Fred · Swift platform · Capabilities, for teams & architects
One Switch For Everything An Agent Can Do
A tool. A whole agent. Soon, a packaged bundle of several agents plus their
supporting pieces. Different sizes, same abstraction — turned on
or off per team, the same way, enforced the same way.
Fred · July 2026 · verified against branch consolidation-22-07
Engineering detail: docs/swift/rfc/AGENT-CAPABILITY-RFC.md
and the CAPAB-01 team deck
The idea, in one line
A capability is anything you can turn on for an agent.
A search tool. A document editor. A whole specialist agent. Eventually, a bundle
of several agents working together. It doesn't matter which —
granting one to a team is the same click, in the same place.
Every capability has a name, a description, and one switch a platform or team admin controls.
That switch is enforced the same way everywhere — the same permission check, whether it gates a tool or an entire agent.
This deck walks through what's shipped today, why the switch matters, and where the same idea is headed next.
Shipped today · 1 of 2
Tools your agents can use — one switch each
Document access shippedSemantic search over your team's document library (RAG) — the agent cites what's actually in your files, not what it remembers.
Writable document shippedCo-write a document with the agent in a side-by-side editor, and export it to Word or Markdown when it's ready.
PowerPoint generator shippedUpload your own template — the agent extracts the right values from the conversation and returns a finished deck.
Three very different features. One shape underneath: a capability with a name, a description, and a switch.
Shipped today · 2 of 2 — the new part
Whole agents now live in the same catalog
Specialist agents — Mindmap, Document Comparison,
a SQL expert, a general assistant — now show up as entries in the
exact same capability catalog as the tools on the previous slide,
behind the exact same admin switch.
Fred · Administration › Capabilities
Capability
Team Alpha
Team Beta
Team Gamma
Document accesstoolsearch & cite the document library
PowerPoint generatortoolfill slide decks from a template
Mindmapagentvisualize a transcript or document as a knowledge map
SQL expertagentquery structured/tabular data sources
Same screen, same switch, same permission model — whether the row is a tool or a whole agent.
Why this matters
The switch is the security boundary
Flexibility
Give Finance the PowerPoint generator and Document access, nothing else.
Give the Platform team the SQL expert and Mindmap, not Finance's tools.
Composing a team's agent lineup is a handful of clicks in an admin screen — not a deployment, not a code change.
Security
Nothing is available to a team unless it was explicitly granted — enforced the same way (one permission check) whether it's a tool or a whole agent.
A capability a team was never granted isn't just hidden in the menu — it isn't reachable by that team's agents at all.
One model to audit, one model to reason about — not a different story for tools than for agents.
One lever, two payoffs: teams get exactly the surface they need — and nothing they don't.
Next horizon · a direction, not a shipped feature
A capability doesn't have to stop at one agent
Worked example: "Move to cloud" — packaged as one capability,
one switch, one thing a team turns on. Underneath, it's an assembly:
Five collaborating agentsdiscovery, cost estimation, migration planning, execution, validation — the kind of multi-agent crew the platform's agent-composition model already builds today.
A processorthe background work behind the scenes — scanning inventory, running migration steps — the same kind of job a capability's own backend route already does for the PowerPoint generator.
A UIa dedicated panel for the whole workflow — the same side-panel slot a capability already gets today for its own view.
Nothing here is a new mechanism — an agent is already a capability; a capability already gets its own backend and its own panel. "Move to cloud" is what happens when we package those existing pieces as one switchable product instead of five separate things a team has to assemble by hand.
Take away
Same idea, three sizes
A toolDocument access, Writable document, PowerPoint generator — shipped
→
A whole agentMindmap, SQL expert, and others — now in the same catalog, same switch, shipped
→
A packaged assembly"Move to cloud" — several agents + a processor + a UI, as one switch — next horizon
Every size is the same underlying model: a capability, with a manifest
and a switch a team admin controls. That's what makes the next size — assemblies —
reachable without reinventing anything.
Engineering detail: docs/swift/rfc/AGENT-CAPABILITY-RFC.md
and the CAPAB-01 team presentation deck