Directing @yagni · Lesson 4 of 4

Which tools does YAGNI connect to, and what does it do with them?

Quick answer

YAGNI connects through native, first-party connectors to the tools you already pay for: Google (Gmail, Calendar, Drive), Slack, Linear, GitHub, HubSpot, Stripe, and Notion today, with the list growing. It reads them to feed the Teams and ships approved work back into them. It never hosts or migrates your tools.

Which native connectors exist today?

ConnectorWhat it feeds
Google: Gmail, Calendar, DriveThe Inbox, the agenda @yagni prepares against, your docs
SlackWhat the team is saying and deciding
LinearEngineering work: issues, cycles, what is blocked
GitHubWhat is actually shipping: pull requests, releases
HubSpotThe pipeline: deals, contacts, the sales motion
StripeRevenue: invoices, subscriptions, the numbers against goal
NotionThe documents your team already wrote

These are native, first-party connectors with read, draft, and completion depth, not a thin marketplace wrapper. The list grows regularly, and the order is driven by what customers run on. If a tool you depend on is not here yet, ask: it goes on the list.

What does “additive” mean?

YAGNI never hosts your apps and never migrates your data. Connect Stripe and your Stripe data stays in Stripe. Connect Linear and your engineers keep working exactly where they work now. The systems of record do not move; the reading and the routine work move off your plate.

The only thing YAGNI replaces is the next tool you were about to buy and the operations hire you were about to make to run all of it. Everything already in the stack stays where it is.

What does YAGNI do with read access?

It feeds the Teams. One agent reads across every connected tool into one memory, which is what makes the Front possible: the Sales Team’s picture includes the Gmail thread and the Stripe invoice, not just the HubSpot record. Reading is reversible, so the agent does it freely, and every fact it publishes cites the rows it came from.

How does approved work ship back?

Through the same connectors, with the approval gate in front of it. A draft reply ships into Gmail when you approve it in the Feed. A status comment lands in Linear. A follow-up files into HubSpot. Each shipped action leaves an honest receipt with the actual tool call folded underneath, so the audit trail is complete on both sides.

How is all of that secured?

Connector credentials are customer-scoped and AES-256-GCM encrypted, and application access is scoped to the authenticated workspace or customer. Irreversible and high-blast actions remain approval-gated at every level; lower-risk routine work graduates only with explicit consent and stays recorded. Tool audits keep sanitized action metadata rather than result payloads or message bodies. The security page has the full picture, including current SOC 2 Type II status, the DPA, and support for your security review.

Common questions

What does additive mean in practice?

YAGNI sits on top of your stack. It reads your tools and ships approved work back into them, and it never hosts your apps or migrates your data. Your Stripe data stays in Stripe; your Linear issues stay in Linear.

Are connectors priced separately?

No. Every connector is included on every plan. Usage is driven by how much the agent reads and composes, which is what credits meter, not by tool count.

What if a tool I run on is not built yet?

Ask, and it goes on the list. New native connectors ship regularly, and the order is driven by what customers run on. These are first-party connectors with read, draft, and completion depth, not a thin marketplace wrapper.

How is connector access secured?

Connector credentials are customer-scoped, AES-256-GCM encrypted, resolved only at execution time, and never placed in model prompts. Tool calls record sanitized action metadata, and application data access is workspace- or customer-scoped.

Read enough. Run it.