Concept register · Theme 06 of 14 9 concepts · 93 talks
assay · concepts · the-repo-is-a-factory
The repo is a factory
Continuous AI as a third pillar beside CI/CD: cadenced agent loops inside the repository, read-only sandboxed steps, narrow countable output channels, and the pull request as the hard human gate.
assay: strongest external validation
§1What it is
The reference architecture
Agent steps run read-only, with no direct secret access, in a container; an algorithmic preload assembles the information package so the agent does not roam for inputs; output passes through narrow, countable channels — this workflow may create exactly one issue — with plan and apply separated and threat detection between the stages. Pull requests are never merged by the system. The safety economics invert in automation: better rails let the train run faster, so guardrails are what license autonomy.
Dormancy becomes velocity
A daily maintenance loop — wake on a cadence, read its memory, pick from a maintainer-shaped task list — burned down years of accumulated backlog on dormant open-source repositories and shipped multiple releases from projects that had gone quiet. The work was always there; it was labor-constrained. The conclusion generalizes: quality work that never fit the budget becomes schedulable.
Fix the gate, not the instances
When flow jams, the management move is not to repair items by hand but to add a quality gate to the factory so hundreds flow. Repositories are blocked, flowing, or idle — and blocked-on-human is a state, not a failure. The owner's job shifts to flow design.
The closest sibling, and the counterposition
A five-person company bans handwritten code outright: humans own design decisions, constraints, and invariants; a planner faces a deliberately adversarial reviewer with the loop capped at five before a human arbitrates on structured disagreement data; five CI gates — including skill quality as merge-blocking, because the agent is the primary operator — and 217 of 295 triaged issues shipped in 30 days. At the other pole, one team self-merges with no human review at all. It works for them; nobody else followed, and the divergence across the whole conference was only ever in how much evidence the gate receives.
§2The concepts in this theme
Each concept has its own page in the concept register — with sightings from every event we review, and where Assay stands on each.
- Harness engineering as a discipline established 25
- Model tiering and routing established 21
- Multi-agent organization design established 16
- Parallel fan-out versus long horizons established 13
- The harness feedback flywheel established 11
- Durable agent execution established 10
- The repository as a continuous factory established 10
- Small and specialist models corroborated 6
- Fleet visibility and the observability of failure corroborated 3
§3How Assay implements this
The desks are these loops, with names
Intake, worker, review, verification, arbitration — five cadenced roles, each producing a narrow artifact, together "automated, repetitive, collaborative, integrated, auditable," which is the Continuous AI definition restated. The closest external implementations converged on this shape independently; that is the strongest validation in the playlist.
Draft-only, human-merged
"The pull request is the hard human-in-the-loop point" has been Assay's standing rule: agent work lands as draft pull requests, a reviewer role owns the ready flip, and a human merges. Arrived at independently by every serious implementation on stage — evidence the constraint is structural rather than conservative.
Narrow outputs, enforced by permissions
Each role writes through its own verbs under its own application scope — the may-create-exactly-one-issue pattern, implemented as enforced permissions rather than declared configuration. Declaring the output budget as inspectable data is a planned tightening of the same idea.
Findings become gates
When a failure class recurs, the response is a guard, a lint, or a board check — not the same hand-fix again. That is "fix the gate, not the instances," and it is where the registers, the guardrail layer, and the feedback loop meet.
Deliberately not adopted
Auto-merge on green: the human gate is a posture, not a missing feature — loosening it for narrow classes would first need the sibling's depth of automated gating, and that trade is not warranted here. And the agent zoo — hundreds of one-off workflows — would spend the trust roster, the token scoping, and the review ownership that five comprehensible roles preserve.
§4Talks that cover this theme
#11The Agentic Repository Automation RevolutionDon Syme, GitHub Next
#34
#28Piece of PIMatthias Lübken
#20More software, faster: Odevo’s AI Native transformationDaniel Jones, re:cinq; Tomasz Maj, Odevo
#06State of Play: AI Coding AssistantsBirgitta Böckeler, Thoughtworks
#039
#26Token costs are explodingLuke Marsden, HelixML
#10Stop Maintaining, Start EvolvingKatie Roberts, Nearform
8 of 93 talks shown — the ones that reach the most concepts in this theme. Every sighting, per talk, is on the concept pages above.