Levin Riegner
L+R Newsletters
Review dashboard for newsletter construction, evidence, artifacts, and production runs.
Access is limited to approved Levin Riegner accounts.
Access Denied
This Google account is not on the allowlist.
Review dashboard
Current Edition
The generated edition currently exposed by the dashboard. Open the preview to read the email-style HTML, or the issue pack to inspect the markdown source.
Newsletter Model
Configuration that defines the audience, cadence, approval gate, and publishing target for this newsletter.
Sections
Editorial buckets used to assemble the newsletter. Item targets are balance recommendations, not hard caps.
| Section | Format | Links | Rules | Activity |
|---|
Cadence Jobs
Configured pipeline jobs, their schedules, and the steps they execute.
| Job | Stage | Status | Cron | Steps |
|---|
Data Sources Overview
Read-only package setup for deterministic sources, source groups, discovery queries, Gmail Alert inputs, and evergreen resources.
Sources
Watched sources and source types. These are deterministic inputs checked by the research run before broader discovery is considered.
| Source | Type | Bucket | Health | Target |
|---|
Source Groups
Package-level source buckets used to explain why inputs exist and how they support editorial coverage.
| Group | Description | Priority |
|---|
Static Discovery Queries
Broad public-web searches configured in the package. These are static queries, not derived from emergent stories.
| Query | Status | Priority | From |
|---|
Google Alerts
Gmail alert subjects configured for this newsletter package, using the account and sender query from the runtime environment.
| Subject | Status | Provider | Window |
|---|
Design Resources
Evergreen UX references that are rendered deterministically instead of competing with news stories.
| Resource | Source | Description |
|---|
Issue History
Generated editions grouped by issue date, with latest build status and recovery links for older previews and packs.
| Edition | Latest Build | Status | Stories | Recovery Links |
|---|
Stories
Generated story candidates grouped by configured newsletter section. Status comes from the pipeline; Decision is the human editorial layer.
| Preview | Actions | Order |
|---|
Source Health
Configured source status across deterministic inputs. Failing or unchecked sources usually explain thin or stale research output.
| Source | Status | Type | Bucket | Target | Changed | Failures | Checked |
|---|
Query Performance
Configured and runtime discovery queries, with explicit cluster yield and included-story yield definitions.
| Query | Status | Discoveries | Clusters | Included | Cluster Yield | Included Yield | Measured |
|---|
Run History
Automation runs, timing, step coverage, outcome, and concise operating metrics.
| Run | Started | Outcome | Steps | Metrics |
|---|
Audit Log
Human and dashboard write actions, separated from automation runs with before/after detail.
| Time | Actor | Action | Target | Details |
|---|
Internal Workflow
How the current package workflow turns configured inputs into reviewable newsletter artifacts.
Check configured inputs
Construction shows the newsletter model, sections, and cadence jobs. Data Sources shows source groups, watched sources, static discovery queries, Gmail Alerts, and evergreen resources.
Run collection and discovery
The research job collects deterministic sources, broad query results, and Gmail Alert leads, then stores discoveries with source URLs, snippets, and timestamps.
Cluster and research stories
Related discoveries are deduplicated into story clusters, then promoted into story rows with section, summary, why-it-matters text, priority, evidence, and inclusion state.
Use diagnostics before editing
Diagnostics explains source health and query performance. Runs shows which automation steps executed, and Audit Log shows human/dashboard writes.
Review and decide stories
Stories is the editorial workspace. Open a story to inspect evidence, query provenance, other candidate URLs, existing copy, and saved decisions.
Generate and recover builds
Generate new edition creates an issue pack and preview. Issue History groups builds by edition date and keeps latest and previous Preview/Pack recovery links.
Validate and approve outside publishing
Link validation runs after rendering. Publishing and email sends remain outside this dashboard and require explicit approval.
Human Editor Workflow
A practical review sequence using the dashboard surfaces that exist now.
Start with Needs Review
Use the Needs Review filter in Stories, then open each story to inspect evidence, source quality, query provenance, and other candidate URLs.
Shape the candidate set
In Stories, use Accept or Reject for the inclusion decision. Open the detail drawer to edit copy, set section order, mark an item for review, or leave decision notes.
Check source balance
Use Data Sources for source setup and Construction for section balance targets. Use Diagnostics when a section feels thin, stale, repetitive, or too dependent on one source type.
Generate a fresh build
Click Generate new edition after decisions are saved. This builds a new issue pack, renders the Beehiiv preview, applies the LLM editorial pass, and validates links.
Read like the recipient
Open the preview from Current Edition. Use Text Changes in Issue History when comparing builds, then check section rhythm, duplicated claims, weak implications, broken style, and whether links support the story.
Iterate deliberately
If the draft is not ready, return to Stories, adjust decisions or notes, and generate again. Use Issue History to recover older previews or issue packs.