Two-role pipeline: reasoning architect + format-specialist editor — 85% SWE-bench.
Recent activity
Version cuts and proof, newest first — the living track record.
Spec sheet
The benchmark fields — designed for comparison across teams.
- Topology
- Pipeline
- Agent count
- 2
- Platform
- Aider
- Runs on
- Aider ×2
- Industries
- software-delivery
- Task kinds
- code-editingbug-fixingrefactoring
- Trust tier
- Self-Reported
- Proof entries
- 1
Topology & roster
Pipeline (two-stage). Architect receives the task and produces a natural-language plan of changes. Editor receives the plan and applies edits in the required diff format. One-directional: Architect does not see Editor output unless a retry is triggered. The Architect is model-agnostic; any strong reasoning model can fill the role.
System wiring
Node details
Typical Pipeline layout — schematic, not verified wiring
HumanHuman operatorHuman gate
- Tool
- Human operator
- Autonomy
- Human-gated
- directs → Stage 1 agent
BuilderStage 1 agent
- Tool
- Stage 1 agent
- Autonomy
- Runs autonomously
- hands off to → Stage 2 agent
- directs ← Human operator
BuilderStage 2 agent
- Tool
- Stage 2 agent
- Autonomy
- Runs autonomously
- hands off to → QA reviewer
- hands off to ← Stage 1 agent
QAQA reviewer
- Tool
- QA reviewer
- Autonomy
- Runs autonomously
- delivers to → Output artifact
- hands off to ← Stage 2 agent
ResourceOutput artifact
- Tool
- Output artifact
- Autonomy
- Runs autonomously
- delivers to ← QA reviewer
How a typical Pipeline team handles a task
Typical Pipeline layout — schematic, not verified wiring
Task arrives
Human operator directs Stage 1 agent.
The builders execute
Stage 1 agent and Stage 2 agent build the work.
Independent review gates the work
QA reviewer reviews the work. This reviewer is autonomous and separate from the agent that built the work, so the check is independent of its author.
The artifact lands
The artifact lands in Output artifact: QA reviewer contributes via "delivers to".
Human holds the last word
Human operator holds final approval.
Replicate a typical Pipeline setup
Typical Pipeline layout — schematic, not verified wiring
Ingredients
- HumanHuman operator
- BuilderStage 1 agent
- BuilderStage 2 agent
- QAQA reviewer
- ResourceOutput artifact
Setup order
- 1.Provision the substrate: Output artifact.
- 2.Wire Stage 1 agent: it receives "directs" from Human operator and sends "hands off to" to Stage 2 agent. Wire Stage 2 agent: it receives "hands off to" from Stage 1 agent and sends "hands off to" to QA reviewer. Wire QA reviewer: it receives "hands off to" from Stage 2 agent.
- 3.Give QA reviewer an independent workspace/verdict channel: "delivers to" to Output artifact.
- 4.Declare the human gate: Human operator holds final approval.
Performance metrics
Windowed metrics with provenance. [unknown] means it was not tracked — an honest hole beats an invented figure.
o1-preview (architect) + o1-mini (editor). Source: aider.chat/2024/09/26/architect.html [evidence_linked]
Claude 3.5 Sonnet as both architect and editor. Source: aider.chat/2024/09/26/architect.html [evidence_linked]
Token economics
Cost transparency is part of the honesty architecture. [unknown] means it was not tracked — not that it is zero.
Blueprint
Operational DNA — why it works, how it was built, and how it is overseen. Not files for sale; knowledge of the design.
Separating reasoning from edit-format compliance removes conflicting objectives from a single model. The architect can focus entirely on what to change; the editor focuses entirely on how to format the output. This enables using a top-tier reasoning model cost-effectively since the architect's output is natural language, not code diffs.
Aider open-source CLI. Architect model specified separately from editor model in config. Tested combinations include: o1-preview + o1-mini (85.0% SWE-bench), Claude 3.5 Sonnet as both roles (80.5%), Claude 3.5 Sonnet (architect) + various editors. Model costs differ significantly between architect and editor — o1-mini is ~10× cheaper than o1-preview.
User reviews changes via Aider's standard diff review workflow. No autonomous loop — Aider operates in a human-on-the-loop mode where each set of changes is presented for confirmation. Source: Aider blog.
Proof (1)
The team's shared track record — tasks, incidents, lessons, milestones. Per-entry provenance tags are always visible.
- ArtifactSep 26, 2024evidence-linked
Aider architect/editor mode blog post published
o1-preview (architect) + o1-mini (editor) = 85.0% on SWE-bench. Documents the separation of reasoning from edit-format compliance as a key performance lever.
https://aider.chat/2024/09/26/architect.html
Sign in to add a proof entry.
Sign inAttestations (0)
Named third-party statements from people with first-hand experience. Attestations are what separates Peer-Attested from Evidence-Linked.
No attestations yet. Worked with this configuration or agent? Attest to it using the form below — attestations are named third-party statements and are what separates Peer-Attested from Evidence-Linked.
Sign in to attest to this team.
Sign in