Controlled rehearsal proof
A controlled Campfire-style proof shows SDF attaching governed evidence to cloud-agent work, checking the PR reviewer surface, and catching incomplete or wrongly targeted PR publication.
The demo proof page shows controlled proof of the operating model: agent-generated work moves with evidence, the reviewer-facing PR description is checked against that evidence, and description remediation happens only with explicit permission.
Controlled proof only. No hosted enforcement, production/customer governance, automatic approval, automatic merge, automatic code repair, security certification, or guaranteed correctness is claimed.
Core proof line
Homepage proof stays buyer-friendly. This page carries the deeper evidence chain and boundaries.
Demo walkthrough
A short Loom walkthrough shows the current controlled path from assisted assessment context to completed governed PR proof.
Some browsers block embedded Loom playback. The direct link remains the reliable demo path.
Video not loading? Watch on Loom
The recording is a walkthrough of controlled rehearsal proof surfaces. The first commercial step remains a private free repo-backed readiness snapshot, then a paid readiness assessment plus first governed change where deeper evidence review is useful.
This is a controlled rehearsal proof walkthrough. It does not claim hosted enforcement, production/customer governance, automatic approval, automatic merge, billing-grade cost, or measured savings.
What the walkthrough proves
The walkthrough proves the full path from adoption to governed work without turning the GTM site into an execution surface.
This is what governed AI-assisted delivery looks like in practice: a bounded change, governed evidence, a reviewable PR surface, and committed evidence for drill-down.
SDF caught an incomplete PR reviewer surface, remediated the PR description from governed evidence with explicit permission, and detected a wrong-base PR publication issue. It made the delivery trail visible; it did not approve, merge, deploy, repair, or mutate application code.
PR #7 adopts the governed starting point in a clean controlled Rails-shaped rehearsal. Commercial work adapts this pattern to the customer's actual repo, stack, workflow, and risk profile.
The proof runs as local SDF tooling inside the controlled rehearsal. It is not hosted enforcement.
PR #8 delivers a small bounded /factory-proof change through the full governed work anatomy, showing the kind of controlled work item that can seed customer-specific operating guidance.
GTM dogfooding and Bootstrap self-assessment showed the product-learning loop: real governed work leaves evidence, reviewed lessons can be promoted through Bootstrap changes, and future receiver front-door installs can receive safer guidance. This is reviewed packaging, not autonomous policy mutation.
PR #8 uses a production-style governed PR body with prompt/run log, criteria, playbooks, preflight, risk, verification, evidence, and AI usage so reviewers can see what they are being asked to trust.
The readable PR body points reviewers to committed evidence records for audit and drill-down.
Next step
The demo shows where the path can lead. The first commercial step is a free repo-backed readiness snapshot.
We use lightweight repo signals and shared context to show whether your repo is a fit for governed AI-assisted delivery.
Rails two-PR flow
The strongest current demo is a controlled Rails-shaped rehearsal where setup lands before the bounded governed work item.
main
<- PR #7: setup governed starting point
<- PR #8: complete governed work item
Purpose: governed setup proof
Shows: a governed starting point can be adopted in a controlled Rails-shaped rehearsal
Status: draft/open controlled rehearsal proof
Purpose: completed governed work proof
Shows: a real bounded Rails change completed through the full SDF anatomy
Status: draft/open controlled rehearsal proof
Governed PR anatomy
The PR body is the reviewer decision surface. The committed files remain the audit trail.
This is reviewer context and evidence packaging. It is not automatic approval, automatic merge, or automatic trust judgement.
AI usage and cost visibility
The demo PR captures AI usage/economics evidence from local tool logs. Cost remains unavailable / not billing-grade, and no measured savings are claimed.
If capture is disabled or unavailable, SDF records unavailable values rather than inventing numbers.
reported_by_provider_through_local_tool_logs
921,936
1,213
923,149
unavailable / not billing-grade
not claimed
Completed governed work proofs
These are controlled rehearsal proofs, not a claim of production governance, all-stack coverage, or native tooling for every receiver language.
A controlled Campfire-style receiver proof shows SDF can make cloud-agent work reviewable by attaching governed evidence, checking the PR reviewer surface, catching incomplete or wrongly targeted PR publication, and remediating PR descriptions from governed evidence with explicit permission.
A governed work item has been completed end-to-end in a controlled Rails receiver.
A governed work item has been completed end-to-end in a controlled React/TypeScript-shaped receiver, with the Ruby-based SDF factory tooling running separately from the Node app.
Runtime / tooling boundary
Governed PR output modes
Capability lifecycle
The controlled rehearsal proof also includes receiver-local capability status, drift/status detection, recovery-plan preview, and runtime alignment guidance.
These are operator review tools, not automatic repair, automatic apply, hosted monitoring, or continuous monitoring.
Proof sources
These references name the controlled rehearsal proof path without adding live Bootstrap calls, GitHub API access, repo scanning, receiver mutation, hosted enforcement, or automatic PR creation.
What this does not claim
This is controlled rehearsal proof, not a claim of production customer enforcement. It shows the governed workflow, evidence shape, and review surface working in bounded receiver repos. It does not claim code correctness, hosted enforcement, automatic approval or merge, automatic repair, guaranteed correctness, security certification, billing-grade cost reporting, measured savings, or universal stack coverage.