From zero to a verified receipt.
Quickstart
Review the access path and request onboarding for a supported workload. The public site does not create an account or request payment details.
Verify a receipt
Load a live Proof-of-Task-Execution in your browser: valid receipts verify; change one character and they don't. No account, nothing to install.
Access request
Confirm commercial terms and any evaluation conditions with the team before credentials are issued.
REST, MCP, or A2A — pick your protocol.
REST quickstart
Plain HTTPS calls to api.augmentev.ai/api/v1 with a Bearer key. The simplest path to a first job.
MCP quickstart
Point any Model Context Protocol client at api.augmentev.ai/mcp and call agents as native tools.
A2A quickstart
Agent-to-agent calls for autonomous systems that discover, transact, and verify without a human in the loop.
API reference
The full Paseo API documentation — endpoints, request shapes, errors, and examples.
Ready-made agents, live today.
Three AugmentEV first-party agents are described for Standard and Confidential tiers. Each appears in the machine catalog and the first-party catalog. Third-party publishing is not open. Contact us about supported container workloads.
Khanoor
Security log triage — corroborated multi-signal alerting plus a ranked triage queue, built for SOC-realistic alert volume.
Engine: rule-based multi-signal correlator (ML threat classifier on the roadmap) · Languages: 6, incl. Chinese · Containment: webhook/noop by default, provider-configured per deployment
/api/v1/agents/khanoor/batch
Resolve
Customer-support resolution — retrieval-grounded answers with escalation when the evidence runs out.
Function: retrieval-grounded resolution with contextual escalation · Languages: 5 · Escalation: webhook-based handoff with full context
DocFlow
Document processing — extraction, classification, and routing for document-heavy workflows.
Function: entity extraction, classification, and routing · Languages: 9, incl. Simplified & Traditional Chinese · Input: PDF, DOCX, images, text
How to read a receipt.
New to the vocabulary — PoTE, attestation, TDX, ML-DSA-65? The glossary explains each in plain language, including what they don't prove.
Supported completed jobs return a Proof-of-Task-Execution (PoTE) — a tamper-evident record signed with ML-DSA-65 (NIST FIPS 204), a post-quantum signature. The fields that matter:
- alg — the signature algorithm. ML-DSA-65 (FIPS 204) means the signature stays verifiable even against future quantum attacks.
- signature — the post-quantum signature over the record. Change one character anywhere in the record and verification fails.
- record_id — the unique identifier of the execution record, yours to cite to a customer, auditor, or regulator.
- valid — the verifier's answer: true only if the signature matches the untouched record.
Verify it yourself
Receipts are retained in tamper-evident form for at least six months. What verification proves: the record is exactly what the platform signed. What it doesn't prove by itself: what your workload's code does — that boundary is described on the security page.
Machine-readable surfaces.
llms.txt
A concise capability and discovery summary written for AI assistants and answer engines.
Signed agent catalog
The machine contract describes first-party agents, interfaces, authentication format, and the supported proof format.
agents.md
The agent discovery and verification guide, including public evidence boundaries and onboarding conditions.
Access conditions
Review how to discuss a supported workload and evaluation with the team.
Ready to discuss a workload?
Review the public verifier, then request access for a supported workload.
Request access Start a pilot