Private preview is open to a few more founding customers.Apply
Platform · End-to-end

One platform.
From connected to running in production.

Sempleo is the context layer, the agent engine, and the workspace where agents run — one continuous system, not three integrations. Every piece is built to be auditable, reviewable, and yours.

What it does

Every capability,
on the same spine.

Context

Five-layer context model

Company, team, client, project, and user — curated, versioned, and reviewable.

  • Ownership per layer
  • Freshness per field
  • Full audit trail
Connect

OAuth connectors

Gmail, Calendar, Drive, Slack, HubSpot, Jira, and Notion today. Hybrid retrieval against your vector store.

  • OAuth per workspace
  • Per-tenant embeddings
  • Reference, don’t copy
Marketplace

Install, don’t train

Roughly thirty agents across eleven categories, each carrying a Conversational, Hybrid, or Automation badge. Install per-team or per-workspace; fork any of them; publish your own as private catalogue entries.

  • ~30 starter agents
  • 11+ categories
  • Install, fork, or publish
Authoring

Workflows in plain English

The Workflow Builder is an installed agent. Describe the workflow in plain English; it parses intent, maps your installed agents’ input/output schemas, drafts the definition, and previews it for confirmation.

  • Conversational authoring
  • Multi-step branching
  • The spec is the artefact
Health

Context health dashboard

Per-field quality scored by Haiku, rolled up per layer and across the workspace. Where a field is thin, “Assist” proposes a fill — a human approves.

  • Per-field Haiku scoring
  • Workspace + layer rollups
  • Per-agent readiness
Runtime

Agent runtime

Every agent is a readable spec with declared context requirements, tools, and a rubric. The runtime resolves context, runs the agent, and writes a per-run trace.

  • Versioned, reviewable
  • Context-aware by design
  • Rubric-gated outputs
Workspace

A review queue, not a chat

Writes land as pending review — the agent does the drafting, your operator approves the send.

  • Per-run rationale
  • Cited evidence
  • Approve, edit, or reject
Governance

Rubrics + audit log

Every output scored against a per-agent rubric. Every context change and every run logged; retention scales with plan.

  • Per-agent rubrics
  • Immutable audit log
  • Scoped API keys
Observe

Per-run trace

See which layers attached, which sources were cited, how long each step took, and what it cost — every run.

  • Layer attachment view
  • Citation list
  • Latency & cost breakdown
MCP

Open by protocol

Speaks the Model Context Protocol both ways. Sempleo is an MCP server for any client that reads it, and an MCP client for your own servers.

  • MCP server · read + suggest
  • Up to 3 external servers (Pro)
  • Unlimited (Enterprise)
Model

Bring your own model

Run on Sempleo’s managed default, or route through your own Anthropic or OpenAI account on Enterprise.

  • Sempleo-managed default
  • BYO Anthropic or OpenAI
  • No training on your data
How it runs

Four moves,
kickoff to production.

01
Step 01 · Connect

Connect the tools
you already use.

OAuth into Google, Atlassian, HubSpot, Slack, and Notion. Point at any MCP server you already run. Sempleo references your data with per-layer access control, not a shadow copy.

Design target: first connectors live on day one.
Connected sources · Workspaceapp.sempleo.ai / admin / sources
G
● synced
GmailThreads · attachments · recent
C
● synced
CalendarEvents · attendees · agenda
D
● synced
DriveShared drives · per-folder scope
N
● synced
NotionWiki · policies · runbooks
S
● synced
SlackApproved channels · DMs off
J
● synced
JiraProjects · issues · cycles
H
○ ready
HubSpotConnect to import contacts
M
○ ready
MCP serverBring your own · up to 3 on Pro

Reference, don’t copy. Sempleo reads from your source of truth. Revoke access and the context evaporates — no shadow copy.

02
Step 02 · Curate

Seed the
five layers.

Agents propose context entries from your existing artefacts. A human reviewer stamps them verified.

Design target: 75% context health across all layers inside the first week.
Context health · Workspaceapp.sempleo.ai / context / health
Company
100%
4 entries · all verified
Team
84%
18 entries · 3 need review
Client
62%
74 entries · 12 gaps flagged
Project
91%
32 entries · 1 stale
# 3 proposed entries awaiting review
propose client.rebrand.tone # from 12 sent threads · confidence: high
propose team.vocab.sprint # from 6 standups · confidence: medium
propose user.signoff # from 40 sent · confidence: high
03
Step 03 · Install

Install agents.
Don’t train them.

Marketplace of roughly thirty starter agents across eleven categories. Each carries a Conversational, Hybrid, or Automationtype badge. Install per-team or per-workspace, fork when a starter doesn’t fit, or author your own through the Workflow Builder — in plain English.

Design target: first install to first production run inside a week.
Marketplace · installedapp.sempleo.ai / agents
Email Drafter
Comms

Outbound email in your voice, grounded in thread history and client tone.

starterForkable
SOW Drafter
Sales

Assembles statements of work from the brief and your firm’s commercial template.

starterForkable
Account Researcher
Research

Pre-call brief from CRM, news, filings, and prior engagement notes.

starterForkable
Project Status
Delivery

Weekly status from Jira, commits, and Slack — written in your house format.

starterForkable

Every installed agent carries its context requirements explicitly. If a layer is missing, the agent surfaces the gap rather than silently guessing.

04
Step 04 · Run & govern

Trace every run.
Review what matters.

Every agent run shows which layers attached, which sources were cited, how long each step took, and what it cost. Flag, rerun, rollback — all native.

Design target: drafts ship without substantive edit on the first try.
run · r_9f4c21 · Email Drafter · reply to thread #8243.2s · 4,812 tok · cost $0.042
01 · intake
Resolved entity · client.rebrand · project.rebrand-2026
00.12s
02 · assemble
Attached layers · company · team · client · user (4/5)
00.38s
03 · draft
Drafted reply · 124 words · 12 citations
02.10s
04 · gate
Quality gate · voice match 94% · escalation triggers: none
00.28s
05 · approve
Routed to reviewer inbox · awaiting send
pending

Nothing ships without a human unless you say it can.Low-stakes tasks auto-send when voice-match > 90%; sensitive tasks always queue for approval.

Open by protocol

Sempleo speaks MCP
both ways.

As an MCP server

Your team context, over the protocol every modern LLM speaks.

Point Claude Desktop, Cursor, Windsurf, or any other MCP-aware client at your Sempleo workspace. The client reads the same five-layer context your agents do — scoped to the user, authority-respecting, and fully audited.

  • Read tools · context, knowledge, runs
  • Write tools · land as pending review
  • Per-user OAuth · nothing leaks across seats
As an MCP client

Your own MCP servers, live at retrieval time.

Register the MCP servers you already run — internal warehouses, vertical SaaS, whatever your team has exposed — and Sempleo calls them live when an agent runs. Circuit breakers and rate limits are built in; the audit log captures every call.

  • Up to 3 external servers on Professional
  • Unlimited on Enterprise
  • Per-tool allowlist · scoped credentials
Where Sempleo runs

Sempleo lives
where you work.

Web

The workspace, full-fat.

Admin, review queue, context editor, per-run trace — the whole surface, in every modern browser.

Desktop

A native app on macOS and Windows.

Built on Electron. Keeps a persistent review queue in your tray so agent drafts find you, instead of sitting in a tab you forgot to open.

Mobile

Approvals in your pocket.

React Native app for iOS and Android. Review and approve agent runs from wherever you actually are when the queue fills up.

How it compares

A platform,
not a point tool.

CapabilityGeneric LLMVertical chatbotSempleo
Five-layer context modelOwnership per layer, governed by the team.
Partial✓ Native
Agent marketplaceInstall, fork, publish — ~30 agents, 11+ categories.
✓ Shipped
Plain-English workflow authoringDescribe the workflow; the builder drafts the graph.
✓ Workflow Builder
Context health dashboardPer-field Haiku scoring + workspace rollups.
✓ Shipped
Per-run trace & citationsEvery claim linked to its source.
Partial✓ Native
Review queue for writesDrafts land pending; your operator approves.
✓ Native
MCP · both waysServer for clients; client for your servers.
Client only✓ Bidirectional
Bring your own modelRoute prompts through your own provider account.
LockedLocked✓ Anthropic or OpenAI
Integrations

Day-1 connectors
for the systems your operators live in.

G
GmailThreads · attachments
C
CalendarEvents · attendees
D
DriveFiles · folders
N
NotionDocs · wiki
S
SlackChannels · threads
J
JiraProjects · issues
H
HubSpotCRM · contacts
M
Your MCP serversLive at retrieval time
+
More en routeRequest a connector →
Most “AI platforms” are three products stitched together: a connector, a model, and a wrapper. I’m building Sempleo as one continuous system — context, agents, and workspace on the same spine — because the seams between those layers are where trust breaks. If you can’t read what the agent ran on, you can’t ship it into a regulated workflow.
Lasse Nørby
Lasse NørbyFounder · Sempleo
Sempleo

Shape the team-context
layer with us.

We're onboarding a small cohort of founding customers to deploy Sempleo on real workflows. A 45-minute call with the founder — you leave with a plan; we leave with the shape of how your team actually works.