CopilotKit / CopilotKit/outpost

Follow-ups from #105: notification tab, per-doc confidence weighting, dashboard surfacing

Open
#110 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

area: product roadmap roadmap: later
Dominant language
TypeScript
Stars
7
Forks
3
Avg merge
7d 16h
Merged PRs (30d)
15

Description

Follow-up to #105 / PR #106. The feedback→confidence loop shipped in #106; these remaining #105 pieces are tracked here:

In-platform notification surface

  • New Prisma Notification model (type=ESCALATION, ticketId, source, sourceUrl, assignee, readAt — global read state).
  • Producer in the ESCALATION job handler (packages/outpost/queue/src/handlers/escalation.ts) — one place covers Discord/Slack/Teams/command.
  • Notifications tab in the Outpost web sidebar (apps/web/src/components/sidebar.tsx) + unread bell; /notifications route + list/mark-read API.
  • Design already brainstormed (see the "In-platform escalation notifications" design discussion on #105).

Confidence weighting — deeper slices

  • Per knowledge-source / doc reputation (requires persisting the search-result docs behind each AI Message).
  • Per topic / keyword cluster weighting.

Dashboard surfacing

  • Show the current global calibration factor + 👎 clusters (knowledge-gap view) in analytics.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the design discussion on #105 and the ESCALATION handler in packages/outpost/queue/src/handlers/escalation.ts, then inspect apps/web/src/components/sidebar.tsx and the related web routing and API entry points. Done means the notification model, producer, notifications UI and read API, deeper confidence weighting, and dashboard calibration and knowledge-gap views are implemented.

Written by the indexing model from the issue text.

Assessment

Tech stack
typescript
Domain
analytics, backend, database, frontend
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
28/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.