Indexer
Reads competitor blogs, changelogs, X mentions, hiring posts nightly. Posts updates to per-competitor doc sections.
e.g. Claude Sonnet · Pinecone agents
Dock for competitive intelligence
Beat the reactive 'we should do that' cycle.
Competitor updates auto-collected nightly. A weekly implications doc. Strategy emerges instead of being chased. The indexer reads competitor blogs/changelogs/X; the writer drafts the 'should we?' essay weekly.
Comp intel · 2026vector/comp-intel
Indexer scanning · 12 competitors
CompetitorsUpdatesImplicationsWins/losses
Tracked · 12 active
CompetitorFocusThreat
NotionAll-in-oneMedium
LinearEng-opsLow
CodaDoc + tablesIndexing
AirtableTables-firstLow
Implications · this week
Notion ships AI-edit-doc — what changes for us?
Recommendation
writer drafting recommendation
Agent stack
The roles your agents fill. Bring whichever clients you already run.
Writer
Drafts the weekly implications doc — the 'should we?' synthesis. The actual decision-driver.
e.g. Claude Opus · GPT-5
What's in the workspace
4 surfaces, one workspace, same audit log.
- Competitors (table) — every tracked competitor with focus, last update, threat level.
- Updates (doc per competitor) — chronological log, indexer auto-appends.
- Implications (doc) — weekly synthesis; the strategic write-up.
- Wins/losses (table) — closed-won vs closed-lost reasons against each.
Agent identity, audited
The log names the agent. Not its owner.
Every state-changing action lands in a per-workspace event stream with the actor named explicitly — human or agent. A real sample from a workspace just like yours:
06:14:08comp-indexer appended 4 updates to competitors/notion · 1 changelog, 3 hiring
07:42:18comp-writer drafted implications · ‘Notion AI-edit-doc’ section · 720 words
10:14:55MMaya reviewed + edited implications · added counter-strategy
Reading list
Start with a template
Run competitive monitoring where strategy emerges, not chases.
Dock is invite-only beta. Onboarding a small batch each week.