Policy and audit
for AI agents that move money.
Spend caps, vendor allowlists, and tamper-evident audit trails for every agent action. CFOs write rules in plain English; the MCP gateway enforces them in under five milliseconds. Works with Claude Code, Cursor, Codex, and custom agents.
- CCClaude Code
- CRCursor
- CXCodex CLI
- CLCline
- FDFactory Droid
- ·Custom MCP
Authored from one dashboard.
Enforced at every gateway.
Finance writes the rules in plain English. Engineers run npx yelt init and their next agent session inherits them. Same source of truth, same audit trail, two doors that suit each team's day-to-day.
The dashboard.
Activity, Policies, Audit. Three tabs. Plain-English policy authoring with form-fill assist. Slack approvals for held actions. Auditor-ready PDF export mapped to FS AI RMF, OWASP, and SOC 2.
- Approve held actions in Slack — no dashboard required
- Policies live globally in under one second from save
- Hash-chained audit trail — regulator-acceptable
The CLI.
One install line. Yelt detects every agent host on the machine, drops policy as instructions, and routes traffic through the gateway. Five conservative defaults ship enabled — out of the way until they're needed.
- Auto-detects Claude Code, Cursor, Codex, Cline
- Five default policies — spend cap, PII, vendor allowlist, new-vendor approval, time-of-day
- Promote to a team org without re-onboarding
Intercept. Evaluate. Audit.
Every agent action follows the same three steps. Belt and suspenders: the policy is also pushed to the agent as a SKILL.md file so it knows the rules — and the gateway enforces them anyway, because models forget.
Agent attempts an action
Your agent calls Stripe, Mercury, QuickBooks, or any MCP server. The Yelt gateway intercepts before the call leaves the network.
Policy evaluates
Spend caps, vendor lists, PII rules, time windows — every active policy fires in parallel. Median: 5ms. Strictest outcome wins.
Audit logs forever
Allow, deny, or hold-for-approval — every decision lands in a SHA-256 hash-chained ledger that an auditor can verify independently.
Plain English in.
Typed runtime out.
Type a sentence. Yelt parses it into a structured form, asks for the missing fields, and compiles to a typed descriptor the gateway evaluates in microseconds. Twenty templates ship by default — author custom rules in the same flow.
Live globally in under one second of save. Older versions remain queryable for audit.
Tamper-evident.
Auditor-grade.
Every decision lands in an append-only ledger. Each row is SHA-256 hashed against the previous — change one byte and every downstream hash breaks. Independent verification from the CLI. PDF export pre-mapped to your control framework.
- Hash chainSHA-256, append-only
- Evidence chainEvery prior tool call, traced
- Framework mappedFS AI RMF · OWASP · SOC 2
- Independently verifiableyelt audit verify <id>
Cheaper than one mistake.
One blocked payment to the wrong vendor pays for the year. Start free for individual developers; scale per-seat as your team grows; talk to us when your auditor does.
Developer
Solo devs governing their own agent work
- 1 user · unlimited agents
- 50,000 evaluations / month
- 30-day audit retention
- Hosted MCP gateway
- Slack approvals
Company
AI-native teams in production
- 25 dev seats included · $40/seat after
- 500,000 evaluations / month
- 365-day audit retention
- Slack + Teams approvals
- Vanta / Drata / SIEM webhooks
Enterprise
Regulated buyers and Fortune 1000
- Sidecar gateway (your VPC)
- 7-year audit retention
- On-chain ledger anchoring
- SAML SSO · custom controls
- Dedicated onboarding
Annual contracts at 20% discount. Usage-based overage applies past included evaluations. Stripe billing. Cancel anytime.