A running log of what shipped. Platform changes, marketplace additions, context model updates, and security work. Future releases will stream here automatically from the product — for now, entries are curated by hand.
Legal pages + editorial blog
Published the Privacy Policy, Terms of Service, and DPA. Rewrote the blog as static editorial posts, trimmed the footer to real routes, and pointed the nav sign-in at app.sempleo.ai.
Agent roster to ~30, eleven categories
Expanded the marketplace to roughly thirty agents across eleven categories — Comms, Sales, Research, Delivery, Ops, Knowledge, Authoring, Quality, Finance, People, and Legal. Every agent is a readable spec, a rubric, and an audit trail. Fork what doesn’t fit; publish your own as tenant-scoped entries.
Five-layer context model
Shipped the five-layer context model — company, team, client, project, user. Each layer has its own review cadence and authorship rules. Agents declare which layers they need; missing layers surface in the UI rather than silently degrading output.
Review queue + audit log
Every agent run now lands in a review queue with its inputs, rationale, and citations. Approvals, edits, and rejections produce an append-only audit record keyed to the user and workspace. Nothing ships externally without a human in the loop.
MCP server — read + suggest
Sempleo now speaks the Model Context Protocol both ways. Expose your team context to any MCP-aware LLM client; pull in live data from your own MCP servers. Scopes are per-tenant, per-agent, and fully logged.
Private preview with founding customers
Opened the private preview with a small group of founding customers across professional services, marketing, and engineering teams. The founder sits with each team during seeding; kickoff to production is designed as a four-week rollout.
Want earlier changes as they ship? Request early accessand we’ll add you to the monthly brief.