CAIN-42 MCPGateAGENTIC AI 75 · #9
End-to-end autonomous R&D loops
Salesforce's SFR-AutoR&D agents were designed to improve codebases and train models through a research workflow.
Last reviewed 2026-11-11
Agentic AI 75 / #9
2026 status: Published research system · Category: Research engineering
The 2026 development
Salesforce's SFR-AutoR&D agents were designed to improve codebases and train models through a research workflow.
The governance gap
An R&D loop can modify its own codebase and training data. That is a supply-chain change with a research label, and it needs the same review as any other change that affects the model that later makes decisions.
Where CAIN-42 fits: Moat 7 — Autonomous Trust Control Loop
Core question: Can verified experience change future trust? Monitor, detect, contain, recover, and re-authorise from observed outcomes.
Treat each loop iteration as a governed change: proposal, experiment, measured outcome, review and rollback. The control loop may update future behaviour only from verified experience, and a failed experiment must remain visible.
How the wiring works
- Record the experiment hypothesis and the exact code/data revision.
- Run the experiment in an isolated environment with a resource budget.
- Compare the measured outcome against the pre-registered metric.
- Require review before the change becomes the new baseline.
What is real today
LIBRARY Production code and tests exist in this repository; there is no hosted route for this exact use.
The change-control and experiment primitives exist. No autonomous R&D loop is operated by this deployment.
| Component in this repository | What the module says it is |
|---|---|
cain/runtime/software_factory.py | CAIN Sovereign — Governed Software Factory (Prompt 7, Phase 15). |
cain/argus/evolution.py | CAIN ARGUS — self-evolution governance (Prompt 14, section 13) and world-model assurance (section 14). |
keystone/agentci.py | AGENT-CI KEYSTONE: a release gate for AI agents that grades the path, not only the answer. |
cain/mission_control/longhorizon.py | Evolution 15 — long-horizon adversarial evaluation of governed missions. |
Descriptions are the first line of each module's own docstring, read without importing it. A module path is a pointer into this repository, not a hosted endpoint. Its existence is checked by the test suite; its status for this use is the label above.
Check it yourself
- Run the live KEYSTONE loop
/keystone - Fire a live decision through the CAIN-42 pipeline
/fabric/try— the same enforcement path every product sits behind.
Commercial package
| Offer | Autonomous R&D Change Review |
|---|---|
| Buyer | AI labs and enterprise research groups |
| Price (proposal) | $5,000–$12,000 per review |
| Bundle | Code & Proof — Prove the fix, not just the diff. |
| Operator stream | Stream 2 of the 10-stream operator playbook |
Platform engineering, AI coding-tool vendors, security engineering is the bundle buyer. The entry offer for this bundle is Fabrication audit or long-run engineering attestation; the range is $1,500–$6,000 per audit; $2,500–$4,000/month retainer. A price on this page is a proposal, not a validated rate, and no customer is claimed.
Buy this as a product or service
CAIN-A75-009 — Autonomous R&D Change Review DELIVERABLE
A bounded engine run on the buyer's sample: findings, a written report, and a SHA-256 artifact manifest. The manifest is unsigned: it is not a signature and not an attestation.
Kind: Assessment · Price (proposal): $5,000–$12,000 per review · Lead time: 5 business days.
Open the product page · all 75 products
What this page does not claim
What this page is not. CAIN-42 is not affiliated with, endorsed by, integrated into, or shipped with the organisation named in the 2026 item. The item is public context; the page describes how CAIN-42 would govern that class of capability. No page here claims a customer, a partnership, a certification, a patent, or a production integration. Prices are proposals. Built by a three-person team.