Outcomes, not tokens.
Made into infrastructure.

AgentGuard records which configured outcome ran, its policy decision, model, measured token use and cost, and the runtime's local status. A signature protects the recorded metadata from later editing; it does not independently prove a real-world business result or human identity. AgentGuard does not receive prompts or completions; your configured model provider does.

"Applied AI is about jobs to be done, not tokens to be consumed. Token usage may be a reasonable short-term proxy for adoption. But long term, success comes from outcomemaxxing, not tokenmaxxing."

@SierraPlatform · outcomes-based pricing for AI agents, May 27, 2026  ·  amplified by @saranormous (Conviction)

Business outcome examples, mapped to shipped vertical catalogs

"A mortgage completed"

→ related catalog
@agentguard-run/spend/verticals: realestate

The current catalog covers transaction deadlines, lease abstraction, fair-housing copy checks, property operations, screening records, comps assembly, and disclosure packets. It records configured SDK steps; it does not establish that a mortgage closed.

"An order returned"

→ related catalog
@agentguard-run/spend/verticals: ecommerce

The implemented return and refund template is read-only: it applies the supplied policy to supplied order facts, recommends a next step, and requires human approval. It never executes a refund. Signing can bind that configured decision metadata.

"A customer saved"

→ measurement boundary
@agentguard-run/spend/verticals: ecommerce

The current catalog can draft source-grounded support replies and chargeback materials. It contains no customer-retention or saved-customer verifier. A customer's application must measure the business result separately.

"A policy comparison drafted"

→ related catalog
@agentguard-run/spend/verticals: insurance

The insurance catalog includes source-grounded policy variance, ACORD extraction, commission reconciliation, loss-run, renewal, COI, and FNOL templates. Reviewer behavior and receipt signing depend on runtime configuration.

"A basket size increased"

→ measurement boundary
@agentguard-run/spend/verticals: ecommerce

The current catalog has no basket-size or conversion verifier. It can record governed model calls for implemented ecommerce templates, but the merchant must measure any change in order value.

"A contract closed"

→ related catalog
@agentguard-run/spend/verticals: law

The law catalog includes source-grounded clause extraction, chronologies, deposition summaries, billing entries, document assembly, and factual drafting. Its disclaimer keeps a licensed attorney as human of record; it does not close a contract.

"Books closed"

→ related catalog
@agentguard-run/spend/verticals: accounting

The accounting catalog includes source-grounded categorization, reconciliations, document extraction, trial-balance comparison, return-data preparation, and a month-end close package. Its runtime status does not independently attest that books are closed or compliant.

"Your custom outcome"

→ implemented paths
@agentguard-run/spend/outcomes

Implement an OutcomeTemplate with the outcome-runtime API, or scaffold local BYO outcome YAML with agentguard init. agentguard advisor writes one spend policy and quickstart; it does not execute or certify a business outcome.

Managed $99/mo: unlock hosted builder access

Your business doesn't fit a template? Build your own outcomes.

The Spend package exports five vertical outcome catalogs and a library API for custom templates. Advisor can be rerun; it writes a local policy.yaml and quickstart from your answers. The current Managed plan exposes the hosted Outcome Builder:

See pricing →

One Advisor. Eight examples from nine recognized profiles.

agentguard advisor asks six setup questions and writes one local policy plus quickstart. Its nine explicit profiles affect suggested scope, capability, model pair, caps, and posture; unmatched input uses a generic fallback.

Law firm

→ recognized profile
matter scope · data_write

Suggests a matter-scoped policy, a compliance posture, a configured primary and fallback model, and spend caps based on the collected answers.

Insurance agency

→ recognized profile
policy scope · data_write

Suggests a policy-scoped configuration and compliance posture. The generated SpendPolicy does not itself create insurance outcome templates.

Shopify / e-commerce

→ recognized profile
order scope · payment_initiate

Suggests an order-scoped policy and standard posture. It does not execute refunds or create task-specific ecommerce routes by itself.

Accounting / bookkeeping firm

→ recognized profile
engagement scope · data_write

Suggests an engagement-scoped policy and compliance posture. Generated records are software logs, not certified or guaranteed compliance evidence.

Real estate / mortgage broker

→ recognized profile
transaction scope · data_write

Suggests a transaction-scoped policy, model pair, and caps. The separate vertical catalog supplies the implemented real-estate templates.

Local services / barbershop

→ recognized profile
job scope · data_write

Recognizes listed local-service terms and writes a job-scoped policy. It does not ship a booking adapter or complaint workflow.

Marketing / consulting agency

→ recognized profile
campaign scope · data_write

Writes a campaign-scoped SpendPolicy. Receipt signing remains optional configuration and invoice attachment is the customer's integration.

Software team

→ recognized profile
repo scope · read_only

Suggests a repository-scoped read-only policy for software terms. Healthcare is the ninth explicit profile; unmatched startup language uses the generic fallback.

How an outcome receipt works

Step 1 · Define

Outcome + budget

Select an implemented vertical catalog or configure an OutcomeTemplate. Templates carry a capability, model route, spend cap, prompt version, inputs, output format, and quality-gate settings.

Step 2 · Enforce

Before configured model calls

The outcome runtime asks the in-process Spend guard before each drafter, reviewer, or fallback call it runs. Your configured runner sends prompts directly to your selected provider. AgentGuard does not receive prompts or completions; your configured model provider does.

Step 3 · Prove

Signed, chained, verifiable

Signing requires configured Ed25519 keys and decision-log storage. A reviewer with the public key can then verify the signature and hash chain offline or in the browser verifier. That check establishes record integrity, not the truth or legal effect of a business outcome.

Install and inspect the implemented paths

# 1. install the SDK
$ npm install @agentguard-run/spend
# Production use is available up to 10,000 enforcement calls per calendar month under the package license.

# 2. configure a provider key for Advisor; AgentGuard does not receive it
$ agentguard auth openrouter

# 3. write a local spend policy and quickstart
$ agentguard advisor

# 4. agentguard demo produces a deterministic signed decision receipt, not external proof of a business outcome
$ agentguard demo
$ npm install @agentguard-run/spend verify an outcome receipt →

Why now

Sierra published the outcome-based pricing thesis in December 2024. @saranormous (Conviction GP) amplified it on May 27, 2026. The "tokenmaxxing → outcomesmaxxing" pivot is moving from thesis to default expectation across Applied AI buyers right now.

Outcome-based operations can use outcome-aware infrastructure: per-outcome budgets, capability checks, local quality-gate status, and optional signed technical records. AgentGuard ships those software mechanisms. AgentGuard is patent-pending. The SDK, five vertical catalogs, and AgentGuard Advisor are available under their published package terms.

see the tiers → OpenRouter quickstart