8 hours ago
    cli
  8. Submitted → Reviewed
    C Carl
    Carl primary
    S Shannon
    Shannon light
    Model
    gpt-5.5
    Duration
    about 3 hours
    Tokens
    4,603,676
    Cost
    ~$3.82
    Started Jun 27, 01:37
    Completed Jun 27, 04:33 · about 5 hours ago
    cli

Conversation

QA review feedback, agent handoffs, and follow-up notes for this task.

QA Feedback codex about 10 hours ago

PR #16 current head 9ff8f81 needs rework before merge. EnrichmentService.note_taxonomy caches note_extraction by contact only, so a second Fathom transcript/summary for the same contact reuses the first extraction; reproduced Denver/Broncos sample then Austin/Lakers still returning Denver/Broncos. Fix cache key/invalidation so reviewed taxonomy matches the current paste, then update PR body to include all 7 task URLs and current 231-test proof. Local review: rails test green; db:prepare/seed green; route smoke green.

Handoff codex about 10 hours ago

PR #16 rework is pushed at current head df7f678. The stale Fathom taxonomy cache blocker is fixed by transcript-digest note_extraction keys in 2cb0e59; current branch also includes the later enrich-tags split. Verification on current head: bin/rails test -> 233 runs, 907 assertions, 0 failures. Ready for re-review.

QA Feedback codex about 9 hours ago

PR #16 is not ready for QA approval yet. The admin Prompts catalog claims the enrich prompt returns facts plus public profiles, but Llm::ClaudeProvider still asks for facts only and explicitly excludes profiles. Also, PR #16 includes rolio-enrich-tags while that task is still building/claimed, and the PR targets main because Rolio has no release branch. Align the prompt/provider contract and PR scope/base before resubmitting.

Comment about 8 hours ago

Shared PR #16 rework pushed at 23b9fbb: enrich prompt/provider contract is aligned, rolio-enrich-tags is submitted on PR #16, and Rolio's standalone PR base is documented as main. Local full suite and latest GitHub Actions CI passed.

Comment about 5 hours ago

QA approved PR #16 at head 23b9fbb. Local bin/rails test passed (239 runs, 952 assertions, 0 failures), latest GitHub Actions CI run 28274558968 passed, PR is CLEAN, and main base is intentional for standalone Rolio. PR body was updated to include rolio-enrich-polish2.

Sealed-bid sizing

Edit →

Alex (PM)

—

Avi (PO)

SMALL

Dev

SMALL

Actual

—