Safe to say yes.
Your awks read your code, write commits and move your work items along, so the controls are built in. By default a person is asked at two points on a work item that changes code: the plan before the build, and the pull request before it ships. How often you're consulted in between is a dial you set. Merging a pull request, pushing to main and force-pushing always wait for a person's approval, wherever the dial sits. Opening a pull request and posting outside your team wait for approval too, unless a person on your team in that thread has chosen to approve all of that kind; routine moves of the assigned work item through your workflow happen automatically, and every agent action is auditable.
Strong logical isolation per tenant. Each customer gets a separate database, credentials protected by per-tenant encryption keys (no key shared across customers), and separate per-team workloads, credentials, and audit trails. Every agent runs inside an OS-level sandbox with deny-by-default network egress, and a hard cross-tenant boundary keeps each customer's data, queries, and credentials inside their own tenant. The boundary is architectural, not a policy check — no prompt, tool call, or input can carry an agent across it.
Role-scoped agents with least privilege. Read-only roles (e.g. reporting/triage agents) are technically restricted from writing. Actions that are irreversible or reach beyond your team need explicit human approval. Merging a PR, pushing to main and force-pushing are approved one at a time, every time. Opening a PR and posting externally pause for approval too, unless a person in that thread has chosen to approve all of that kind. Routine bookkeeping on the assigned work item, like moving it through your workflow, happens automatically. Write access is scoped to the specific repositories you authorise.
Every agent action is auditable. Git activity, Jira changes, work item lifecycle, team administration, credential management — all logged with the context of the agent's task. Timestamped, team-scoped, exportable to CSV. Retention by plan, from 30 days up to 10 years.
Your code is never used to train models. We call frontier LLMs through commercial provider APIs — Anthropic, OpenAI, and Google — under business terms that prohibit training on your prompts and code, not consumer apps. Your code stays your code.
SAML 2.0 SSO on Scale and Enterprise; SCIM 2.0 user provisioning on Enterprise. Role-based permissions for admin access. Compatible with Okta, Google Workspace, Microsoft Entra ID, and other SAML 2.0 providers via standards compliance. Note: only your admins need AwkTeams accounts — engineers and PMs work with the agents through Slack, GitHub, and Jira using their existing identities.
Our hosting runs on Google Cloud Platform in Sydney, which is SOC 2 Type II and ISO 27001 certified; our Privacy Policy lists every other service that processes your data, and where. AwkTeams' own SOC 2 Type II audit is on our roadmap for our first enterprise customer cohort. All data is encrypted at rest (AES-256); credentials and secrets are additionally protected with per-tenant envelope-encryption keys (no shared key across customers). Data is encrypted in transit with TLS 1.2 or higher. Per-tenant databases and per-team workloads provide strong logical isolation at both the tenant and team level.
The major AI platforms are converging on running each agent in its own sandboxed runtime — AwkTeams is built on the same principle, with a strong focus on protecting your data. Agents operate without long-lived credentials in their environment, and their network access is deny-by-default — outbound traffic is limited to the specific endpoints your team has authorised. Combined with per-customer databases and encryption keys, the result is containment by design: every agent operates strictly inside its own team's boundary, with credentials, network reach, and data access all stopping at that edge.
Where the rest is written down
- Every service that processes your data, and where: Privacy Policy
- The actions that wait for a person's approval, in the terms you agree to: Terms, §8
Need more detail for a security review? Ask us and we'll answer your security questionnaire