Why deterministic-only?
AI language models are probabilistic. A well-crafted vendor prompt or an unusual negotiation context could, in principle, nudge an LLM-based approver toward a favourable decision it shouldn’t make. Tavryn eliminates this entire attack surface by placing an inviolable math layer between the negotiation and the wallet. No matter what the negotiation agent concludes, a $10,000 transaction against a $2,000 autonomous ceiling returnsneeds_human — every time, without exception.
The LLM cannot approve transactions. Policy evaluation is performed exclusively by deterministic TypeScript code. The negotiation agent’s output feeds into the policy check as input data only — it has no mechanism to influence the outcome of the policy evaluation itself.
Policy parameters
You configure the following parameters per organisation. All values are fetched fresh on every evaluation — there is no in-memory caching that could serve stale limits.max_auto_transaction
The autonomous spending ceiling in USDC. Any proposed transaction at or below this value can be executed without human involvement, provided all other checks pass.
- Default:
2000 - Transactions above this value return
needs_humanand trigger a supervisor approval link.
min_savings
The minimum projected annual savings required to justify initiating a renegotiation. If the agent calculates that renegotiation would yield less than this amount, the deal is rejected outright — it’s not worth the operational overhead.
- Default:
200 - Deals below this threshold return
rejectedunless a human override is explicitly configured for the evaluation context.
human_approval_required_above
A separate escalation threshold that triggers supervisor notification regardless of the autonomous ceiling. Useful when you want a human in the loop for any transaction above a certain size even if your max_auto_transaction is higher.
- Default:
2000 - When the transaction amount exceeds this value, the engine adds a
needs_humanflag alongside any other checks.
allowed_categories
The whitelist of spend categories the agent is permitted to negotiate within. Any transaction in a category not on this list is hard-rejected (rejected) immediately — it does not escalate to a human, it stops.
Supported category values:
software
cloud
contractors
infrastructure
legal
marketing
category_budgets
An optional per-category monthly budget expressed as a USDC amount. The engine tracks cumulative spend for the current calendar month and adds the proposed transaction amount before comparing against the limit.
- If
prior_spend + proposed_amount > category_budgetbutproposed_amount <= category_budget, the engine returnsneeds_human— you may still want to approve it. - If
proposed_amount > category_budgeton its own, the engine returnsrejected. - If no budget is configured for a category, the check is skipped automatically.
How a policy check works
The policy engine runs seven sequential checks. All checks run regardless of earlier failures so you receive a complete diagnostic, not just the first error.
The final verdict is determined by strict priority:
rejected beats needs_human beats approved. A single hard rejection prevents human escalation — those cases require a policy change, not a supervisor override.
1-tap HMAC-SHA256 approval links
When a transaction returnsneeds_human, Tavryn generates a cryptographically signed approval link delivered out-of-band to your designated supervisor. The token is an HMAC-SHA256 signature over the transaction parameters, scoped to a single negotiation ID.
Token properties:
- Expires 48 hours after generation
- Single-use only — the first redemption atomically marks the token as consumed, preventing concurrent double-approvals
- Scoped to a specific negotiation — a token generated for one deal cannot authorise a different deal
- Every approval requires the negotiation context to be present; open-ended business-wide approvals are explicitly prohibited
Server-side enforcement
In addition to the policy engine itself, Tavryn enforces policy a second time server-side immediately before any escrow creation or payment execution. This server-side guard:- Fetches your organisation’s policy directly from the database (never from a request parameter)
- Queries live treasury balance from the Arc network via JSON-RPC, with a database fallback
- Calculates real cumulative category spend for the current calendar month
- Re-runs the full policy check with all live values
- Verifies a valid, unused human approval record for the exact negotiation, when required