The Record platform

Deploy, govern, and operate every agent.

Bring the agents your teams already use—or run critical workflows in Record's managed sandbox runtime. Govern identity, access, credentials, policy, tools, models, knowledge, spend, incidents, and audit as one operating system.

01Connect any agent

Codex, Claude, ADK, Record Runtime, and custom harnesses enter through one governed platform.

02Govern before execution

Identity, access, credentials, policies, approvals, tools, models, and budgets are decided before action.

03Managed sandbox runtime

Run critical agents in isolated sandboxes with filesystem, process, network, egress, and credential controls.

04Incident operations

Record detects, contains, routes, and resolves agent failures—with an owner and evidence for every response.

ITSM for AI agents™

Your AI agents are a workforce. Nobody’s managing them.

They read your systems, call your tools, and spend your budget — but unlike every employee, no one provisioned them, scoped their access, approved their actions, or assembled a complete record of what they did. Everything IT built to make human access safe, your AI agents go without. Record is that system, for the AI agent workforce.

A day in the life of a governed agent
Step 1 / 9 · Build

You describe the outcome. Record assembles the agent.

The plan, harness, tools, runtime, and operating boundaries start as one managed blueprint — built conversationally and ready to run.

New agent · Agent Studiolistening…
@ Data & tools/ Skills
Record managed
finance-close-agent · autonomous
Govern · what it can see & do

Control every action before it happens.

Every agent gets an identity, least-privilege access it never holds as a key, one Cedar policy your team approves in a pull request, and a human in the loop on what matters.

Record Identity & Access

Your agents never hold a credential — so there’s nothing to steal.

Credentials minted just-in-time at the wire, scoped to the task, and revoked when it completes. The agent only ever sees a placeholder — never a key.

Record Policy Engine

One policy your security team approves in a pull request.

One Cedar policy — readable, version-controlled, co-owned by compliance. Risky actions fail closed.

Human Approval
Refund $4,200 — held for approvalpaused
Record Human Review

The actions that matter still wait for a human.

The $50K posting or the prod delete pauses for a human. The pause is durable — it survives crashes, restarts, and deploys.

Operate · run the fleet

Run the whole workforce on one operating layer.

One governed front door to every model, tool, and skill—plus the knowledge agents need and spend that is capped, attributed, and routed deliberately.

Slack@record analyze PR #847
Teams/run due_diligence_agent
Webhookgithub.push → main branch
APIPOST /agents/support_bot
CLIrecord agent chat ...
A2Aagent://claims invoke
RecordSame policy. Every surface.
Record Channels & API

Trigger agents from the surfaces where work already starts.

Launch governed agents from Slack, Teams, webhooks, API, CLI, or A2A. Every entry point reaches the same identity, policy, approval, and audit controls.

Jira
Confluence
Salesforce
Sync
Knowledge Base847 indexed
PROJ-4821 · Auth regressionBug
API Design — Auth FlowDoc
Acme Corp · EnterpriseAccount
Sprint 24 planning notesTask
Record Brain

Agents that know your business — and get smarter every run.

Your institutional knowledge — Jira, Confluence, Salesforce, docs, prior decisions — synced into a queryable graph. Memory that compounds every run.

Budget & Spend
Team cap set: $2,000 / weekpolicy
Record Spend Management

The model bill nobody can explain — capped, attributed, and bent down.

Hard caps before the burn, every dollar attributed to a user, team, and agent — and calls that don’t need your best model, auto-routed to a cheaper one. Spend Finance can actually explain, not a surprise invoice.

Observe & audit · what it did

Every action on the record. Every issue owned.

Every action is traced and tied to the human who launched it. Silent failures become tracked Issues, and what touched your data becomes one query.

trace-ak48f2
2.4s$0.0034✓ 3 gates
0600ms1.2s1.8s2.4s
agent.run
2.4s
harness.validate
34ms
gateway.route
8ms
llm.generate
1.8s
sandbox.exec
420ms
Record Observability

See what an agent actually did — not “tool call succeeded.”

Model calls, tool calls, policy decisions, approvals, credential leases, spend — correlated by agent, team, and the human who launched it.

Issues
Tool error spike: jira.createIssuesignal
Record Incidents & Diagnostics

Silent failures become tracked Issues — own them, diagnose them, resolve them.

Signals cluster by fingerprint into durable Issues — owner, priority, lifecycle, and auto-reopen. Route what matters to Slack or Teams.

Agent
Harness
Gateway
Sandbox
Executed
System of record

“What touched our data?” is one query, not a months-long investigation.

One queryable trail — who called it, what it touched, on whose behalf, with which credential. One answer for the auditor.

One platform · every agent

Connect any agent. Govern all of it. Run the critical ones deeper.

Record brings identity, access, tools, models, knowledge, spend, policy, approvals, runtime controls, incidents, and audit into one operating platform. Govern every agent, then run critical workflows with deeper guarantees.

Platform-wide control

Record Agent Control Plane

Access managementIdentity + JIT credentials the agent never holds.
Tool & MCP registryEvery MCP / OpenAPI tool and skill, governed per call.
Model gateway100+ models behind one governed, per-tenant key.
Budget & spendHard caps, auto-routing to cheaper models, spend attributed per user, team, and agent.
Policy & approvalsOne Cedar policy plus human-in-the-loop on risky actions.
Observability & auditEvery call traced, attributed, and on the record.
Managed agents get everything above — plus
Agents Record runs

Record Runtime

Kernel-level enforcement
Choose your agent harnessRecord-native or bring your own
Record RuntimeClaude CodeCodexADKHermesCustom
Sandbox + kernel enforcementSyscalls, files, and egress — not just the prompt.
Managed lifecycle + warm capacityRecord owns launch, scaling, readiness, and shutdown — with governance baked in.
Durable HITL resumeApprovals survive crashes, restarts, and deploys.
Runtime state & resumeCross-pod resume on conformance-tested adapters.
See it live

See it on your stack.

30 minutes with the founder — a working walkthrough on the systems you're trying to say yes to.