Use Cases · Founders & SMB

The sixth hire ramps in a week, not six months.

Cortex gives founders and lean teams an agent that carries everything you know — your ICP, your constraints, your client preferences, your board commitments — so you stop repeating yourself and start compounding.

agent / founders-smbslack · live
daily · briefing
you
Workflow recipe (leadership.daily_briefing): top 3 urgent items, upcoming deadlines, and any anomalies from connected…
cortex
Start every day knowing what actually matters — without opening six tabs.
Google WorkspaceLinearGitHub
[ Thesis ]
A senior engineer joins a new company and ships meaningful code in weeks. A senior GTM leader at the same company takes six months to ramp. The difference is that one of them is walking into a function with institutional memory, and the other is walking into a function that runs on what lives in people's heads. When capture is automatic, that changes.
Read the founding thesis
[ 01 · Jobs ]

Jobs your agent handles.

Every scenario runs on a real Cortex capability. The memory split shows what stays in this session and what graduates into the team's institutional knowledge.
[ Scenario 01 ]

Start every day knowing what actually matters — without opening six tabs.

Trigger

Scheduled recipe fires weekdays at 8am, delivered to your personal Slack DM from Cortex.

In Slack

Workflow recipe (leadership.daily_briefing): top 3 urgent items, upcoming deadlines, and any anomalies from connected tools

Agent does
Google Workspace — calendar + emailLinear — open issues + blockersGitHub — open PRs needing reviewInstitutional memory — current priorities and contextSlack — DM morning briefing
Conversational memory

Today's specific items flagged and any context the founder adds in reply.

Institutional memory

Current priorities and top blockers — updated as the founder responds and confirms. The briefing gets sharper over time because it reflects what actually got acted on.

[ Scenario 02 ]

Weekly risk scan — churn signals, revenue anomalies, operational blockers — before they become problems.

Trigger

Scheduled Monday recipe. Covers the whole business in one pass.

In Slack

Workflow recipe (leadership.risk_detection): scan for churn signals, ARR changes, and operational anomalies — severity-labeled list

Agent does
Notion — customer health notesGoogle Workspace — revenue and usage signalsLinear — overdue items + blockersInstitutional memory — baseline and prior flagsSlack — weekly risk list with High/Medium/Low labels
Conversational memory

This week's scan window and any flags the founder dismissed or escalated.

Institutional memory

Recurring risks stored by pattern — 'customer health flags have appeared before every churn in the past year.' Surfaces predictive context, not just this week's data.

[ Scenario 03 ]

Board prep digest built from your actual data, not from the founder rebuilding it from scratch every quarter.

Trigger

Scheduled Friday recipe — or triggered manually in the week before a board meeting.

In Slack

Workflow recipe (leadership.board_prep): key metrics, top wins and challenges, risk list, and Q priorities from all connected tools

Agent does
Notion — metrics and OKRsLinear — team highlights and blockersGoogle Workspace — financial and growth dataInstitutional memory — prior board narrative and commitmentsSlack — structured executive summary
Conversational memory

The specific quarter reviewed and any narrative framing the founder added.

Institutional memory

Commitments made to the board stored permanently — 'committed to 20% MoM growth through Q2 2026.' Surfaces before every future board prep so nothing falls through.

[ Scenario 04 ]

New hire ramps in a week instead of six months — because the agent already knows everything.

Trigger

A new hire joins. The founder types one message. The agent briefs them from institutional memory.

In Slack

@cortex brief [Mia, new Head of Marketing] on our ICP, current positioning, top 3 priorities, active campaigns, and the customers she should talk to first

Agent does
Institutional memory — ICP, positioning, prioritiesNotion — active project contextGoogle Workspace — key customer listSlack — post onboarding brief to Mia's DM
Conversational memory

Mia's specific role and the founder's framing from this session.

Institutional memory

The brief delivered becomes a reference fact. When Mia asks follow-up questions over the next two weeks, the agent builds on the same foundation — no re-explaining, no context gaps.

[ Scenario 05 ]

Run multiple clients or brands from one place — with a dedicated agent per account and shared standards across all of them.

Trigger

Agency owner or multi-brand founder manages several Cortex agents — one per client, company-scope for shared playbooks.

In Slack

@cortex what does Client A prefer for reporting format, and does that conflict with anything in our standard delivery template?

Agent does
Institutional memory — Client A preferences (agent-scoped)Institutional memory — standard delivery template (company-scoped)Slack — reply with preference summary and any conflicts
Conversational memory

The specific reporting question and the client in context.

Institutional memory

Client A's preferences stored at agent-scope; delivery standards stored at company-scope. When a new team member takes over Client A, they inherit the full history instantly.

[ Scenario 06 ]

Every time you explain something to the agent, it stops being tribal knowledge.

Trigger

Ongoing. The founder explains something in Slack — a product decision, a customer story, a strategic pivot.

In Slack

@cortex note this: we're not pursuing enterprise contracts below $50k ACV because the implementation overhead kills margin — this is a hard constraint for the next 18 months

Agent does
Institutional memory — store as permanent constraint factSlack — confirm stored
Conversational memory

The specific context in which the founder stated this constraint.

Institutional memory

'No enterprise contracts below $50k ACV — implementation margin constraint, valid through Q2 2027.' Surfaces in every sales conversation, every pricing review, every board prep — without the founder ever repeating it.

[ 02 · Two layers of memory ]

Working in every job above.

Two tiers, working in parallel. One fades unless it matters; one compounds forever.
Conversational memory

What happened in this session — the Slack thread you referenced, the customer you named, the draft you iterated on. Persists through the conversation and short-term window. Volatile by design: fades unless it matters.

Institutional memory

Facts that proved their value — accessed repeatedly, confirmed accurate, promoted by the system. “Drift raised their Pro price to $400/seat.” “Acme Corp runs on Salesforce CPQ.” Written once by accident, available forever to every session.

[ 03 · Connected tools on this page ]
SlackNotionLinearGitHubGoogle WorkspaceHubSpot

Stop being the documentation bottleneck.

Deploy in 10 minutes. No DevOps required.