Filesystem
Read-only by defaultAgents can browse and read project files. Writes, deletes and renames require an explicit policy grant — by directory, file pattern and named approver.
Product
Boxed.ai wraps the tools your agents call. Every action passes through a policy gate. Every decision lands in an evidence-grade log. Works across providers — you don't rip out the agent stack you already have.
How it works
01
Your agent — built on OpenAI Responses, Azure OpenAI Assistants, LangChain or AutoGen — calls a wrapped tool through the Boxed.ai gateway instead of the raw provider.
02
The gateway checks the call against your policy: scoped permission, sanitised inputs, rate limits, blast-radius checks. Sensitive actions trigger a step-up approval.
03
Approved calls pass through to the underlying tool. Calls awaiting approval queue for a named human; denied calls return a structured refusal the agent can handle gracefully.
04
Every prompt, retrieved context item, tool call, parameters, approver and outcome is appended to a hash-chained audit log. Exception MI surfaces what your second line needs to see.
The gateway model
Model-layer alignment is necessary but not sufficient. NCSC and OWASP both flag indirect prompt injection as a class of attack that cannot be fully patched at the model. Boxed.ai works at the execution boundary, where actions are bounded by code rather than by hope.
That means you get the same guarantees regardless of which provider, framework or model your team picks next quarter.
AGENT RUNTIME
OpenAI Responses
Azure Assistants
LangChain / AutoGen
BOXED.AI
Policy gate
Approvals
Audit log
TOOLS
Email, CRM
Files, Git
Payments, APIs
Tool wrappers
The MVP ships with three high-value, high-risk tool wrappers. They are deliberately conservative defaults — easy to relax, expensive to forget.
Agents can browse and read project files. Writes, deletes and renames require an explicit policy grant — by directory, file pattern and named approver.
Agents can branch, commit and open PRs. Direct pushes to protected branches are blocked. Merges require a human review on the PR itself, never the agent.
Agents can compose, address and attach files. Sending requires a named approver per recipient class. Drafts and decisions are recorded on the audit log.
Connectors for Stripe, GoCardless, HubSpot, Salesforce and common UK practice-management systems are on the build plan for the first paid tier.
The audit log
Boxed.ai writes an append-only record for every tool call evaluated by the policy gate. Each entry is hash-chained to the previous one — so any tampering with historical events is detectable on review.
Logs export as JSONL for ingest into your SIEM, GRC tooling or auditor's evidence locker. A signed manifest accompanies every export.
Captured per call
Where we are
Boxed.ai is in active development. We are running design partners through a working policy gate, three tool wrappers and the audit log described on this page. RBAC, GRC connectors and automated incident response are on the build plan for later phases. If you'd like to be in the design-partner cohort, we'd like to hear from you.
Talk to a founder