Outcomes, not tokens.
Made into infrastructure.

AgentGuard proves what the AI agent attempted, who authorized it, what it cost, and whether it succeeded. A cryptographic proof-of-outcome receipt for every action. Powered by @OpenRouter. Zero data plane.

"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)

Sierra's outcome examples, mapped to AgentGuard skills

"A mortgage completed"

→ produced by
agentguard-spend-real-estate

Per-transaction caps on mortgage doc review, comps research, contract analysis. Each completed loan ships with a signed receipt chain proving every AI-assisted step.

"An order returned"

→ produced by
agentguard-spend-ecommerce

Per-order budgets for RMA processing + refund authorization. Capability gates restrict refund authorization to payment_initiate-tier agents. Signed receipt = cryptographic context for PCI-DSS review.

"A customer saved"

→ produced by
agentguard-spend-ecommerce

Per-interaction budgets for chargeback package drafting + customer retention workflows. Each saved customer produces a Visa CE 3.0 receipt package with source pointers.

"A policy comparison drafted"

→ produced by
agentguard-spend-insurance

Per-client budgets for quote letters, policy comparisons, certificates of insurance, renewals, and lead qualification. Reviewer Cascade runs on E&O-sensitive outcomes and produces a signed receipt for each AI-assisted step.

"A basket size increased"

→ produced by
agentguard-spend-ecommerce

Per-recommendation budgets for upsell + cross-sell suggestions. Signed receipt links the recommendation to the order, the model, and the conversion.

"A contract closed"

→ produced by
agentguard-spend-law-firm

Per-matter budgets across contract redlining, legal research, brief drafting. Attorney-client-privilege-aware capability gates. Signed receipts can be reviewed in malpractice insurance audits at the reviewer's discretion.

"Books closed"

→ produced by
agentguard-spend-accounting

Per-engagement budgets for receipt OCR, GL categorization, month-end accruals. PCAOB AS 1215 citation-aware documentation. Signed receipts attach to SOX-regulated work product for review.

"Your custom outcome"

→ produced by
agentguard advisor

Don't fit one of the 5 templates? Run agentguard advisor: local LLM walks you through defining YOUR outcomes, assigns the cheapest model that delivers each, sets per-outcome budgets. Customize beyond templates on the Solo tier.

Solo $49/mo: unlock outcome builder

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

The free tier ships with 5 pre-built vertical skills and one-shot agentguard advisor for unique businesses. The Solo tier unlocks the full Outcome Builder:

See pricing →

One Advisor. Eight industry flavors.

agentguard advisor is one CLI command that becomes a different kind of advisor depending on what business you run. Same engine, vertical-aware recommendations.

Law firm

→ becomes your
AI policy advisor

Defines outcomes per matter, recommends models per task type, flags privileged-content workflows that need higher capability tiers.

Insurance agency

→ becomes your
AI producer-workflow advisor

Defines outcomes per policyholder, routes comparisons and quote letters through Reviewer Cascade, sets low caps for renewals and certificates of insurance.

Shopify / e-commerce

→ becomes your
AI support-cost advisor

Defines outcomes per order, routes triage to cheap models and chargeback packages to opus, sets peak-season cap flexing rules.

Accounting / bookkeeping firm

→ becomes your
AI workflow advisor

Defines outcomes per engagement, recommends month-end vs everyday model routing, generates SOX-grade per-client billing trails.

Real estate / mortgage broker

→ becomes your
AI transaction advisor

Defines outcomes per closing, routes contract analysis vs listing copy to different models, flags fair-housing-sensitive content.

Local services / barbershop

→ becomes your
AI booking/spend advisor

Defines outcomes per appointment, sets receptionist-AI budgets, routes high-volume booking to cheap models, escalates complaints to better ones.

Marketing / consulting agency

→ becomes your
AI delivery-cost advisor

Defines outcomes per client deliverable, sets per-engagement budgets, attaches signed AI-cost trails to client invoices.

Startup / scaleup

→ becomes your
AI agent governance advisor

Defines outcomes per user-facing agent, sets capability tiers for human-in-the-loop vs autonomous actions, produces signed logs for investor review.

How an outcome receipt works

Step 1 · Define

Outcome + budget

Pick a vertical skill or run agentguard advisor. Each outcome gets: required capability tier, allowed models, per-outcome budget cap, downgrade fallback.

Step 2 · Enforce

Locally, on every call

The SDK wraps your OpenAI / Anthropic / Bedrock / OpenRouter client. Before each call: budget check, capability gate, model selection. Block, downgrade, shadow, or allow. Zero data leaves your runtime.

Step 3 · Prove

Signed, chained, verifiable

Every decision is Ed25519-signed and hash-chained. Auditor, reviewer, or buyer can verify the chain offline or paste it into agentguard.run/verify for browser-side validation. No vendor attestation needed.

Install + define your first outcome in 90 seconds

# 1. install the SDK (free, unlimited, forever)
$ npm install @agentguard-run/spend

# 2. bring your own OpenRouter key (it stays in your env, we never see it)
$ agentguard auth openrouter

# 3. let local LLM walk you through defining outcomes for your business
$ agentguard advisor

# 4. see a real signed outcome receipt
$ 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 pricing requires outcome-based infrastructure: per-outcome budgets, capability-gated authorization, cryptographic proof every outcome happened. That's what AgentGuard ships. 6 US patent provisionals on the underlying primitives. Free SDK. Free 5 vertical skills. Free AgentGuard Advisor for any business.

see the tiers → OpenRouter quickstart