CAIN-42 MCPGateAGENTIC AI 75 · PRODUCTS
Seventy-five products and services
Each 2026 agentic development productised into a fixed-scope offer: buyer, deliverable, price band, exclusions and an honest delivery status. 41 can produce a bounded engine artifact today.
Last reviewed 2026-11-11
75 products and services, one per 2026 agentic development. 41 are DELIVERABLE today: an engine in this repository produces a bounded, unsigned artifact from a sample. 21 are PILOT, 0 ADVISORY and 13 DESIGN. The status is the buying instruction, not a slogan.
The 75 governance pages · machine-readable catalog · the 75 in one table · public product evidence on clawx.click
What the four statuses mean
DELIVERABLE (41)
An engine in this repository produces a bounded artifact from a supplied sample today.
PILOT (21)
Library code or a live mechanism exists; a bounded pilot needs engineering time.
ADVISORY (0)
Simulation or advisory only. No production engine is delivered.
DESIGN (13)
A design-partner engagement. No engine or control is delivered.
How a delivery works
No engine runs from a public web request. An operator runs the catalog CLI against a sample the buyer supplies, reviews the output, and sends three files: findings.json, report.md and manifest.json. The manifest is a SHA-256 integrity record; it is not a signature and not an attestation.
python3 -m cain_agentic_products.cli selftest
python3 -m cain_agentic_products.cli deliver CAIN-A75-014 --out work/acme/014The self-test runs every DELIVERABLE SKU and verifies its manifest. It reports 41/41 on this build. If a SKU cannot produce a verified artifact, it is not marked DELIVERABLE.
Seven product lines
Code & Proof (12)
Prove the fix, not just the diff.
Platform engineering, AI coding-tool vendors, security engineering
$1,500–$6,000 per audit; $2,500–$4,000/month retainer
Memory & Context (8)
Memory that cannot launder authority.
Agent-platform teams, enterprise AI governance, regulated data owners
$2,500 per audit; metered from $0.0002 per inspection
Identity & Authority (13)
Every agent, every delegation, every boundary.
CISO, IAM, platform security, agent-tool vendors
$2,500–$7,500 per review; integration from $10,000
Commerce & Payments (13)
Delegated spending with a ceiling and a receipt.
Fintech, commerce platforms, marketplaces, treasury teams
$2,500–$7,500 per review; integration from $10,000
Physical & Lab (9)
A validity check between the plan and the machine.
Lab automation, robotics, industrial operations, construction technology
$5,000–$15,000 per engagement
Swarm & Multi-Agent (5)
Delegation you can follow across every hop.
Agent orchestrator vendors, research labs, enterprise platform teams
$3,500–$7,500 per audit; $2,500–$4,000/month retainer
Runtime Containment & Evidence (15)
Contain first, then prove what happened.
SOC, incident response, compliance, enterprise IT
$2,500–$5,000 per review; $2,000–$10,000 per evidence pack
Code & Proof (12)
Prove the fix, not just the diff. Entry offer: Fabrication audit or long-run engineering attestation.
| SKU | Product / service | Kind | Status | Price (proposal) |
|---|---|---|---|---|
| CAIN-A75-001 | Long-Run Engineering Attestation #1 Full-day autonomous software engineering | Assessment | DELIVERABLE | $3,500 per run audit; $1,500–$6,000 fixed audits |
| CAIN-A75-004 | Proof-Carrying Change Review #4 Machine-checkable security proofs | Assessment | DELIVERABLE | $5,000–$15,000 per proof review |
| CAIN-A75-009 | Autonomous R&D Change Review #9 End-to-end autonomous R&D loops | Assessment | DELIVERABLE | $5,000–$12,000 per review |
| CAIN-A75-010 | Failure-Driven Improvement Audit #10 Failure-driven agent improvement | Assessment | DELIVERABLE | $3,500–$7,500 per audit |
| CAIN-A75-011 | Formal Artifact Review #11 Self-supervised theorem discovery | Assessment | DELIVERABLE | $5,000–$12,000 per review |
| CAIN-A75-023 | Vulnerability-to-Patch Proof #23 Autonomous vulnerability investigation and repair | Fix + Prove | DELIVERABLE | $2,500–$5,000 per engagement |
| CAIN-A75-024 | Coding-Agent Action Gate #24 Coding agents inside native development tools | Assessment | DELIVERABLE | $2,500–$5,000 per review |
| CAIN-A75-038 | Parallel Agent Run Review #38 Multi-agent desktop supervision | Assessment | PILOT | $2,500–$5,000 per review |
| CAIN-A75-041 | Creative Workflow Provenance #41 Multistep creative agents | Assessment | PILOT | $2,500–$5,000 per review |
| CAIN-A75-054 | Deployment Trace Evaluation #54 Deployment-driven agent benchmarks | Evaluation | PILOT | $3,500–$7,500 per audit |
| CAIN-A75-058 | Framework Evaluation Review #58 Repeated-run comparisons of agent frameworks | Evaluation | PILOT | $5,000–$12,000 per study |
| CAIN-A75-062 | Local Agent Containment Review #62 Local AI coding on personal computers | Assessment | PILOT | $3,500–$7,500 per review |
Memory & Context (8)
Memory that cannot launder authority. Entry offer: Memory authority audit; hosted memory-sanitisation pilot.
| SKU | Product / service | Kind | Status | Price (proposal) |
|---|---|---|---|---|
| CAIN-A75-014 | Memory Authority Audit #14 Persistent, correction-aware agent memory | Assessment | DELIVERABLE | $2,500 per audit; pilot from $5,000 |
| CAIN-A75-015 | Context Integrity Review #15 Retained reasoning and context compaction | Assessment | DELIVERABLE | $3,500–$7,500 per review |
| CAIN-A75-016 | Memory Consolidation Review #16 Offline memory consolidation (dreaming) | Assessment | DELIVERABLE | $3,500–$7,500 per review |
| CAIN-A75-029 | Personal Context Review #29 Personal context connected to mobile actions | Assessment | DELIVERABLE | $3,500–$7,500 per review |
| CAIN-A75-031 | Context Graph Review #31 Shared organisational context graphs | Assessment | DELIVERABLE | $5,000–$12,000 per review |
| CAIN-A75-055 | Memory Evaluation Review #55 Multi-session memory evaluation | Assessment | PILOT | $3,500–$7,500 per evaluation review |
| CAIN-A75-065 | Mobile Data Boundary Review #65 Work–personal data separation for mobile agents | Assessment | DESIGN | $5,000–$12,000 per review |
| CAIN-A75-072 | Saved Workflow Review #72 Reusable user-defined workflow skills | Assessment | DELIVERABLE | $2,500–$5,000 per review |
Identity & Authority (13)
Every agent, every delegation, every boundary. Entry offer: Agent authority review; MCP/A2A boundary review.
| SKU | Product / service | Kind | Status | Price (proposal) |
|---|---|---|---|---|
| CAIN-A75-017 | Portable Skill Review #17 Agent skills as a portable ecosystem standard | Assessment | DELIVERABLE | $2,500–$5,000 per review |
| CAIN-A75-021 | Agent Credential Review #21 Task-scoped, short-lived agent credentials | Assessment | DELIVERABLE | $3,500–$7,500 per review |
| CAIN-A75-030 | Business-System Connector Review #30 Agent communication across business systems | Assessment | DELIVERABLE | $2,500–$5,000 per review |
| CAIN-A75-033 | Clinical Tool Boundary Review #33 Pathology agents as interoperable MCP tools | Assessment | DELIVERABLE | $5,000–$12,000 per review |
| CAIN-A75-040 | Creative Tool Boundary Review #40 Native creative-project editing through MCP | Assessment | DELIVERABLE | $2,500–$5,000 per review |
| CAIN-A75-046 | Ontology & Policy Review #46 Business ontologies for regulated-industry agents | Assessment | PILOT | $5,000–$12,000 per review |
| CAIN-A75-050 | Agent Interaction Risk Review #50 Banking detection of agent activity | Assessment | PILOT | $5,000–$12,000 per review |
| CAIN-A75-051 | Agent Identity Review #51 Know Your Agent identity intelligence | Assessment | PILOT | $5,000–$12,000 per review |
| CAIN-A75-060 | Research Toolchain Review #60 Composable web-research toolchains | Assessment | DELIVERABLE | $3,500–$7,500 per review |
| CAIN-A75-061 | Domain Model Authority Review #61 CRM-specialised reasoning models | Assessment | DESIGN | $5,000–$12,000 per review |
| CAIN-A75-063 | Chat Approval Review #63 Agent permission review inside collaboration tools | Assessment | PILOT | $2,500–$5,000 per review |
| CAIN-A75-068 | Third-Party Agent Review #68 Bring-your-own-agent advertising | Assessment | DESIGN | Advisory from $10,000 |
| CAIN-A75-069 | Interop Authority Review #69 Agentic advertising interoperability standards | Assessment | DESIGN | Advisory from $10,000 |
Commerce & Payments (13)
Delegated spending with a ceiling and a receipt. Entry offer: Payment-mandate review; browser-agent checkout review.
| SKU | Product / service | Kind | Status | Price (proposal) |
|---|---|---|---|---|
| CAIN-A75-022 | Agent Wallet Mandate Review #22 Bounded agent identities and wallets | Assessment | DELIVERABLE | $3,500–$7,500 per review |
| CAIN-A75-028 | Mobile Agent Action Review #28 Cross-application mobile task execution | Assessment | DELIVERABLE | $3,500–$7,500 per review |
| CAIN-A75-047 | Commerce Protocol Authority Review #47 Universal commerce protocol | Assessment | DESIGN | Advisory from $10,000 |
| CAIN-A75-048 | Agent Checkout Mandate Review #48 Browser payments without exposing card details | Assessment | DELIVERABLE | $3,500–$7,500 per review |
| CAIN-A75-049 | Web Tool Definition Review #49 Structured website actions through WebMCP | Assessment | DELIVERABLE | $2,500–$5,000 per review |
| CAIN-A75-052 | Agent-to-Agent Deal Review #52 Controlled agent-to-agent commerce experiments | Assessment | PILOT | $5,000–$12,000 per review |
| CAIN-A75-053 | Consumer Agent Authority Review #53 Consumer agents connected to real services | Assessment | DESIGN | Advisory from $10,000 |
| CAIN-A75-057 | Commerce Refusal Review #57 Shopping benchmarks that reward refusing bad purchases | Assessment | DELIVERABLE | $2,500–$5,000 per review |
| CAIN-A75-059 | Browser Agent Control Review #59 More efficient browser representations and action loops | Assessment | PILOT | $2,500–$5,000 per review |
| CAIN-A75-066 | Browser Errand Review #66 Mobile browser agents for real-world errands | Assessment | PILOT | $2,500–$5,000 per review |
| CAIN-A75-067 | Campaign Authority Review #67 Agent-to-agent advertising execution | Assessment | DESIGN | Advisory from $10,000 |
| CAIN-A75-070 | Brand Agent Review #70 Retailer-controlled agents in search | Assessment | DESIGN | Advisory from $7,500 |
| CAIN-A75-074 | Mobile Expansion Review #74 Broader international mobile-agent deployment | Assessment | DESIGN | $5,000–$12,000 per review |
Physical & Lab (9)
A validity check between the plan and the machine. Entry offer: Physical-action assurance review (advisory, simulation-first).
| SKU | Product / service | Kind | Status | Price (proposal) |
|---|---|---|---|---|
| CAIN-A75-002 | Physical Autonomy Assurance Review #2 Agent-operated molecular-biology laboratories | Assessment | DELIVERABLE | $7,500–$15,000 per engagement |
| CAIN-A75-003 | Discovery Loop Evidence Review #3 Closed-loop experimental discovery | Assessment | DELIVERABLE | $5,000–$12,000 per review |
| CAIN-A75-007 | Physical Action Twin Review #7 Digital twins for safe physical agent actions | Assessment | DELIVERABLE | $7,500–$15,000 per engagement |
| CAIN-A75-008 | Robotics Release Gate Review #8 Robot programming through agent teams | Assessment | DELIVERABLE | $7,500–$15,000 per review |
| CAIN-A75-012 | Research Evidence Review #12 Experimentally validated biological binder discovery | Assessment | DELIVERABLE | Advisory engagement from $10,000 |
| CAIN-A75-032 | Research Retrieval Provenance #32 Agent-assisted search through biological archives | Assessment | DELIVERABLE | Advisory from $7,500 |
| CAIN-A75-043 | Physical Schedule Assurance Review #43 Agentic construction scheduling | Assessment | DESIGN | Advisory from $10,000 |
| CAIN-A75-044 | Contract Evidence Review #44 Evidence-based construction change orders | Evidence Pack | DESIGN | $7,500–$15,000 per engagement |
| CAIN-A75-073 | Industrial Knowledge Review #73 Industrial expertise captured as agents | Assessment | DESIGN | Advisory from $10,000 |
Swarm & Multi-Agent (5)
Delegation you can follow across every hop. Entry offer: Swarm delegation audit; collusion and drift review.
| SKU | Product / service | Kind | Status | Price (proposal) |
|---|---|---|---|---|
| CAIN-A75-005 | Research Provenance Review #5 Open-world multi-agent mathematical discovery | Assessment | DELIVERABLE | $3,500–$7,500 per review |
| CAIN-A75-006 | Swarm Delegation Audit #6 Single-prompt coordination of specialised agent teams | Assessment | DELIVERABLE | $3,500–$7,500 per audit |
| CAIN-A75-013 | Multi-Model Orchestration Review #13 Multi-model workflow orchestration | Assessment | DELIVERABLE | $3,500–$7,500 per review |
| CAIN-A75-025 | Fleet Governance Design Review #25 Reported orchestration of 10,000 concurrent agents | Assessment | DELIVERABLE | Advisory from $10,000 |
| CAIN-A75-039 | Fast-Path Authority Review #39 Faster models for collaborative subagents | Assessment | PILOT | $3,500–$7,500 per review |
Runtime Containment & Evidence (15)
Contain first, then prove what happened. Entry offer: Runtime containment review; signed evidence pack.
| SKU | Product / service | Kind | Status | Price (proposal) |
|---|---|---|---|---|
| CAIN-A75-018 | Enterprise Agent Governance Review #18 Full-stack agent safety infrastructure | Assessment | DELIVERABLE | $5,000–$12,000 per review; appliance from $50k/yr |
| CAIN-A75-019 | Runtime Containment Audit #19 Runtime agent quarantine | Retainer | DELIVERABLE | $2,500–$5,000 per audit; $1,500–$4,000/month retainer |
| CAIN-A75-020 | OS Containment Review #20 Operating-system-enforced agent containment | Assessment | DELIVERABLE | $5,000–$12,000 per review |
| CAIN-A75-026 | Signed Deliverable Pack #26 Finished knowledge-work deliverables | Evidence Pack | DELIVERABLE | $2,000–$10,000 per pack |
| CAIN-A75-027 | Agent Lease Review #27 Always-on workplace teammates | Retainer | DELIVERABLE | $3,500–$7,500 per review |
| CAIN-A75-034 | Regulated Workflow Evidence Review #34 Clinical-trial oversight agents | Evidence Pack | DELIVERABLE | $7,500–$15,000 per engagement |
| CAIN-A75-035 | Real-Time Agent Gate Review #35 Voice agents that reason while listening | Assessment | DELIVERABLE | $3,500–$7,500 per review |
| CAIN-A75-036 | Threat Investigation Evidence Review #36 Evidence-grounded threat investigation | Evidence Pack | PILOT | $2,500–$5,000 per review |
| CAIN-A75-037 | Enterprise Execution Governance #37 Enterprise agent execution with governance | Assessment | PILOT | $5,000–$12,000 per review; appliance from $50k/yr |
| CAIN-A75-042 | Background Agent Lease Review #42 Continuous creative-production agents | Retainer | DESIGN | $3,500–$7,500 per review |
| CAIN-A75-045 | Approval-Gated Remediation Review #45 IT investigation with approval-gated remediation | Retainer | PILOT | $2,500–$5,000 per review |
| CAIN-A75-056 | Benchmark Evidence Review #56 Visually complex knowledge-work evaluation | Evaluation | PILOT | $2,500–$5,000 per review |
| CAIN-A75-064 | Agent Inventory Review #64 Enterprise agent inventory and cost accountability | Retainer | PILOT | $5,000–$12,000 per review |
| CAIN-A75-071 | Proactive Agent Lease Review #71 Proactive personal assistants | Retainer | PILOT | $3,500–$7,500 per review |
| CAIN-A75-075 | Delegation Measurement Review #75 Observational evidence of larger task delegation | Assessment | PILOT | $2,500–$5,000 per review |
What this offer is not. No customer, partnership, endorsement, certification, patent or third-party audit is claimed. Prices are proposals, not validated rates. DELIVERABLE means a bounded engine run on a sample, not an assessment of a production system. Built by a three-person team.