QenSAi · AIAGF · Governance in UseEngineering review edition · 11 October 2026
Evidence brief for AI engineers and technical evaluators

Governance in use.
Review the work, decisions
and evidence.

A human-led agent system is being used to govern its own improvement. These records show how people and agents define work, challenge proposals, retain decisions, apply bounded corrections and return source-linked evidence.

Evidence through 9 October 2026 Public work in progress Source-linked review guide
The review proposition: the selected records support bounded instances of human direction, agent review, correlated communication and evidence capture. The review question is whether those records justify their specific claims, and what further tests would establish repeatability and enforcement.
01 · The underlying story

Use the governance system on real work while development continues.

The operator wanted the work itself to be inspectable: what the task was, which agent was investigating it, what another agent challenged, what required a person’s decision, and what remained unresolved.

The objective was not to make every technical gap disappear before presenting the proof of concept. The agent initially pursued technical completion beyond that objective. The person corrected the scope, and the system’s records retained both the correction and the unfinished engineering.

The October 9 report assembles this process from separate dated operations. A repaired interface, a bounded completion, three-seat communication, a corrected dialogue and a substantive proposal review are different cases with different acceptance boundaries.

Two linked records, two outcomes

The work’s oversight form carries the gap, diagnosis, remedy and acceptance. A separate proof-of-concept management record carries the walkthrough, communication landmarks and capture evidence.

Signal Capture preserves an operation and prepares an editorial return. Finishing that return does not install a repair or close the underlying technical task.

Sources: process objective, P1 · saved scope, E1 · human scope correction.

1 · PurposeHuman defines outcome and boundaries.
2 · GuidanceFind existing canon and registered functions.
3 · AssignmentTask scope → routing node → assembly → worker.
4 · ReviewDialogue, questions and decisions remain on the topic.
5 · ActionPerform the authorized work; retain the actual outcome.
6 · ReturnCapture provenance and prepare a reviewable account.

This is the documented organizing process. It is not a reconstructed single execution trace or proof that every mechanism ran in every case.

02 · Central case · 9 October 2026

Review changed a concrete proposal before implementation.

The substantive topic was preparation for a new published-prompt correction experiment. Investigation exposed missing source bindings for existing intent-classification, lexicon-resolution and pressure-resolution functions. Engineering work stayed on its own oversight form and gap list; the proof of concept captured how the people and agents handled it.

  1. Investigate existing state. The executing seat used existing canon and records to prepare three import corrections and source-to-function mappings. Main report · substantive work.
  2. Submit a concrete proposal for challenge. The governing reviewer reported testing isolated copies, conditionally accepted the three import edits, corrected the mapping and write procedure, and found fourteen affected imports rather than three. No producer was executed. E6 · retained reviewer reply.
  3. Keep further conditions inspectable. Later review removed a circular commit requirement and required audit events to refer to a real task. Three writer fixes were accepted with conditions; six ordered checks were specified for obtaining the audit-linked task. Reported review sequence.
  4. Preserve the separate human decision. At the retained Response Table readback, the operator-action row was pending and unanswered. Reviewer acceptance did not establish human approval to implement. An empty row also does not prove that no action occurred elsewhere. E9 · decision readback.
  5. Retain an observed permission boundary. A separate attempted gap-to-task link returned HTTP 403: “Link-spawned-task requires admin role”; the recorded gap was unchanged. This is one observed role refusal, not a complete security test. E4 · endpoint extract.
  6. Capture progress without inflating execution claims. The capture agent reported source-linked drafts, and later addenda entered an assembled account while the prior signal and draft stayed unchanged. These are dated reported editorial states, not independent publishing-database verification. E8 · E10.
Engineering conclusion: the retained process supports inspectable challenge, revised proposal conditions and a distinct human decision. The proposed source and database repairs are not established here as installed. The fresh published-prompt correction experiment remained open in the report.
03 · Supporting evidence

Inspect each case on its own terms.

Select an evidence group, then open the source entries under each case. Dates, evidence types and limitations stay attached to the claim.

Showing six supporting cases. The central October 9 case is above.

28–29 September 2026 · Recorded operations

A real defect became a reviewed product fix

The selected task disappeared when the consumer Desk reloaded. The owning seat traced a staged repair through an operator commit, deployment and reported hosted owner-view verification. Signal Capture retained the operation and its linked editorial return.

Supported conclusion

Product work and its capture can be connected to dated evidence. The acceptance is attributed to the owning seat and scoped to the owner view.

Review question

Ask for the exact deployed version, the before/after reproduction and acceptance artifacts. Test member access and hosted sending separately.

Inspect the source entries and limits (R1, R1C)
R1 · Task selection persistence operation

Evidence type: Dated owner evidence packet

This is the owner’s dated evidence. It does not establish member-view acceptance or hosted-send acceptance.

Retained-source identifier46951e376ae3731e8be7255271f086d17c278be611b64fcb81c64a5fe44396d6

Hash identifies retained private bytes. It does not independently verify the event or supply the withheld original.

R1C · Selection persistence capture return

Evidence type: Capture-seat readback report

This is an attributed capture-seat report. It does not make the operation an automatically captured or universal-access demonstration.

Retained-source identifiera0259025d00171547f9fd6e2167d64541d13592f8cd0a8bfb10f2f07c58dabe4

Hash identifies retained private bytes. It does not independently verify the event or supply the withheld original.

30 September 2026 · UTC · Recorded operations

Approval, completion and capture were correlated

The recorded sequence is human execution approval at 03:25:18, completion at 03:25:39 and automatic capture at 03:25:40. The capture seat reused the existing signal and prepared a draft; it did not replay the operation.

Supported conclusion

This supplies one local example of authorized completion followed by correlated capture and an attended return. The process-only path returned before model dispatch.

Review question

Inspect the task identity, approval and completion events, dedupe query and persisted capture. The timestamps describe sequence; they are not a measured latency advantage.

Inspect the source entries and limits (R2, R2C)
R2 · Authorized completion checkpoint

Evidence type: Selected original chat export; OQS-reported readback

This is a retained OQS checkpoint, not a fresh rerun. Its bounded event search does not claim to contain every event.

Retained-source identifierf1f760a1846411901f532bbf92853fd39568d44d79adfca6f7c1a75172bfc7c8

Hash identifies retained private bytes. It does not independently verify the event or supply the withheld original.

R2C · Completion-to-capture return

Evidence type: Capture-seat source, dedupe, draft and Response Table readbacks

One local completion-to-capture path; attended editorial preparation. No inference retry, autonomous repair, hosted execution or continuing coverage is established.

Retained-source identifier16533ca9932aa4b872c5fbdda0d0c78f6d2006040e7bb8a4c53e4d97ba3df9af

Hash identifies retained private bytes. It does not independently verify the event or supply the withheld original.

2 October 2026 · Recorded operations

Three seats returned answers to one work surface

For each of three seats, the person sent and armed a read-only request. The retained sequence proceeds through delivery wake, attended readiness, dispatch, reply pickup and a posted Response Table answer. Returns were recorded at 06:14:20, 06:44:20 and 07:17:45 UTC.

Supported conclusion

The shared table supported one recorded exchange per seat. A wake alone did not dispatch. The sources retain local spool evidence and an open citation-gate watcher error.

Review question

Review how send, arm, dispatch and reply are correlated; request raw transport evidence. Repeat across tasks and environments before estimating delivery reliability.

Inspect the source entries and limits (R3, R3C)
R3 · Three-seat Response Table communication trial

Evidence type: Historical OQS session report

One read-only trial per seat on one workstation. The report is historical evidence, not a current watcher-health check or proof that every request succeeds.

Retained-source identifierec3ad41a309bc500b5d39706266882a7a79282fc21c60f70e361c11d02cd0afd

Hash identifies retained private bytes. It does not independently verify the event or supply the withheld original.

R3C · Three-seat communication capture return

Evidence type: Capture-seat evidence qualification and draft return

The source describes local spool evidence without central Flight Recorder IDs and an open citation-gate watcher error. No autonomous operation or reliability rate is claimed.

Retained-source identifier4e24f1e0f87a0c77822f755c0e1d79663da766eb89eb4afbf76f337581c11348

Hash identifies retained private bytes. It does not independently verify the event or supply the withheld original.

7 October 2026 · Recorded operations

An inaccurate answer was retained and challenged

The first Relay answer invented terminology and missed the requested content. The reviewer rejected it. A revised request supplied six required beats; the next answer returned those beats but still omitted an evidence sentence and used an unsupported processing label.

Supported conclusion

Dialogue transport and attended review were recorded. The later answer was qualified editorial material. The changed request prevents this from being treated as a controlled same-prompt correction experiment.

Review question

Compare both complete requests and answers. Distinguish a Relay return, an attended saved review and a native Response Table or discussion return.

Inspect the source entries and limits (R4, R4B)
R4 · Corrected TAG Relay exchange

Evidence type: Retained request, response and attended review artifact

This demonstrates dialogue transport and attended review. It is not a controlled same-prompt experiment, independent file access, task execution or automatic insertion of a Relay answer into the Response Table.

Retained-source identifier9ee976fa5df9898d561eb852399e79a6edd39d08e2a69f4a4ae4902e1edc6375

Hash identifies retained private bytes. It does not independently verify the event or supply the withheld original.

R4B · Relay and discussion route review

Evidence type: Retained route investigation

The recorded Relay thread and discussion thread are different. Visibility of an attended review is not a saved native discussion return.

Retained-source identifier45594a7e85f72a65196bb12ca72d8193f62391cdf846cc15144b75e1cb3675ba

Hash identifies retained private bytes. It does not independently verify the event or supply the withheld original.

15 September 2026 · Earlier bounded proof

An approved application correction changed the rendered output

A terse refusal lacked rationale and safe alternatives. A correction received separate human approval. The application rendered an output that preserved the refusal and added explanation and alternatives. The raw model answer remained terse.

Supported conclusion

The receipt has matching nonempty active/rendered correction lists. Its own approval claim is unmeasured; the separate approval readback supplies that evidence. This is deterministic application rendering, not model learning.

Review question

Inspect the raw and rendered outputs, correction content, separate approval and receipt. Model execution is browser-reported rather than independently attested.

Inspect the source entries and limits (H1, H1R)
H1 · September approved application correction

Evidence type: Historical local case and separate approval readback references

The changed output was deterministic application rendering. This is not evidence of model learning, retraining or a changed raw model answer. Earlier unsuccessful attempts remain part of the record.

Retained-source identifier1e712c7cc768228eaadedc6051d6e598c12b0efe2fb0d9674164328b3e29431f

Hash identifies retained private bytes. It does not independently verify the event or supply the withheld original.

H1R · September correction receipt

Evidence type: Selected facts checked directly in a retained JSON export

Model execution is browser-reported, not independently attested. A receipt alone does not establish the approval facts.

Retained-source identifier205ab80929e209ca6e42bc5820e8e4557939ff66b5092db8e15845957fc34071

Hash identifies retained private bytes. It does not independently verify the event or supply the withheld original.

15 September 2026 · Earlier bounded proof

A held task incorporated one approved delta

A controlled case held a task, approved one new correction, reused the retained response and completed with a paired-response record. The recorded event chain contained one model dispatch. An earlier attempt failed chronology and scope conditions and remains negative evidence.

Supported conclusion

This is a different task from the application-correction case. It supports a bounded checkpoint observation with one dispatch, not a measured cost saving, latency result or general reliability rate.

Review question

Inspect the hold time, correction approval time, task identity, checkpoint and full dispatch chain. Retain the failed attempt and explain why the later chronology met acceptance.

Inspect the source entries and limits (H2)
H2 · September held-checkpoint case

Evidence type: Separate historical acceptance report with negative attempt retained

This is a different task from the application-correction case. The one-dispatch observation belongs only to this controlled checkpoint case. It is not a saving, latency or reliability result.

Retained-source identifierdc567ce642d98927d4f5f69764ac881436073ed5960ad1f22d4b859881ff577d

Hash identifies retained private bytes. It does not independently verify the event or supply the withheld original.

04 · Control model and evidence correspondence

Separate the intended controls from their observed instances.

Component / boundaryRole in the documented designWhat these records contributeNext verification
Request intake and identityCapture intent, identify the caller and establish action-specific authority.R2 records one approval sequence; E4 records one admin-role refusal. A broad A1 token-admission test is not provided.Exercise missing, expired and wrong-role credentials; distinguish admission from execution permission.
2VP Workbench, NTF guidance and oversight formRepresent the work, locate applicable governing material and bind scope and acceptance.P1 and E2–E5 connect the scope, separate work records, gap labels and saved procedure.Show the exact versioned rules consumed by one task and the authority for each transition.
Threaded task and request identityJoin assignment, reply, review and result to the work they concern.R2–R4 retain correlated operations and distinguish transport surfaces. R3 has local spool evidence without central Flight Recorder IDs.Test duplicate delivery, missing correlations, out-of-order replies and cross-topic isolation.
Response Table and human decisionKeep questions, answers, challenges and consequential decisions inspectable.Three-seat returns in R3; retained governing review and separate pending action in E9.Confirm persistence, authorization and readback under concurrent updates.
Feedback applicationApprove a bounded delta and verify its effect and provenance.H1/H1R show application-rendered correction; H2 records a distinct held-checkpoint delta.Separate raw model behavior, deterministic rendering and checkpoint reuse in every claim.
Signal Capture and evidence returnPreserve real operations; dedupe capture; prepare source-linked material for editorial review.R1C, R2C, R3C and E7–E10 retain capture returns with dated limits.Independently read the durable store and lineage; verify editorial and publication states separately.

2VP is named Two-Vector Protocol on the site. NTFs are project governance/function references. SPOC is used here for the topic’s oversight record. This brief does not infer completeness of every deeper Synapse, compatibility or execution-authority mechanism from these selected cases.

05 · Assessment

A useful process record, with a bounded evidentiary reach.

Supported now

Dated examples of human-led work; concrete agent challenge; saved communication and decisions; retained failures; correction provenance; source-linked capture.

Still open

The fresh published-prompt experiment, proposed producer installation, remaining engineering gaps and separately recorded operator decisions.

Requires new evidence

Repeatable enforcement, comprehensive permission coverage, independently attested model execution, production reliability, savings and physical robotic control.

Private-source hashes identify bytes; public package hashes identify the redacted files. Neither establishes truth by itself. Agent-reported verification is attributed. The portable public package is a selected record, not a complete audit or an independent laboratory replication.

06 · Proposed independent evaluation

Turn the review into a bounded, reproducible test.

This plan is proposed work. No new model or task experiment was run to prepare this brief.

TestFreeze before executionAcceptance evidence
Authority before actionCaller, role, task scope, rules version, permitted action and denied action.Admission and authorization outcomes; no denied side effect; independently read state before and after.
Threaded correspondenceRequest/task/thread IDs, delivery path and expected return destination.Complete event sequence; matching persisted reply; duplicate and out-of-order behavior; retained failures.
Approved correction pairPrompt, model/version, generation configuration, correction and scoring rubric. Record or control randomness.Baseline without correction; separate human approval; later run; raw and rendered outputs; matching active/rendered correction provenance. Classify which layer changed.
Held checkpointHold conditions, allowed delta, task identity and dispatch-count definition.Approval occurs after hold; only permitted delta applied; preserved response and complete dispatch chain.
Proposal / program promotionExact source revision, isolated change, behavioral tests, activation authority and rollback criteria.Review is distinct from implementation approval; verified test results; separately authorized activation; demonstrated rollback.
Capture integrityStable source reference, dedupe key, durable store, lineage and acceptance query.Independent readback, expected unique source, linked return and correct draft/publication state.

Retain unsuccessful trials. Agree the denominator before reporting rates. Repeat across representative tasks, configurations and environments; report variance and cost only when actually measured.

For robotics, define sensor validity, operating envelope, stopping behavior, timing and hardware safety separately. The reviewed series contains no physical robotic acceptance trial.

07 · Forwardable source package

Read the account. Inspect the entries. Review the data.

This presentation is a technical reading guide to the existing public proof package. It is not an additional trial. The following links give reviewers the underlying account, selected evidence and machine-readable records.

  1. Governance in use — the process and its evidence: primary process account, updated October 9.
  2. Process evidence annex: P1–P3, R1–R4B and H1–H2, with evidence classes and limits.
  3. October 9 evidence annex: E1–E10, including role refusal, reviewer conditions and pending human decision.
  4. Human scope-correction case study: supporting chapter within the broader process account.
  5. Source package guide: scope, portable file inventory and review boundaries.
  6. Before an agent acts: the guided presentation; its illustrative journey and fixed fixture are separate from the recorded operations.
  7. AIAGF proof catalog: broader historical context. This brief’s claims use the cited October 9 package.

The public sources are redacted; private originals remain with the operator. A reproducibility review may require controlled access to the relevant raw artifacts. Public narrative and historical draft readbacks do not establish the current state of every internal task.